{
"schema": 1,
"id": "llm-apis",
"title": "LLM API pricing and rate limits",
"updated": "2026-10-30",
"license": "CC BY 4.0, link to the directory page",
"source": "https://getstackversus.com/limits/llm-apis",
"tools": [
{
"id": "openai-api",
"name": "OpenAI API",
"vendor": "OpenAI",
"category": "llm-api",
"url": "https://openai.com/api/",
"checked": "2026-10-30",
"sources": {
"pricing": {
"name": "Pricing | OpenAI API",
"url": "https://platform.openai.com/docs/pricing"
},
"rate_limits": {
"name": "Rate limits | OpenAI API",
"url": "https://platform.openai.com/docs/guides/rate-limits"
},
"models": {
"name": "Models | OpenAI API",
"url": "https://developers.openai.com/api/docs/models"
},
"batch": {
"name": "Batch API | OpenAI API",
"url": "https://developers.openai.com/api/docs/guides/batch"
},
"reasoning": {
"name": "Reasoning models | OpenAI API",
"url": "https://developers.openai.com/api/docs/guides/reasoning"
},
"spend_limits": {
"name": "Spend limits | OpenAI API",
"url": "https://developers.openai.com/api/docs/guides/spend-limits"
},
"latest_model": {
"name": "Using GPT-6 | OpenAI API",
"url": "https://developers.openai.com/api/docs/guides/latest-model"
},
"marketing_pricing": {
"name": "Pricing | OpenAI",
"url": "https://openai.com/api/pricing/"
}
},
"unit": {
"tag": "Per 1M tokens",
"definition": "Prices per 1M tokens.",
"source": "pricing",
"quote": "Prices per 1M tokens."
},
"free": {
"summary": "Free usage tier available to users in an allowed geography, with a $100/month usage limit. No trial credit amount is stated.",
"published": true,
"source": "rate_limits",
"quote": "Free | User must be in an allowed geography | $100 / month"
},
"plans": [
{
"id": "free",
"name": "Free",
"priceUsd": null,
"priceNote": "No purchase required; pay-as-you-go token prices apply",
"billing": "usage",
"included": "Qualification: user must be in an allowed geography. Usage limit: $100 / month.",
"source": "rate_limits",
"quote": "Free | User must be in an allowed geography | $100 / month",
"sourceUrl": "https://platform.openai.com/docs/guides/rate-limits"
},
{
"id": "build",
"name": "Build",
"priceUsd": 5,
"priceNote": "Unlocked at $5 in total credit purchases",
"billing": "usage",
"included": "Usage limit $500 / month. Astra, Sol, Terra: 5,000 RPM, 1,000,000 TPM. Luna: 5,000 RPM, 2,000,000 TPM.",
"source": "rate_limits",
"quote": "Build | $5 in total credit purchases | $500 / month",
"sourceUrl": "https://platform.openai.com/docs/guides/rate-limits"
},
{
"id": "launch",
"name": "Launch",
"priceUsd": 100,
"priceNote": "Unlocked at $100 in total credit purchases",
"billing": "usage",
"included": "Usage limit $5,000 / month. Astra, Sol, Terra: 10,000 RPM, 4,000,000 TPM. Luna: 10,000 RPM, 10,000,000 TPM.",
"source": "rate_limits",
"quote": "Launch | $100 in total credit purchases | $5,000 / month",
"sourceUrl": "https://platform.openai.com/docs/guides/rate-limits"
},
{
"id": "grow",
"name": "Grow",
"priceUsd": 500,
"priceNote": "Unlocked at $500 in total credit purchases",
"billing": "usage",
"included": "Usage limit $200,000 / month. Astra, Sol, Terra: 15,000 RPM, 40,000,000 TPM. Luna: 30,000 RPM, 180,000,000 TPM.",
"source": "rate_limits",
"quote": "Grow | $500 in total credit purchases | $200,000 / month",
"sourceUrl": "https://platform.openai.com/docs/guides/rate-limits"
}
],
"rates": [
{
"item": "GPT-6 Astra (gpt-6-astra) input, Standard",
"value": "$10.00 per 1M tokens",
"numeric": 10,
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "gpt-6-astra | $10.00 | $50.00 | $1.00 | $12.50 | $25.00",
"verified": true,
"sourceUrl": "https://platform.openai.com/docs/pricing"
},
{
"item": "GPT-6 Astra (gpt-6-astra) output, Standard",
"value": "$50.00 per 1M tokens",
"numeric": 50,
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "gpt-6-astra | $10.00 | $50.00 | $1.00 | $12.50 | $25.00",
"verified": true,
"sourceUrl": "https://platform.openai.com/docs/pricing"
},
{
"item": "GPT-6 Astra (gpt-6-astra) cached input, Standard",
"value": "$1.00 per 1M tokens",
"numeric": 1,
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "gpt-6-astra | $10.00 | $50.00 | $1.00 | $12.50 | $25.00",
"verified": true,
"sourceUrl": "https://platform.openai.com/docs/pricing"
},
{
"item": "GPT-6 Astra (gpt-6-astra) prompt cache write, 30m / 12h",
"value": "$12.50 (30m write) / $25.00 (12h write) per 1M tokens",
"numeric": 12.5,
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "gpt-6-astra | $10.00 | $50.00 | $1.00 | $12.50 | $25.00",
"verified": true,
"sourceUrl": "https://platform.openai.com/docs/pricing"
},
{
"item": "GPT-6.1 Sol (gpt-6.1-sol) input, Standard",
"value": "$2.00 per 1M tokens",
"numeric": 2,
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "gpt-6.1-sol | $2.00 | $10.00 | $0.10 | $2.50 | $5.00",
"verified": true,
"sourceUrl": "https://platform.openai.com/docs/pricing"
},
{
"item": "GPT-6.1 Sol (gpt-6.1-sol) output, Standard",
"value": "$10.00 per 1M tokens",
"numeric": 10,
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "gpt-6.1-sol | $2.00 | $10.00 | $0.10 | $2.50 | $5.00",
"verified": true,
"sourceUrl": "https://platform.openai.com/docs/pricing"
},
{
"item": "GPT-6.1 Sol (gpt-6.1-sol) cached input, Standard",
"value": "$0.10 per 1M tokens",
"numeric": 0.1,
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "gpt-6.1-sol | $2.00 | $10.00 | $0.10 | $2.50 | $5.00",
"verified": true,
"sourceUrl": "https://platform.openai.com/docs/pricing"
},
{
"item": "GPT-6.1 Sol (gpt-6.1-sol) prompt cache write, 30m / 12h",
"value": "$2.50 (30m write) / $5.00 (12h write) per 1M tokens",
"numeric": 2.5,
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "gpt-6.1-sol | $2.00 | $10.00 | $0.10 | $2.50 | $5.00",
"verified": true,
"sourceUrl": "https://platform.openai.com/docs/pricing"
},
{
"item": "GPT-6.1 Terra (gpt-6.1-terra) input, Standard",
"value": "$1.00 per 1M tokens",
"numeric": 1,
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "gpt-6.1-terra | $1.00 | $5.00 | $0.05 | $1.25 | $2.50",
"verified": true,
"sourceUrl": "https://platform.openai.com/docs/pricing"
},
{
"item": "GPT-6.1 Terra (gpt-6.1-terra) output, Standard",
"value": "$5.00 per 1M tokens",
"numeric": 5,
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "gpt-6.1-terra | $1.00 | $5.00 | $0.05 | $1.25 | $2.50",
"verified": true,
"sourceUrl": "https://platform.openai.com/docs/pricing"
},
{
"item": "GPT-6.1 Terra (gpt-6.1-terra) cached input, Standard",
"value": "$0.05 per 1M tokens",
"numeric": 0.05,
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "gpt-6.1-terra | $1.00 | $5.00 | $0.05 | $1.25 | $2.50",
"verified": true,
"sourceUrl": "https://platform.openai.com/docs/pricing"
},
{
"item": "GPT-6.1 Terra (gpt-6.1-terra) prompt cache write, 30m / 12h",
"value": "$1.25 (30m write) / $2.50 (12h write) per 1M tokens",
"numeric": 1.25,
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "gpt-6.1-terra | $1.00 | $5.00 | $0.05 | $1.25 | $2.50",
"verified": true,
"sourceUrl": "https://platform.openai.com/docs/pricing"
},
{
"item": "GPT-6 Luna (gpt-6-luna) input, Standard",
"value": "$0.10 per 1M tokens",
"numeric": 0.1,
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "gpt-6-luna | $0.10 | $0.50 | $0.01 | $0.125 | $0.25",
"verified": true,
"sourceUrl": "https://platform.openai.com/docs/pricing"
},
{
"item": "GPT-6 Luna (gpt-6-luna) output, Standard",
"value": "$0.50 per 1M tokens",
"numeric": 0.5,
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "gpt-6-luna | $0.10 | $0.50 | $0.01 | $0.125 | $0.25",
"verified": true,
"sourceUrl": "https://platform.openai.com/docs/pricing"
},
{
"item": "GPT-6 Luna (gpt-6-luna) cached input, Standard",
"value": "$0.01 per 1M tokens",
"numeric": 0.01,
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "gpt-6-luna | $0.10 | $0.50 | $0.01 | $0.125 | $0.25",
"verified": true,
"sourceUrl": "https://platform.openai.com/docs/pricing"
},
{
"item": "GPT-6 Luna (gpt-6-luna) prompt cache write, 30m / 12h",
"value": "$0.125 (30m write) / $0.25 (12h write) per 1M tokens",
"numeric": 0.125,
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "gpt-6-luna | $0.10 | $0.50 | $0.01 | $0.125 | $0.25",
"verified": true,
"sourceUrl": "https://platform.openai.com/docs/pricing"
},
{
"item": "Batch API discount",
"value": "50% cost discount compared to synchronous APIs; each batch completes within 24 hours",
"numeric": 50,
"unit": "% off",
"published": true,
"source": "batch",
"quote": "Better cost efficiency: 50% cost discount compared to synchronous APIs",
"verified": true,
"sourceUrl": "https://developers.openai.com/api/docs/guides/batch"
},
{
"item": "gpt-6-astra input / output, Flex/Batch",
"value": "$5.00 input / $25.00 output / $0.50 cached input per 1M tokens",
"numeric": 5,
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "gpt-6-astra | $5.00 | $25.00 | $0.50 | $6.25 | $12.50",
"verified": true,
"sourceUrl": "https://platform.openai.com/docs/pricing"
},
{
"item": "gpt-6.1-sol input / output, Flex/Batch",
"value": "$1.00 input / $5.00 output / $0.05 cached input per 1M tokens",
"numeric": 1,
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "gpt-6.1-sol | $1.00 | $5.00 | $0.05 | $1.25 | $2.50",
"verified": true,
"sourceUrl": "https://platform.openai.com/docs/pricing"
},
{
"item": "gpt-6.1-terra input / output, Flex/Batch",
"value": "$0.50 input / $2.50 output / $0.025 cached input per 1M tokens",
"numeric": 0.5,
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "gpt-6.1-terra | $0.50 | $2.50 | $0.025 | $0.625 | $1.25",
"verified": true,
"sourceUrl": "https://platform.openai.com/docs/pricing"
},
{
"item": "gpt-6-luna input / output, Flex/Batch",
"value": "$0.05 input / $0.25 output / $0.005 cached input per 1M tokens",
"numeric": 0.05,
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "gpt-6-luna | $0.05 | $0.25 | $0.005 | $0.0625 | $0.125",
"verified": true,
"sourceUrl": "https://platform.openai.com/docs/pricing"
},
{
"item": "gpt-6-astra input / output, Fast",
"value": "$20.00 input / $100.00 output / $2.00 cached input per 1M tokens",
"numeric": 20,
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "gpt-6-astra | $20.00 | $100.00 | $2.00 | $25.00 | $50.00",
"verified": true,
"sourceUrl": "https://platform.openai.com/docs/pricing"
},
{
"item": "gpt-6.1-sol input / output, Fast",
"value": "$4.00 input / $20.00 output / $0.20 cached input per 1M tokens",
"numeric": 4,
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "gpt-6.1-sol | $4.00 | $20.00 | $0.20 | $5.00 | $10.00",
"verified": true,
"sourceUrl": "https://platform.openai.com/docs/pricing"
},
{
"item": "gpt-6.1-terra input / output, Fast",
"value": "$2.00 input / $10.00 output / $0.10 cached input per 1M tokens",
"numeric": 2,
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "gpt-6.1-terra | $2.00 | $10.00 | $0.10 | $2.50 | $5.00",
"verified": true,
"sourceUrl": "https://platform.openai.com/docs/pricing"
},
{
"item": "gpt-6-luna input / output, Fast",
"value": "$0.20 input / $1.00 output / $0.02 cached input per 1M tokens",
"numeric": 0.2,
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "gpt-6-luna | $0.20 | $1.00 | $0.02 | $0.25 | $0.50",
"verified": true,
"sourceUrl": "https://platform.openai.com/docs/pricing"
},
{
"item": "gpt-6-astra input / output, Ultrafast",
"value": "$60.00 input / $300.00 output / $6.00 cached input per 1M tokens",
"numeric": 60,
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "gpt-6-astra | $60.00 | $300.00 | $6.00 | $75.00 | $150.00",
"verified": true,
"sourceUrl": "https://platform.openai.com/docs/pricing"
},
{
"item": "gpt-6.1-sol input / output, Ultrafast",
"value": "$12.00 input / $60.00 output / $0.60 cached input per 1M tokens",
"numeric": 12,
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "gpt-6.1-sol | $12.00 | $60.00 | $0.60 | $15.00 | $30.00",
"verified": true,
"sourceUrl": "https://platform.openai.com/docs/pricing"
},
{
"item": "GPT-6 Astra context window / max output",
"value": "1.05M context window; 128K max output tokens",
"numeric": 1050000,
"unit": "tokens",
"published": true,
"source": "models",
"quote": "gpt-6-astra ... Max output 128K tokens Context window 1.05M",
"verified": true,
"sourceUrl": "https://developers.openai.com/api/docs/models"
},
{
"item": "GPT-6.1 Sol context window / max output",
"value": "1.05M context window; 128K max output tokens",
"numeric": 1050000,
"unit": "tokens",
"published": true,
"source": "models",
"quote": "gpt-6.1-sol ... Max output 128K tokens Context window 1.05M",
"verified": true,
"sourceUrl": "https://developers.openai.com/api/docs/models"
},
{
"item": "GPT-6.1 Terra context window / max output",
"value": "1.05M context window; 128K max output tokens",
"numeric": 1050000,
"unit": "tokens",
"published": true,
"source": "models",
"quote": "gpt-6.1-terra ... Max output 128K tokens Context window 1.05M",
"verified": true,
"sourceUrl": "https://developers.openai.com/api/docs/models"
},
{
"item": "GPT-6 Luna context window / max output",
"value": "1.05M context window; 128K max output tokens",
"numeric": 1050000,
"unit": "tokens",
"published": true,
"source": "models",
"quote": "gpt-6-luna ... Max output 128K tokens Context window 1.05M",
"verified": true,
"sourceUrl": "https://developers.openai.com/api/docs/models"
},
{
"item": "Rate limit, Build tier, Astra/Sol/Terra",
"value": "5,000 RPM; 1,000,000 TPM",
"numeric": 5000,
"unit": "RPM",
"published": true,
"source": "rate_limits",
"quote": "Build | Astra, Sol, Terra | 5,000 | 1,000,000",
"verified": true,
"sourceUrl": "https://platform.openai.com/docs/guides/rate-limits"
},
{
"item": "Rate limit, Build tier, Luna",
"value": "5,000 RPM; 2,000,000 TPM",
"numeric": 5000,
"unit": "RPM",
"published": true,
"source": "rate_limits",
"quote": "| Luna | 5,000 | 2,000,000",
"verified": true,
"sourceUrl": "https://platform.openai.com/docs/guides/rate-limits"
},
{
"item": "Rate limit, Launch tier, Astra/Sol/Terra",
"value": "10,000 RPM; 4,000,000 TPM",
"numeric": 10000,
"unit": "RPM",
"published": true,
"source": "rate_limits",
"quote": "Launch | Astra, Sol, Terra | 10,000 | 4,000,000",
"verified": true,
"sourceUrl": "https://platform.openai.com/docs/guides/rate-limits"
},
{
"item": "Rate limit, Launch tier, Luna",
"value": "10,000 RPM; 10,000,000 TPM",
"numeric": 10000,
"unit": "RPM",
"published": true,
"source": "rate_limits",
"quote": "| Luna | 10,000 | 10,000,000",
"verified": true,
"sourceUrl": "https://platform.openai.com/docs/guides/rate-limits"
},
{
"item": "Rate limit, Grow tier, Astra/Sol/Terra",
"value": "15,000 RPM; 40,000,000 TPM",
"numeric": 15000,
"unit": "RPM",
"published": true,
"source": "rate_limits",
"quote": "Grow | Astra, Sol, Terra | 15,000 | 40,000,000",
"verified": true,
"sourceUrl": "https://platform.openai.com/docs/guides/rate-limits"
},
{
"item": "Rate limit, Grow tier, Luna",
"value": "30,000 RPM; 180,000,000 TPM",
"numeric": 30000,
"unit": "RPM",
"published": true,
"source": "rate_limits",
"quote": "| Luna | 30,000 | 180,000,000",
"verified": true,
"sourceUrl": "https://platform.openai.com/docs/guides/rate-limits"
},
{
"item": "Rate limit, Free tier",
"value": "To view the limits for each model at your usage tier, go to Settings > Organization > Limits",
"unit": "RPM/TPM",
"published": false,
"source": "rate_limits",
"quote": "To view the limits for each model at your usage tier, go to Settings > Organization > Limits and review Rate limits.",
"verified": true,
"sourceUrl": "https://platform.openai.com/docs/guides/rate-limits"
},
{
"item": "Requests per day (RPD) per tier",
"value": "RPD is listed as a rate-limit metric; no per-tier RPD figures published",
"unit": "RPD",
"published": false,
"source": "rate_limits",
"quote": "Rate limits use metrics such as RPM (requests per minute), RPD (requests per day), TPM (tokens per minute), TPD (tokens per day)",
"verified": true,
"sourceUrl": "https://platform.openai.com/docs/guides/rate-limits"
},
{
"item": "Realtime audio tokens, gpt-realtime-2.1",
"value": "$32.00 input / $64.00 output / $0.40 cached input per 1M audio tokens",
"numeric": 32,
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "gpt-realtime-2.1 | Audio | $32.00 | $64.00 | $0.40",
"verified": true,
"sourceUrl": "https://platform.openai.com/docs/pricing"
},
{
"item": "Image generation tokens, gpt-image-2.5-sunburst (Standard)",
"value": "$8.00 image input / $30.00 image output / $2.00 cached per 1M tokens; text input $5.00",
"numeric": 8,
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "gpt-image-2.5-sunburst | Image | $8.00 | $30.00 | $2.00",
"verified": true,
"sourceUrl": "https://platform.openai.com/docs/pricing"
},
{
"item": "Web search tool calls",
"value": "$10.00 / 1k calls + search content tokens billed at model rates",
"numeric": 10,
"unit": "USD/1k calls",
"published": true,
"source": "pricing",
"quote": "Web search (all models) | $10.00 / 1k calls + Search content tokens billed at model rates.",
"verified": true,
"sourceUrl": "https://platform.openai.com/docs/pricing"
}
],
"overage": {
"policy": "hard-stop",
"summary": "Usage is paid from prepaid credits bought in advance. If requests fail because the organization has used up its prepaid credits, add credits. Optional hard spend limits make affected requests return a 429 error.",
"source": "spend_limits",
"quote": "whether the organization exhausted its prepaid credits."
},
"gotchas": [
{
"title": "Reasoning tokens billed as output",
"detail": "Reasoning tokens are not visible via the API, but they take up space in the context window and are billed as output tokens.",
"source": "reasoning",
"quote": "While reasoning tokens are not visible via the API, they still occupy space in the model’s context window and are billed as output tokens.",
"sourceUrl": "https://developers.openai.com/api/docs/guides/reasoning"
},
{
"title": "Prompt cache writes are billed above input price",
"detail": "Prompt caching has separate 30-minute and 12-hour write prices, e.g. gpt-6-astra $12.50 (30m) and $25.00 (12h) per 1M tokens vs $10.00 input.",
"source": "pricing",
"quote": "gpt-6-astra | $10.00 | $50.00 | $1.00 | $12.50 | $25.00",
"sourceUrl": "https://platform.openai.com/docs/pricing"
},
{
"title": "Data residency and FedRAMP uplift",
"detail": "Regional processing (data residency) endpoints cost 10% more for models released on or after March 5, 2026. FedRAMP endpoints also cost 10% more.",
"source": "pricing",
"quote": "Regional processing (data residency) endpoints are charged a 10% uplift for models released on or after March 5, 2026.",
"sourceUrl": "https://platform.openai.com/docs/pricing"
},
{
"title": "Separate long-context rate limit",
"detail": "Long-context models have a separate rate limit for long-context requests, shown in the developer console.",
"source": "rate_limits",
"quote": "For long context models like GPT-5.5, there is a separate rate limit for long context requests.",
"sourceUrl": "https://platform.openai.com/docs/guides/rate-limits"
},
{
"title": "OpenAI-approved monthly usage limit",
"detail": "Each organization has a monthly usage limit approved by OpenAI, separate from the spend limits you set yourself.",
"source": "rate_limits",
"quote": "OpenAI sets an approved monthly usage limit for each organization. This is separate from the spend limits that you can configure",
"sourceUrl": "https://platform.openai.com/docs/guides/rate-limits"
},
{
"title": "Hard spend limit can be slightly exceeded",
"detail": "Hard spend limits do not take effect instantly, so recorded spend can go slightly over the amount you set.",
"source": "spend_limits",
"quote": "Enforcement is not instantaneous, so recorded spend can slightly exceed the configured amount.",
"sourceUrl": "https://developers.openai.com/api/docs/guides/spend-limits"
},
{
"title": "Tool tokens billed at model rates",
"detail": "Tokens used by built-in tools are billed at the chosen model's per-token rates, on top of per-call tool fees.",
"source": "pricing",
"quote": "Tokens used for built-in tools are billed at the chosen model's per-token rates.",
"sourceUrl": "https://platform.openai.com/docs/pricing"
},
{
"title": "Ramp-rate throttling",
"detail": "A slow_down error can happen even within your RPM and TPM limits if traffic grows too quickly. Above 1M TPM, increase traffic by no more than 50% every 15 minutes.",
"source": "rate_limits",
"quote": "A slow_down error can occur even when your traffic is within its requests-per-minute and tokens-per-minute limits.",
"sourceUrl": "https://platform.openai.com/docs/guides/rate-limits"
},
{
"title": "Priority processing renamed Fast mode",
"detail": "Priority processing was renamed Fast mode on July 30, 2026. Fast and Ultrafast are priced above Standard.",
"source": "pricing",
"quote": "Priority processing was renamed Fast mode on July 30, 2026.",
"sourceUrl": "https://platform.openai.com/docs/pricing"
}
]
},
{
"id": "anthropic-api",
"name": "Claude API",
"vendor": "Anthropic",
"category": "llm-api",
"url": "https://claude.com/platform/api",
"checked": "2026-10-30",
"sources": {
"pricing_page": {
"name": "Pricing (claude.com/pricing, API tab)",
"url": "https://www.anthropic.com/pricing"
},
"docs_pricing": {
"name": "Pricing - Claude Platform Docs",
"url": "https://docs.claude.com/en/docs/about-claude/pricing"
},
"rate_limits": {
"name": "Rate limits - Claude Platform Docs",
"url": "https://docs.anthropic.com/en/api/rate-limits"
},
"models": {
"name": "Models overview - Claude Platform Docs",
"url": "https://platform.claude.com/docs/en/models/overview"
},
"thinking": {
"name": "Thinking - Claude Platform Docs",
"url": "https://platform.claude.com/docs/en/build-with-claude/thinking"
},
"vision": {
"name": "Vision (images) - Claude Platform Docs",
"url": "https://platform.claude.com/docs/en/build-with-claude/vision"
},
"api_credits": {
"name": "API credits for Max and Team plans - Claude Platform Docs",
"url": "https://platform.claude.com/docs/en/about-claude/api-credits-for-subscribers"
}
},
"unit": {
"tag": "Per million tokens (MTok)",
"definition": "Prices are per million tokens (MTok), in USD. Tokens are pieces of text that models process.",
"source": "docs_pricing",
"quote": "Tokens are pieces of text that models process. How many tokens the same text produces depends on the model’s tokenizer, the language, and the type of content."
},
"free": {
"summary": "New users get a small amount of free credits to test the API. The amount is not stated.",
"published": false,
"source": "docs_pricing",
"quote": "New users receive a small amount of free credits to test the API. Contact sales for information about extended trials for enterprise evaluation."
},
"plans": [
{
"id": "start",
"name": "Start tier",
"priceUsd": null,
"priceNote": "Pay-as-you-go at per-token rates",
"billing": "usage",
"included": "Monthly spend cap of $500 USD",
"source": "rate_limits",
"quote": "| Start | $500 USD |",
"sourceUrl": "https://docs.anthropic.com/en/api/rate-limits"
},
{
"id": "build",
"name": "Build tier",
"priceUsd": null,
"priceNote": "Pay-as-you-go at per-token rates",
"billing": "usage",
"included": "Monthly spend cap of $1,000 USD",
"source": "rate_limits",
"quote": "| Build | $1,000 USD |",
"sourceUrl": "https://docs.anthropic.com/en/api/rate-limits"
},
{
"id": "scale",
"name": "Scale tier",
"priceUsd": null,
"priceNote": "Pay-as-you-go at per-token rates",
"billing": "usage",
"included": "Monthly spend cap of $200,000 USD",
"source": "rate_limits",
"quote": "| Scale | $200,000 USD |",
"sourceUrl": "https://docs.anthropic.com/en/api/rate-limits"
},
{
"id": "custom",
"name": "Custom tier",
"priceUsd": null,
"priceNote": "Contact sales",
"billing": "usage",
"included": "No monthly spend cap; limits are arranged with the account team.",
"source": "rate_limits",
"quote": "Organizations on the Custom tier have no monthly spend cap; limits are arranged with their account team.",
"sourceUrl": "https://docs.anthropic.com/en/api/rate-limits"
}
],
"rates": [
{
"item": "Claude Fable 5.1 input",
"value": "$10 / MTok",
"numeric": 10,
"unit": "USD/1M input tokens",
"published": true,
"source": "docs_pricing",
"quote": "Claude Fable 5.1 ... | $10 / MTok | $50 / MTok | $12.50 / MTok | $20 / MTok | $0.25 / MTok",
"verified": true,
"sourceUrl": "https://docs.claude.com/en/docs/about-claude/pricing"
},
{
"item": "Claude Fable 5.1 output",
"value": "$50 / MTok",
"numeric": 50,
"unit": "USD/1M output tokens",
"published": true,
"source": "docs_pricing",
"quote": "Claude Fable 5.1 ... | $10 / MTok | $50 / MTok | $12.50 / MTok | $20 / MTok | $0.25 / MTok",
"verified": true,
"sourceUrl": "https://docs.claude.com/en/docs/about-claude/pricing"
},
{
"item": "Claude Fable 5.1 cache write (5-minute)",
"value": "$12.50 / MTok",
"numeric": 12.5,
"unit": "USD/1M tokens",
"published": true,
"source": "docs_pricing",
"quote": "Claude Fable 5.1 ... | $10 / MTok | $50 / MTok | $12.50 / MTok | $20 / MTok | $0.25 / MTok",
"verified": true,
"sourceUrl": "https://docs.claude.com/en/docs/about-claude/pricing"
},
{
"item": "Claude Fable 5.1 cache write (1-hour)",
"value": "$20 / MTok",
"numeric": 20,
"unit": "USD/1M tokens",
"published": true,
"source": "docs_pricing",
"quote": "Claude Fable 5.1 ... | $10 / MTok | $50 / MTok | $12.50 / MTok | $20 / MTok | $0.25 / MTok",
"verified": true,
"sourceUrl": "https://docs.claude.com/en/docs/about-claude/pricing"
},
{
"item": "Claude Fable 5.1 cached input (cache hits and refreshes)",
"value": "$0.25 / MTok",
"numeric": 0.25,
"unit": "USD/1M tokens",
"published": true,
"source": "docs_pricing",
"quote": "On Claude Fable 5.1 and Claude Mythos 5.1, a cache hit costs 2.5% of the standard input price ($0.25 USD per million tokens).",
"verified": true,
"sourceUrl": "https://docs.claude.com/en/docs/about-claude/pricing"
},
{
"item": "Claude Fable 5.1 batch input",
"value": "$5 / MTok",
"numeric": 5,
"unit": "USD/1M input tokens",
"published": true,
"source": "docs_pricing",
"quote": "Claude Fable 5.1 ... | $5 / MTok | $25 / MTok",
"verified": true,
"sourceUrl": "https://docs.claude.com/en/docs/about-claude/pricing"
},
{
"item": "Claude Fable 5.1 batch output",
"value": "$25 / MTok",
"numeric": 25,
"unit": "USD/1M output tokens",
"published": true,
"source": "docs_pricing",
"quote": "Claude Fable 5.1 ... | $5 / MTok | $25 / MTok",
"verified": true,
"sourceUrl": "https://docs.claude.com/en/docs/about-claude/pricing"
},
{
"item": "Claude Opus 5.5 input",
"value": "$4 / MTok",
"numeric": 4,
"unit": "USD/1M input tokens",
"published": true,
"source": "docs_pricing",
"quote": "Claude Opus 5.5 ... | $4 / MTok | $20 / MTok | $5 / MTok | $8 / MTok | $0.20 / MTok",
"verified": true,
"sourceUrl": "https://docs.claude.com/en/docs/about-claude/pricing"
},
{
"item": "Claude Opus 5.5 output",
"value": "$20 / MTok",
"numeric": 20,
"unit": "USD/1M output tokens",
"published": true,
"source": "docs_pricing",
"quote": "Claude Opus 5.5 ... | $4 / MTok | $20 / MTok | $5 / MTok | $8 / MTok | $0.20 / MTok",
"verified": true,
"sourceUrl": "https://docs.claude.com/en/docs/about-claude/pricing"
},
{
"item": "Claude Opus 5.5 cache write (5-minute)",
"value": "$5 / MTok",
"numeric": 5,
"unit": "USD/1M tokens",
"published": true,
"source": "docs_pricing",
"quote": "Claude Opus 5.5 ... | $4 / MTok | $20 / MTok | $5 / MTok | $8 / MTok | $0.20 / MTok",
"verified": true,
"sourceUrl": "https://docs.claude.com/en/docs/about-claude/pricing"
},
{
"item": "Claude Opus 5.5 cache write (1-hour)",
"value": "$8 / MTok",
"numeric": 8,
"unit": "USD/1M tokens",
"published": true,
"source": "docs_pricing",
"quote": "Claude Opus 5.5 ... | $4 / MTok | $20 / MTok | $5 / MTok | $8 / MTok | $0.20 / MTok",
"verified": true,
"sourceUrl": "https://docs.claude.com/en/docs/about-claude/pricing"
},
{
"item": "Claude Opus 5.5 cached input (cache hits and refreshes)",
"value": "$0.20 / MTok",
"numeric": 0.2,
"unit": "USD/1M tokens",
"published": true,
"source": "docs_pricing",
"quote": "On Claude Opus 5.5 and Claude Sonnet 5.5, a cache hit costs 5% of the standard input price ($0.20 USD per million tokens on Claude Opus 5.5, $0.10 USD on Claude Sonnet 5.5).",
"verified": true,
"sourceUrl": "https://docs.claude.com/en/docs/about-claude/pricing"
},
{
"item": "Claude Opus 5.5 batch input",
"value": "$2 / MTok",
"numeric": 2,
"unit": "USD/1M input tokens",
"published": true,
"source": "docs_pricing",
"quote": "Claude Opus 5.5 ... | $2 / MTok | $10 / MTok",
"verified": true,
"sourceUrl": "https://docs.claude.com/en/docs/about-claude/pricing"
},
{
"item": "Claude Opus 5.5 batch output",
"value": "$10 / MTok",
"numeric": 10,
"unit": "USD/1M output tokens",
"published": true,
"source": "docs_pricing",
"quote": "Claude Opus 5.5 ... | $2 / MTok | $10 / MTok",
"verified": true,
"sourceUrl": "https://docs.claude.com/en/docs/about-claude/pricing"
},
{
"item": "Claude Opus 5.5 fast mode input",
"value": "$8 USD / MTok",
"numeric": 8,
"unit": "USD/1M input tokens",
"published": true,
"source": "docs_pricing",
"quote": "| Claude Opus 5.5 | $8 USD / MTok | $40 USD / MTok |",
"verified": true,
"sourceUrl": "https://docs.claude.com/en/docs/about-claude/pricing"
},
{
"item": "Claude Opus 5.5 fast mode output",
"value": "$40 USD / MTok",
"numeric": 40,
"unit": "USD/1M output tokens",
"published": true,
"source": "docs_pricing",
"quote": "| Claude Opus 5.5 | $8 USD / MTok | $40 USD / MTok |",
"verified": true,
"sourceUrl": "https://docs.claude.com/en/docs/about-claude/pricing"
},
{
"item": "Claude Sonnet 5.5 input",
"value": "$2 / MTok",
"numeric": 2,
"unit": "USD/1M input tokens",
"published": true,
"source": "docs_pricing",
"quote": "Claude Sonnet 5.5 ... | $2 / MTok | $10 / MTok | $2.50 / MTok | $4 / MTok | $0.10 / MTok",
"verified": true,
"sourceUrl": "https://docs.claude.com/en/docs/about-claude/pricing"
},
{
"item": "Claude Sonnet 5.5 output",
"value": "$10 / MTok",
"numeric": 10,
"unit": "USD/1M output tokens",
"published": true,
"source": "docs_pricing",
"quote": "Claude Sonnet 5.5 ... | $2 / MTok | $10 / MTok | $2.50 / MTok | $4 / MTok | $0.10 / MTok",
"verified": true,
"sourceUrl": "https://docs.claude.com/en/docs/about-claude/pricing"
},
{
"item": "Claude Sonnet 5.5 cache write (5-minute)",
"value": "$2.50 / MTok",
"numeric": 2.5,
"unit": "USD/1M tokens",
"published": true,
"source": "docs_pricing",
"quote": "Claude Sonnet 5.5 ... | $2 / MTok | $10 / MTok | $2.50 / MTok | $4 / MTok | $0.10 / MTok",
"verified": true,
"sourceUrl": "https://docs.claude.com/en/docs/about-claude/pricing"
},
{
"item": "Claude Sonnet 5.5 cache write (1-hour)",
"value": "$4 / MTok",
"numeric": 4,
"unit": "USD/1M tokens",
"published": true,
"source": "docs_pricing",
"quote": "Claude Sonnet 5.5 ... | $2 / MTok | $10 / MTok | $2.50 / MTok | $4 / MTok | $0.10 / MTok",
"verified": true,
"sourceUrl": "https://docs.claude.com/en/docs/about-claude/pricing"
},
{
"item": "Claude Sonnet 5.5 cached input (cache hits and refreshes)",
"value": "$0.10 / MTok",
"numeric": 0.1,
"unit": "USD/1M tokens",
"published": true,
"source": "docs_pricing",
"quote": "On Claude Opus 5.5 and Claude Sonnet 5.5, a cache hit costs 5% of the standard input price ($0.20 USD per million tokens on Claude Opus 5.5, $0.10 USD on Claude Sonnet 5.5).",
"verified": true,
"sourceUrl": "https://docs.claude.com/en/docs/about-claude/pricing"
},
{
"item": "Claude Sonnet 5.5 batch input",
"value": "$1 / MTok",
"numeric": 1,
"unit": "USD/1M input tokens",
"published": true,
"source": "docs_pricing",
"quote": "Claude Sonnet 5.5 ... | $1 / MTok | $5 / MTok",
"verified": true,
"sourceUrl": "https://docs.claude.com/en/docs/about-claude/pricing"
},
{
"item": "Claude Sonnet 5.5 batch output",
"value": "$5 / MTok",
"numeric": 5,
"unit": "USD/1M output tokens",
"published": true,
"source": "docs_pricing",
"quote": "Claude Sonnet 5.5 ... | $1 / MTok | $5 / MTok",
"verified": true,
"sourceUrl": "https://docs.claude.com/en/docs/about-claude/pricing"
},
{
"item": "Claude Haiku 5.5 input (prompts up to 100,000 tokens)",
"value": "$0.10 / MTok",
"numeric": 0.1,
"unit": "USD/1M input tokens",
"published": true,
"source": "docs_pricing",
"quote": "Claude Haiku 5.5 ... | $0.10 / MTokfor prompts up to 100,000 tokens | $0.50 / MTok | $0.125 / MTok | $0.20 / MTok | $0.01 / MTok",
"verified": true,
"sourceUrl": "https://docs.claude.com/en/docs/about-claude/pricing"
},
{
"item": "Claude Haiku 5.5 output (prompts up to 100,000 tokens)",
"value": "$0.50 / MTok",
"numeric": 0.5,
"unit": "USD/1M output tokens",
"published": true,
"source": "docs_pricing",
"quote": "Claude Haiku 5.5 ... | $0.10 / MTokfor prompts up to 100,000 tokens | $0.50 / MTok | $0.125 / MTok | $0.20 / MTok | $0.01 / MTok",
"verified": true,
"sourceUrl": "https://docs.claude.com/en/docs/about-claude/pricing"
},
{
"item": "Claude Haiku 5.5 cache write 5-minute / 1-hour (prompts up to 100,000 tokens)",
"value": "$0.125 / MTok (5m), $0.20 / MTok (1h)",
"unit": "USD/1M tokens",
"published": true,
"source": "docs_pricing",
"quote": "Claude Haiku 5.5 ... | $0.10 / MTokfor prompts up to 100,000 tokens | $0.50 / MTok | $0.125 / MTok | $0.20 / MTok | $0.01 / MTok",
"verified": true,
"sourceUrl": "https://docs.claude.com/en/docs/about-claude/pricing"
},
{
"item": "Claude Haiku 5.5 cached input (prompts up to 100,000 tokens)",
"value": "$0.01 / MTok",
"numeric": 0.01,
"unit": "USD/1M tokens",
"published": true,
"source": "docs_pricing",
"quote": "Claude Haiku 5.5 ... | $0.10 / MTokfor prompts up to 100,000 tokens | $0.50 / MTok | $0.125 / MTok | $0.20 / MTok | $0.01 / MTok",
"verified": true,
"sourceUrl": "https://docs.claude.com/en/docs/about-claude/pricing"
},
{
"item": "Claude Haiku 5.5 input (prompts over 100,000 tokens)",
"value": "$0.50 / MTok",
"numeric": 0.5,
"unit": "USD/1M input tokens",
"published": true,
"source": "docs_pricing",
"quote": "| $0.50 / MTokfor prompts over 100,000 tokens | $2.50 / MTok | $0.625 / MTok | $1 / MTok | $0.05 / MTok |",
"verified": true,
"sourceUrl": "https://docs.claude.com/en/docs/about-claude/pricing"
},
{
"item": "Claude Haiku 5.5 output (prompts over 100,000 tokens)",
"value": "$2.50 / MTok",
"numeric": 2.5,
"unit": "USD/1M output tokens",
"published": true,
"source": "docs_pricing",
"quote": "| $0.50 / MTokfor prompts over 100,000 tokens | $2.50 / MTok | $0.625 / MTok | $1 / MTok | $0.05 / MTok |",
"verified": true,
"sourceUrl": "https://docs.claude.com/en/docs/about-claude/pricing"
},
{
"item": "Claude Haiku 5.5 cache write 5-minute / 1-hour (prompts over 100,000 tokens)",
"value": "$0.625 / MTok (5m), $1 / MTok (1h)",
"unit": "USD/1M tokens",
"published": true,
"source": "docs_pricing",
"quote": "| $0.50 / MTokfor prompts over 100,000 tokens | $2.50 / MTok | $0.625 / MTok | $1 / MTok | $0.05 / MTok |",
"verified": true,
"sourceUrl": "https://docs.claude.com/en/docs/about-claude/pricing"
},
{
"item": "Claude Haiku 5.5 cached input (prompts over 100,000 tokens)",
"value": "$0.05 / MTok",
"numeric": 0.05,
"unit": "USD/1M tokens",
"published": true,
"source": "docs_pricing",
"quote": "| $0.50 / MTokfor prompts over 100,000 tokens | $2.50 / MTok | $0.625 / MTok | $1 / MTok | $0.05 / MTok |",
"verified": true,
"sourceUrl": "https://docs.claude.com/en/docs/about-claude/pricing"
},
{
"item": "Claude Haiku 5.5 batch input / output (prompts up to 100,000 tokens)",
"value": "$0.05 / MTok input, $0.25 / MTok output",
"unit": "USD/1M tokens",
"published": true,
"source": "docs_pricing",
"quote": "Claude Haiku 5.5 ... | $0.05 / MTokfor prompts up to 100,000 tokens | $0.25 / MTok",
"verified": true,
"sourceUrl": "https://docs.claude.com/en/docs/about-claude/pricing"
},
{
"item": "Claude Haiku 5.5 batch input / output (prompts over 100,000 tokens)",
"value": "$0.25 / MTok input, $1.25 / MTok output",
"unit": "USD/1M tokens",
"published": true,
"source": "docs_pricing",
"quote": "| $0.25 / MTokfor prompts over 100,000 tokens | $1.25 / MTok |",
"verified": true,
"sourceUrl": "https://docs.claude.com/en/docs/about-claude/pricing"
},
{
"item": "Batch API discount",
"value": "50 percent discount on both input and output tokens",
"numeric": 50,
"unit": "percent",
"published": true,
"source": "docs_pricing",
"quote": "The Batch API allows asynchronous processing of large volumes of requests with a 50 percent discount on both input and output tokens.",
"verified": true,
"sourceUrl": "https://docs.claude.com/en/docs/about-claude/pricing"
},
{
"item": "Prompt caching multipliers",
"value": "5-minute cache write 1.25x base input; 1-hour cache write 2x base input; cache read 0.1x base input (0.025x on Claude Fable 5.1 and Claude Mythos 5.1; 0.05x on Claude Opus 5.5 and Claude Sonnet 5.5)",
"unit": "multiplier of base input price",
"published": true,
"source": "docs_pricing",
"quote": "| Cache read (hit) | 0.1x base input price (0.025x on Claude Fable 5.1 and Claude Mythos 5.1; 0.05x on Claude Opus 5.5 and Claude Sonnet 5.5) | Same duration as the preceding write |",
"verified": true,
"sourceUrl": "https://docs.claude.com/en/docs/about-claude/pricing"
},
{
"item": "US-only inference (inference_geo: \"us\") multiplier",
"value": "1.1x on all token pricing categories (Claude 4.6 and later models)",
"numeric": 1.1,
"unit": "multiplier",
"published": true,
"source": "docs_pricing",
"quote": "For Claude 4.6 and later models, specifying US-only inference through the `inference_geo` parameter incurs a 1.1x multiplier on all token pricing categories, including input tokens, output tokens, cache writes, and cache reads.",
"verified": true,
"sourceUrl": "https://docs.claude.com/en/docs/about-claude/pricing"
},
{
"item": "Web search tool",
"value": "$10 USD per 1,000 searches, plus standard token costs",
"numeric": 10,
"unit": "USD/1,000 searches",
"published": true,
"source": "docs_pricing",
"quote": "Web search is available on the Claude API for **$10 USD per 1,000 searches**, plus standard token costs for search-generated content.",
"verified": true,
"sourceUrl": "https://docs.claude.com/en/docs/about-claude/pricing"
},
{
"item": "Web fetch tool",
"value": "No additional cost beyond standard token costs",
"numeric": 0,
"unit": "USD",
"published": true,
"source": "docs_pricing",
"quote": "The web fetch tool is available on the Claude API at **no additional cost**.",
"verified": true,
"sourceUrl": "https://docs.claude.com/en/docs/about-claude/pricing"
},
{
"item": "Code execution",
"value": "50 free hours of usage daily per organization; additional hours $0.05 per hour per container",
"numeric": 0.05,
"unit": "USD/container-hour",
"published": true,
"source": "pricing_page",
"quote": "Run Python code in a sandboxed environment for advanced data analysis. 50 free hours of usage daily per organization.",
"verified": true,
"sourceUrl": "https://www.anthropic.com/pricing"
},
{
"item": "Managed Agents session runtime",
"value": "$0.08 per session-hour for active runtime; standard token rates apply",
"numeric": 0.08,
"unit": "USD/session-hour",
"published": true,
"source": "pricing_page",
"quote": "$0.08 per session-hour for active runtime",
"verified": true,
"sourceUrl": "https://www.anthropic.com/pricing"
},
{
"item": "Context window: Claude Fable 5.1, Claude Opus 5.5, Claude Sonnet 5.5, Claude Haiku 5.5",
"value": "1M tokens each",
"numeric": 1000000,
"unit": "tokens",
"published": true,
"source": "models",
"quote": "| Context window | 1M tokens | 1M tokens | 1M tokens | 1M tokens |",
"verified": true,
"sourceUrl": "https://platform.claude.com/docs/en/models/overview"
},
{
"item": "Max output: Claude Fable 5.1, Claude Opus 5.5, Claude Sonnet 5.5, Claude Haiku 5.5",
"value": "128K tokens each",
"numeric": 128000,
"unit": "tokens",
"published": true,
"source": "models",
"quote": "| Max output | 128K tokens | 128K tokens | 128K tokens | 128K tokens |",
"verified": true,
"sourceUrl": "https://platform.claude.com/docs/en/models/overview"
},
{
"item": "Start tier: Claude Fable 5.x (RPM / ITPM / OTPM)",
"value": "1,000 RPM / 500,000 ITPM / 100,000 OTPM",
"unit": "requests/min, input tokens/min, output tokens/min",
"published": true,
"source": "rate_limits",
"quote": "| Claude Fable 5.x1 | 1,000 | 500,000 | 100,000 |",
"verified": true,
"sourceUrl": "https://docs.anthropic.com/en/api/rate-limits"
},
{
"item": "Start tier: Claude Opus 5.5, Claude Sonnet 5.5, Claude Haiku 5.5 (RPM / ITPM / OTPM, each)",
"value": "1,000 RPM / 2,000,000 ITPM / 400,000 OTPM",
"unit": "requests/min, input tokens/min, output tokens/min",
"published": true,
"source": "rate_limits",
"quote": "| Claude Opus 5.5 | 1,000 | 2,000,000 | 400,000 |",
"verified": true,
"sourceUrl": "https://docs.anthropic.com/en/api/rate-limits"
},
{
"item": "Build tier: Claude Fable 5.x (RPM / ITPM / OTPM)",
"value": "2,000 RPM / 1,500,000 ITPM / 300,000 OTPM",
"unit": "requests/min, input tokens/min, output tokens/min",
"published": true,
"source": "rate_limits",
"quote": "| Claude Fable 5.x1 | 2,000 | 1,500,000 | 300,000 |",
"verified": true,
"sourceUrl": "https://docs.anthropic.com/en/api/rate-limits"
},
{
"item": "Build tier: Claude Opus 5.5, Claude Sonnet 5.5, Claude Haiku 5.5 (RPM / ITPM / OTPM, each)",
"value": "5,000 RPM / 5,000,000 ITPM / 1,000,000 OTPM",
"unit": "requests/min, input tokens/min, output tokens/min",
"published": true,
"source": "rate_limits",
"quote": "| Claude Opus 5.5 | 5,000 | 5,000,000 | 1,000,000 |",
"verified": true,
"sourceUrl": "https://docs.anthropic.com/en/api/rate-limits"
},
{
"item": "Scale tier: Claude Fable 5.x (RPM / ITPM / OTPM)",
"value": "4,000 RPM / 4,000,000 ITPM / 800,000 OTPM",
"unit": "requests/min, input tokens/min, output tokens/min",
"published": true,
"source": "rate_limits",
"quote": "| Claude Fable 5.x1 | 4,000 | 4,000,000 | 800,000 |",
"verified": true,
"sourceUrl": "https://docs.anthropic.com/en/api/rate-limits"
},
{
"item": "Scale tier: Claude Opus 5.5, Claude Sonnet 5.5, Claude Haiku 5.5 (RPM / ITPM / OTPM, each)",
"value": "10,000 RPM / 10,000,000 ITPM / 2,000,000 OTPM",
"unit": "requests/min, input tokens/min, output tokens/min",
"published": true,
"source": "rate_limits",
"quote": "| Claude Opus 5.5 | 10,000 | 10,000,000 | 2,000,000 |",
"verified": true,
"sourceUrl": "https://docs.anthropic.com/en/api/rate-limits"
},
{
"item": "Message Batches API limits (Start / Build / Scale)",
"value": "RPM 1,000 / 2,000 / 4,000; batch requests in processing queue 200,000 / 300,000 / 500,000; 100,000 batch requests per batch",
"unit": "requests",
"published": true,
"source": "rate_limits",
"quote": "| 1,000 | 200,000 | 100,000 |",
"verified": true,
"sourceUrl": "https://docs.anthropic.com/en/api/rate-limits"
},
{
"item": "Requests per day (RPD)",
"value": "Not stated. Limits are given as requests per minute (RPM), input tokens per minute (ITPM) and output tokens per minute (OTPM).",
"published": false,
"source": "rate_limits",
"quote": "The rate limits for the Messages API are measured in requests per minute (RPM), input tokens per minute (ITPM), and output tokens per minute (OTPM) for each model class.",
"verified": true,
"sourceUrl": "https://docs.anthropic.com/en/api/rate-limits"
},
{
"item": "Spend or deposit needed to reach each tier",
"value": "Not stated. Organizations are placed on a tier automatically based on usage history and account standing.",
"published": false,
"source": "rate_limits",
"quote": "Organizations are placed on a tier automatically based on usage history and account standing and can move to a higher tier over time as they use the API.",
"verified": true,
"sourceUrl": "https://docs.anthropic.com/en/api/rate-limits"
},
{
"item": "Evaluation tier limits",
"value": "New organizations may start in the Evaluation tier, with limits below the standard limits. No figures are stated.",
"published": false,
"source": "rate_limits",
"quote": "New organizations and organizations with limited usage history may start in the Evaluation tier, with limits below the standard limits shown on this page while account history is established.",
"verified": true,
"sourceUrl": "https://docs.anthropic.com/en/api/rate-limits"
}
],
"overage": {
"policy": "hard-stop",
"summary": "Prepaid credits with optional auto-reload. API requests stop when the credit balance runs out unless you buy credits or turn on auto-reload. Each tier also has a monthly spend cap: once it is reached, API usage pauses until 00:00 UTC on the first day of the next month unless a higher limit is granted. Organizations invoiced through Anthropic sales are billed for usage as usual.",
"source": "rate_limits",
"quote": "Once you reach your tier’s spend cap, API usage pauses until 00:00 UTC on the first day of the next month, unless you request a higher limit sooner."
},
"gotchas": [
{
"title": "Credits run out = requests stop; auto-reload is optional",
"detail": "If the organization has no credits left, API requests stop. To keep building, purchase credits or turn on auto-reload on the Billing page.",
"source": "api_credits",
"quote": "To keep building, purchase credits or turn on auto-reload on the [Billing](https://platform.claude.com/settings/billing) page (`platform.claude.com/settings/billing`) in the Console.",
"sourceUrl": "https://platform.claude.com/docs/en/about-claude/api-credits-for-subscribers"
},
{
"title": "Thinking tokens are billed as output",
"detail": "Tokens Claude spends reasoning are billed as output tokens, even when the thinking text is not returned, and count toward max_tokens.",
"source": "thinking",
"quote": "Thinking has a cost: the tokens Claude spends reasoning are billed as output tokens, even when the thinking text isn’t returned to you, and they count toward `max_tokens` alongside the response text.",
"sourceUrl": "https://platform.claude.com/docs/en/build-with-claude/thinking"
},
{
"title": "Summarized thinking billed at full length",
"detail": "You are charged for the full thinking tokens generated, not the summary tokens you see.",
"source": "thinking",
"quote": "You’re charged for the full thinking tokens generated by the original request, not the summary tokens.",
"sourceUrl": "https://platform.claude.com/docs/en/build-with-claude/thinking"
},
{
"title": "Claude Haiku 5.5 long-prompt pricing",
"detail": "A Claude Haiku 5.5 request whose prompt is over 100,000 tokens pays higher prices. Prompt length counts all input tokens, including cache reads and cache writes.",
"source": "docs_pricing",
"quote": "Claude Haiku 5.5 is priced by prompt length: a request whose prompt is over 100,000 tokens pays higher prices.",
"sourceUrl": "https://docs.claude.com/en/docs/about-claude/pricing"
},
{
"title": "1M context at standard pricing (except Haiku 5.5)",
"detail": "Claude 4.6 and later models (except Claude Haiku 5.5) include the full 1M token context window at standard pricing.",
"source": "docs_pricing",
"quote": "(A 900k-token request is billed at the same per-token rate as a 9k-token request.)",
"sourceUrl": "https://docs.claude.com/en/docs/about-claude/pricing"
},
{
"title": "Newer tokenizer uses about 30% more tokens",
"detail": "Claude 4.7 and later models use a newer tokenizer that produces approximately 30% more tokens for the same text.",
"source": "docs_pricing",
"quote": "This tokenizer produces approximately 30% more tokens for the same text.",
"sourceUrl": "https://docs.claude.com/en/docs/about-claude/pricing"
},
{
"title": "Images are billed as visual tokens",
"detail": "Images are processed in 28×28-pixel patches; each patch is a visual token, priced at the model's per-token rate.",
"source": "vision",
"quote": "An image, therefore, costs `⌈width / 28⌉ × ⌈height / 28⌉` visual tokens.",
"sourceUrl": "https://platform.claude.com/docs/en/build-with-claude/vision"
},
{
"title": "Tool use adds system prompt tokens",
"detail": "When tools are used, the API adds a tool-use system prompt (for example 286 tokens on Claude Opus 5.5, Sonnet 5.5 and Haiku 5.5 with tool choice auto or none), plus tool definitions and tool blocks billed as tokens.",
"source": "docs_pricing",
"quote": "When you use `tools`, the API also automatically includes a special system prompt for the model that enables tool use.",
"sourceUrl": "https://docs.claude.com/en/docs/about-claude/pricing"
},
{
"title": "Fast mode is not available with Batch",
"detail": "Fast mode (Claude Opus 5.5 at $8 / $40 per MTok) cannot be combined with the Batch API; caching and data residency multipliers stack on top of fast mode pricing.",
"source": "docs_pricing",
"quote": "Fast mode is not available with the [Batch API](#batch-processing).",
"sourceUrl": "https://docs.claude.com/en/docs/about-claude/pricing"
},
{
"title": "Spend-cap 429 has no retry-after",
"detail": "When the monthly spend cap is reached, requests return HTTP 429 rate_limit_error with no retry-after header; retries fail until access resumes.",
"source": "rate_limits",
"quote": "The error type is `rate_limit_error`, the same as for a rate limit, but the response has no `retry-after` header.",
"sourceUrl": "https://docs.anthropic.com/en/api/rate-limits"
},
{
"title": "Cached reads don't count toward ITPM",
"detail": "For most models only uncached input tokens and cache writes count toward input-tokens-per-minute limits.",
"source": "rate_limits",
"quote": "**For most Claude models, only uncached input tokens count toward your ITPM rate limits.**",
"sourceUrl": "https://docs.anthropic.com/en/api/rate-limits"
},
{
"title": "Short-interval enforcement and acceleration limits",
"detail": "A per-minute limit may be enforced over shorter intervals (e.g. 60 RPM as 1 request per second), and sharp usage increases can trigger acceleration-limit 429s.",
"source": "rate_limits",
"quote": "For instance, a rate of 60 requests per minute (RPM) might be enforced as 1 request per second.",
"sourceUrl": "https://docs.anthropic.com/en/api/rate-limits"
},
{
"title": "Max and Team subscriptions include API credits",
"detail": "Claude Max 5x ($100), Max 20x ($200) and Team (up to $500 pooled) include monthly Claude API credits that expire each billing cycle with no rollover and do not count toward moving to a higher tier.",
"source": "api_credits",
"quote": "| **Monthly amount** | $100 USD (Max 5x), $200 USD (Max 20x), up to $500 USD (Team, pooled*) |",
"sourceUrl": "https://platform.claude.com/docs/en/about-claude/api-credits-for-subscribers"
}
]
},
{
"id": "gemini-api",
"name": "Gemini API",
"vendor": "Google",
"category": "llm-api",
"url": "https://ai.google.dev/gemini-api",
"checked": "2026-10-30",
"sources": {
"pricing": {
"name": "Gemini Developer API pricing | Gemini API | Google AI for Developers",
"url": "https://ai.google.dev/gemini-api/docs/pricing"
},
"ratelimits": {
"name": "Rate limits | Gemini API | Google AI for Developers",
"url": "https://ai.google.dev/gemini-api/docs/rate-limits"
},
"billing": {
"name": "Billing | Gemini API | Google AI for Developers",
"url": "https://ai.google.dev/gemini-api/docs/billing"
},
"model_argon": {
"name": "Gemini 4 Argon | Gemini API | Google AI for Developers",
"url": "https://ai.google.dev/gemini-api/docs/models/gemini-4-argon"
},
"model_38flash": {
"name": "Gemini 3.8 Flash | Gemini API | Google AI for Developers",
"url": "https://ai.google.dev/gemini-api/docs/models/gemini-3.8-flash"
},
"model_35flashlite": {
"name": "Gemini 3.5 Flash-Lite | Gemini API | Google AI for Developers",
"url": "https://ai.google.dev/gemini-api/docs/models/gemini-3.5-flash-lite"
},
"models": {
"name": "Models | Gemini API | Google AI for Developers",
"url": "https://ai.google.dev/gemini-api/docs/models"
}
},
"unit": {
"tag": "Per 1M tokens",
"definition": "Prices are listed per 1 million tokens in USD, separately for input, output (including thinking tokens) and context caching.",
"source": "pricing",
"quote": "Paid Tier, per 1M tokens in USD"
},
"free": {
"summary": "Free tier with limited access to certain models and free input and output tokens, up to each model's free-tier rate limits. Content on the free tier is used to improve Google's products. Gemini 4 Argon is not available on the Free tier.",
"published": true,
"source": "pricing",
"quote": "Start building free of charge with generous limits, then scale up with prepaid and pay-as-you-go pricing for your production-ready applications."
},
"plans": [
{
"id": "free",
"name": "Free",
"priceUsd": 0,
"billing": "usage",
"included": "Limited access to certain models; free input & output tokens; Google AI Studio access; content used to improve Google's products. Qualification: active project or free trial.",
"source": "pricing",
"quote": "For developers and small projects getting started with the Gemini API.",
"sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing"
},
{
"id": "tier-1",
"name": "Paid – Tier 1",
"priceUsd": null,
"priceNote": "Pay-as-you-go token pricing; setup requires prepaying a minimum of $5 of credits",
"billing": "usage",
"included": "Set up and link an active billing account. Billing tier cap $250. Higher rate limits, context caching, Batch API, access to most advanced models, content not used to improve products.",
"source": "billing",
"quote": "Upgrading from the Free Tier to the Paid Tier means linking a billing account and prepaying to add a minimum of $5 (or equivalent in other currencies) of credits to your account.",
"sourceUrl": "https://ai.google.dev/gemini-api/docs/billing"
},
{
"id": "tier-2",
"name": "Paid – Tier 2",
"priceUsd": null,
"priceNote": "Pay-as-you-go token pricing",
"billing": "usage",
"included": "Paid $100 + 3 days from first successful payment. Billing tier cap $2,000.",
"source": "ratelimits",
"quote": "Paid $100 + 3 days from first successful payment",
"sourceUrl": "https://ai.google.dev/gemini-api/docs/rate-limits"
},
{
"id": "tier-3",
"name": "Paid – Tier 3",
"priceUsd": null,
"priceNote": "Pay-as-you-go token pricing",
"billing": "usage",
"included": "Paid $1,000 + 30 days from first successful payment. Billing tier cap $20,000 - $100,000+.",
"source": "ratelimits",
"quote": "Paid $1,000 + 30 days from first successful payment",
"sourceUrl": "https://ai.google.dev/gemini-api/docs/rate-limits"
},
{
"id": "enterprise",
"name": "Enterprise",
"priceUsd": null,
"priceNote": "Contact sales",
"billing": "usage",
"included": "All features in Paid, plus optional dedicated support channels, advanced security & compliance, provisioned throughput, volume-based discounts, ML ops and model garden, via Gemini Enterprise Agent Platform.",
"source": "pricing",
"quote": "For enterprise deployments, powered by Gemini Enterprise Agent Platform.",
"sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing"
}
],
"rates": [
{
"item": "Gemini 4 Argon – input (Standard)",
"value": "$2.00 per 1M tokens through November 30, 2026",
"numeric": 2,
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "$2.00 through November 30, 2026.",
"verified": true,
"sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing"
},
{
"item": "Gemini 4 Argon – input (Standard) from December 1, 2026",
"value": "$4.00 per 1M tokens starting December 1, 2026",
"numeric": 4,
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "$4.00 starting December 1, 2026.",
"verified": true,
"sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing"
},
{
"item": "Gemini 4 Argon – output incl. thinking tokens (Standard)",
"value": "$10.00 per 1M tokens through November 30, 2026",
"numeric": 10,
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "$10.00 through November 30, 2026.",
"verified": true,
"sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing"
},
{
"item": "Gemini 4 Argon – output incl. thinking tokens (Standard) from December 1, 2026",
"value": "$20.00 per 1M tokens starting December 1, 2026",
"numeric": 20,
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "$20.00 starting December 1, 2026.",
"verified": true,
"sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing"
},
{
"item": "Gemini 4 Argon – context caching (Standard)",
"value": "$0.10 per 1M tokens through November 30, 2026; $0.20 starting December 1, 2026. Implicit caching only.",
"numeric": 0.1,
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "Implicit caching only (explicit caching is not supported).",
"verified": true,
"sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing"
},
{
"item": "Gemini 4 Argon – input (Batch)",
"value": "$1.00 per 1M tokens through November 30, 2026; $2.00 starting December 1, 2026",
"numeric": 1,
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "$1.00 through November 30, 2026.",
"verified": true,
"sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing"
},
{
"item": "Gemini 4 Argon – output (Batch)",
"value": "$5.00 per 1M tokens through November 30, 2026; $10.00 starting December 1, 2026",
"numeric": 5,
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "$5.00 through November 30, 2026.",
"verified": true,
"sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing"
},
{
"item": "Gemini 4 Argon – input (Priority)",
"value": "$3.60 per 1M tokens through November 30, 2026; $7.20 starting December 1, 2026",
"numeric": 3.6,
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "$3.60 through November 30, 2026.",
"verified": true,
"sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing"
},
{
"item": "Gemini 4 Argon – output (Priority)",
"value": "$18.00 per 1M tokens through November 30, 2026; $36.00 starting December 1, 2026",
"numeric": 18,
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "$18.00 through November 30, 2026.",
"verified": true,
"sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing"
},
{
"item": "Gemini 3.8 Flash – input (Standard)",
"value": "$0.75 per 1M tokens through December 31, 2026",
"numeric": 0.75,
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "$0.75 through December 31, 2026.",
"verified": true,
"sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing"
},
{
"item": "Gemini 3.8 Flash – input (Standard) from January 1, 2027",
"value": "$1.50 per 1M tokens starting January 1, 2027",
"numeric": 1.5,
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "$1.50 starting January 1, 2027.",
"verified": true,
"sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing"
},
{
"item": "Gemini 3.8 Flash – output incl. thinking tokens (Standard)",
"value": "$3.75 per 1M tokens through December 31, 2026",
"numeric": 3.75,
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "$3.75 through December 31, 2026.",
"verified": true,
"sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing"
},
{
"item": "Gemini 3.8 Flash – output incl. thinking tokens (Standard) from January 1, 2027",
"value": "$7.50 per 1M tokens starting January 1, 2027",
"numeric": 7.5,
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "$7.50 starting January 1, 2027.",
"verified": true,
"sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing"
},
{
"item": "Gemini 3.8 Flash – context caching (Standard)",
"value": "$0.075 per 1M tokens through December 31, 2026 ($0.15 from January 1, 2027); storage $0.50 / 1M tokens per hour through December 31, 2026 ($1.00 from January 1, 2027)",
"numeric": 0.075,
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "$0.075 through December 31, 2026.",
"verified": true,
"sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing"
},
{
"item": "Gemini 3.8 Flash – input (Batch)",
"value": "$0.375 per 1M tokens through December 31, 2026; $0.75 starting January 1, 2027",
"numeric": 0.375,
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "$0.375 through December 31, 2026.",
"verified": true,
"sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing"
},
{
"item": "Gemini 3.8 Flash – output (Batch)",
"value": "$1.875 per 1M tokens through December 31, 2026; $3.75 starting January 1, 2027",
"numeric": 1.875,
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "$1.875 through December 31, 2026.",
"verified": true,
"sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing"
},
{
"item": "Gemini 3.5 Flash-Lite – input (Standard)",
"value": "$0.30 per 1M tokens (text / image / video / audio)",
"numeric": 0.3,
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "$0.30 (text / image / video / audio)",
"verified": true,
"sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing"
},
{
"item": "Gemini 3.5 Flash-Lite – output incl. thinking tokens (Standard)",
"value": "$2.50 per 1M tokens",
"numeric": 2.5,
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "Output price (including thinking tokens) | Free of charge | $2.50",
"verified": true,
"sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing"
},
{
"item": "Gemini 3.5 Flash-Lite – context caching (Standard)",
"value": "$0.03 per 1M tokens; storage $1.00 / 1M tokens per hour",
"numeric": 0.03,
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "$0.03
$1.00 / 1,000,000 tokens per hour (storage price)",
"verified": true,
"sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing"
},
{
"item": "Gemini 3.5 Flash-Lite – input (Batch)",
"value": "$0.15 per 1M tokens (text / image / video / audio)",
"numeric": 0.15,
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "$0.15 (text / image / video / audio)",
"verified": true,
"sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing"
},
{
"item": "Gemini 3.5 Flash-Lite – output (Batch)",
"value": "$1.25 per 1M tokens",
"numeric": 1.25,
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "Output price (including thinking tokens) | Free of charge | $1.25",
"verified": true,
"sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing"
},
{
"item": "Gemini 3.6 Flash – input / output (Standard)",
"value": "$0.75 input / $3.75 output per 1M tokens through December 31, 2026; $1.50 / $7.50 starting January 1, 2027",
"numeric": 0.75,
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "$0.75 through December 31, 2026.",
"verified": true,
"sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing"
},
{
"item": "Gemini 3.1 Flash-Lite – input / output (Standard)",
"value": "$0.25 input (text / image / video), $0.50 input (audio); $1.50 output per 1M tokens",
"numeric": 0.25,
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "$0.25 (text / image / video)
$0.50 (audio)",
"verified": true,
"sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing"
},
{
"item": "Gemini 3.1 Pro Preview – input / output (Standard)",
"value": "Input $2.00 (prompts <= 200k tokens), $4.00 (prompts > 200k tokens); output $12.00 (<= 200k), $18.00 (> 200k) per 1M tokens",
"numeric": 2,
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "$2.00, prompts <= 200k tokens
$4.00, prompts > 200k tokens",
"verified": true,
"sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing"
},
{
"item": "Gemini 3 Flash Preview – input / output (Standard)",
"value": "$0.50 input (text / image / video), $1.00 input (audio); $3.00 output per 1M tokens",
"numeric": 0.5,
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "$0.50 (text / image / video)
$1.00 (audio)",
"verified": true,
"sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing"
},
{
"item": "Gemini 2.5 Pro – input / output (Standard)",
"value": "Input $1.25 (prompts <= 200k tokens), $2.50 (> 200k); output $10.00 (<= 200k), $15.00 (> 200k) per 1M tokens",
"numeric": 1.25,
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "$1.25, prompts <= 200k tokens
$2.50, prompts > 200k tokens",
"verified": true,
"sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing"
},
{
"item": "Gemini 2.5 Flash – input / output (Standard)",
"value": "$0.30 input (text / image / video), $1.00 input (audio); $2.50 output per 1M tokens",
"numeric": 0.3,
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "$0.30 (text / image / video)
$1.00 (audio)",
"verified": true,
"sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing"
},
{
"item": "Batch API discount",
"value": "50% cost reduction",
"numeric": 50,
"unit": "% discount",
"published": true,
"source": "pricing",
"quote": "Batch API (50% cost reduction)",
"verified": true,
"sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing"
},
{
"item": "Grounding with Google Search (Gemini 3 and newer)",
"value": "5,000 free search requests per month, then $14 per 1,000 requests, daily cap of 1,500 requests per day",
"numeric": 14,
"unit": "USD/1,000 requests",
"published": true,
"source": "pricing",
"quote": "5,000 free search requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests",
"verified": true,
"sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing"
},
{
"item": "Per-model rate limits (RPM / TPM / RPD) per tier",
"value": "Not printed in the docs; rate limits can be viewed in Google AI Studio.",
"published": false,
"source": "ratelimits",
"quote": "Rate limits depend on a variety of factors (such as your usage tier) and can be viewed in Google AI Studio.",
"verified": true,
"sourceUrl": "https://ai.google.dev/gemini-api/docs/rate-limits"
},
{
"item": "Spend-based rate limit per 10 minutes – Tier 1",
"value": "$10",
"numeric": 10,
"unit": "USD per rolling 10 minutes",
"published": true,
"source": "ratelimits",
"quote": "| **Tier 1** | $10 |",
"verified": true,
"sourceUrl": "https://ai.google.dev/gemini-api/docs/rate-limits"
},
{
"item": "Spend-based rate limit per 10 minutes – Tier 2",
"value": "$50",
"numeric": 50,
"unit": "USD per rolling 10 minutes",
"published": true,
"source": "ratelimits",
"quote": "| **Tier 2** | $50 |",
"verified": true,
"sourceUrl": "https://ai.google.dev/gemini-api/docs/rate-limits"
},
{
"item": "Spend-based rate limit per 10 minutes – Tier 3",
"value": "$200",
"numeric": 200,
"unit": "USD per rolling 10 minutes",
"published": true,
"source": "ratelimits",
"quote": "| **Tier 3** | $200 |",
"verified": true,
"sourceUrl": "https://ai.google.dev/gemini-api/docs/rate-limits"
},
{
"item": "Priority inference rate limits",
"value": "0.3x the standard rate limit for each model and tier",
"numeric": 0.3,
"unit": "multiplier",
"published": true,
"source": "ratelimits",
"quote": "Default rate limits are: 0.3x the standard rate limit for each model and tier",
"verified": true,
"sourceUrl": "https://ai.google.dev/gemini-api/docs/rate-limits"
},
{
"item": "Batch API concurrent requests",
"value": "100 concurrent batch requests; 2GB input file size limit; 20GB file storage limit",
"numeric": 100,
"unit": "concurrent batch requests",
"published": true,
"source": "ratelimits",
"quote": "Concurrent batch requests: 100",
"verified": true,
"sourceUrl": "https://ai.google.dev/gemini-api/docs/rate-limits"
},
{
"item": "Batch enqueued tokens – Gemini 4 Argon (Tier 1 / Tier 2 / Tier 3)",
"value": "5,000,000 / 500,000,000 / 1,000,000,000",
"numeric": 5000000,
"unit": "tokens (Tier 1)",
"published": true,
"source": "ratelimits",
"quote": "| Gemini 4 Argon | 5,000,000 |",
"verified": true,
"sourceUrl": "https://ai.google.dev/gemini-api/docs/rate-limits"
},
{
"item": "Batch enqueued tokens – Gemini 3.8 Flash (Tier 1 / Tier 2 / Tier 3)",
"value": "3,000,000 / 400,000,000 / 1,000,000,000",
"numeric": 3000000,
"unit": "tokens (Tier 1)",
"published": true,
"source": "ratelimits",
"quote": "| Gemini 3.8 Flash | 3,000,000 |",
"verified": true,
"sourceUrl": "https://ai.google.dev/gemini-api/docs/rate-limits"
},
{
"item": "Batch enqueued tokens – Gemini 3.5 Flash-Lite (Tier 1 / Tier 2 / Tier 3)",
"value": "10,000,000 / 500,000,000 / 1,000,000,000",
"numeric": 10000000,
"unit": "tokens (Tier 1)",
"published": true,
"source": "ratelimits",
"quote": "| Gemini 3.5 Flash-Lite | 10,000,000 |",
"verified": true,
"sourceUrl": "https://ai.google.dev/gemini-api/docs/rate-limits"
},
{
"item": "Billing tier spend cap – Tier 1 / Tier 2 / Tier 3",
"value": "$250 / $2,000 / $20,000 - $100,000 per month",
"numeric": 250,
"unit": "USD/month (Tier 1)",
"published": true,
"source": "billing",
"quote": "Each tier has a maximum monthly spend limit:",
"verified": true,
"sourceUrl": "https://ai.google.dev/gemini-api/docs/billing"
},
{
"item": "Minimum / maximum prepay credit purchase",
"value": "Minimum $5; maximum $5,000",
"numeric": 5,
"unit": "USD (minimum)",
"published": true,
"source": "billing",
"quote": "The minimum purchase is $5. The maximum amount of credits you can prepay for is $5,000.",
"verified": true,
"sourceUrl": "https://ai.google.dev/gemini-api/docs/billing"
},
{
"item": "Gemini 4 Argon – context window / max output",
"value": "Context window (unified input and output token limit) 1,048,576; max output 65,536 (default synchronous) / up to 1,048,576 (with long decode)",
"numeric": 1048576,
"unit": "tokens",
"published": true,
"source": "model_argon",
"quote": "65,536 (default synchronous) / up to 1,048,576 (with long decode)",
"verified": true,
"sourceUrl": "https://ai.google.dev/gemini-api/docs/models/gemini-4-argon"
},
{
"item": "Gemini 3.8 Flash – input / output token limit",
"value": "Input token limit 1,048,576; output token limit 65,536",
"numeric": 1048576,
"unit": "tokens",
"published": true,
"source": "model_38flash",
"quote": "**Input token limit**
1,048,576
**Output token limit**
65,536",
"verified": true,
"sourceUrl": "https://ai.google.dev/gemini-api/docs/models/gemini-3.8-flash"
},
{
"item": "Gemini 3.5 Flash-Lite – input / output token limit",
"value": "Input token limit 1,048,576; output token limit 65,536",
"numeric": 1048576,
"unit": "tokens",
"published": true,
"source": "model_35flashlite",
"quote": "**Input token limit**
1,048,576
**Output token limit**
65,536",
"verified": true,
"sourceUrl": "https://ai.google.dev/gemini-api/docs/models/gemini-3.5-flash-lite"
}
],
"overage": {
"policy": "hard-stop",
"summary": "New users default to Prepay: usage is deducted from a prepaid credit balance, and when it hits $0 all API keys on the billing account stop working (HTTP 402) until credits are added. Optional auto-reload with a monthly auto-charge limit. Postpay accounts are charged at month end or when the tier spend cap is reached; after the tier cap is reached, service is paused until the next billing cycle.",
"source": "billing",
"quote": "When your Prepay credit balance on the billing account hits $0, all API keys in all projects linked to that billing account will stop working simultaneously."
},
"gotchas": [
{
"title": "Thinking tokens billed as output",
"detail": "Output prices include thinking tokens. For Gemini 4 Argon, every token processed is billed, including thinking tokens and internal tool system instructions and function declarations when using grounding.",
"source": "pricing",
"quote": "Every token the model processes is counted and billed, including thinking tokens and internal tool system instructions and function declarations when using grounding.",
"sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing"
},
{
"title": "Scheduled price increases",
"detail": "Gemini 4 Argon prices double starting December 1, 2026; Gemini 3.8 Flash and Gemini 3.6 Flash prices double starting January 1, 2027.",
"source": "pricing",
"quote": "$4.00 starting December 1, 2026.",
"sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing"
},
{
"title": "Long-context surcharge on Pro models",
"detail": "Gemini 3.1 Pro Preview and Gemini 2.5 Pro charge higher input, output and caching rates for prompts over 200k tokens.",
"source": "pricing",
"quote": "$2.00, prompts <= 200k tokens
$4.00, prompts > 200k tokens",
"sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing"
},
{
"title": "Audio input priced higher",
"detail": "On several models audio input costs more than text/image/video, e.g. Gemini 3.1 Flash-Lite $0.25 (text / image / video) vs $0.50 (audio).",
"source": "pricing",
"quote": "$0.25 (text / image / video)
$0.50 (audio)",
"sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing"
},
{
"title": "Free-tier data used to improve products",
"detail": "Content on the Free tier is used to improve Google's products; on the Paid tier it is not. The invite-only Contributor tier is also used to improve products.",
"source": "pricing",
"quote": "Content **not** used to improve our products",
"sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing"
},
{
"title": "Context cache storage charged hourly",
"detail": "Explicit context caching carries a storage fee per 1M tokens per hour (e.g. $4.50 for Gemini 3.1 Pro Preview and Gemini 2.5 Pro). Gemini 4 Argon supports implicit caching only.",
"source": "pricing",
"quote": "$4.50 / 1,000,000 tokens per hour (storage price)",
"sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing"
},
{
"title": "Overage past $0 balance or spend cap",
"detail": "Prepay billing is subject to overages during the approximately 10 minute billing pipeline latency; batch jobs and agents may consume credits beyond the balance.",
"source": "billing",
"quote": "Prepay billing is subject to overages during the approximately 10 minute billing pipeline latency.",
"sourceUrl": "https://ai.google.dev/gemini-api/docs/billing"
},
{
"title": "Prepaid credits expire and are non-refundable",
"detail": "Unused prepaid credits expire after 12 months and are non-refundable, except when switching to a Postpay account.",
"source": "billing",
"quote": "After credits are purchased, unused credits expire after 12 months and are non-refundable, except after switching to a Postpay account.",
"sourceUrl": "https://ai.google.dev/gemini-api/docs/billing"
},
{
"title": "Google Cloud $300 welcome credit not usable",
"detail": "Accounts opened after March 2, 2026 cannot use the $300 Google Cloud Welcome credit for Gemini API and AI Studio usage.",
"source": "billing",
"quote": "If you opened your account after March 2, 2026, you can't use these credits to pay for Gemini API and AI Studio usage",
"sourceUrl": "https://ai.google.dev/gemini-api/docs/billing"
},
{
"title": "Tier cap pauses all projects",
"detail": "After the cumulative billing-account total reaches the tier spend cap, service is paused for all linked projects until the 1st of the next month, unless an increase is requested.",
"source": "billing",
"quote": "After the cumulative account total reaches the tier limit, service is paused for all projects linked to that billing account until the start of the next billing cycle (the 1st of each month).",
"sourceUrl": "https://ai.google.dev/gemini-api/docs/billing"
},
{
"title": "Rate limits per project; RPD resets at midnight Pacific",
"detail": "Rate limits are applied per project, not per API key, and requests-per-day quotas reset at midnight Pacific time. Preview and experimental models have more restricted limits.",
"source": "ratelimits",
"quote": "Rate limits are applied per project, not per API key. Requests per day (**RPD**) quotas reset at midnight Pacific time.",
"sourceUrl": "https://ai.google.dev/gemini-api/docs/rate-limits"
}
]
},
{
"id": "mistral-api",
"name": "Mistral AI API",
"vendor": "Mistral AI",
"category": "llm-api",
"url": "https://mistral.ai/",
"checked": "2026-10-30",
"sources": {
"pricing": {
"name": "Pricing | Mistral",
"url": "https://mistral.ai/pricing#api-pricing"
},
"tiers": {
"name": "Rate limit and usage tiers",
"url": "https://docs.mistral.ai/deployment/laplateforme/tier/"
},
"docs_pricing": {
"name": "API pricing | Mistral Docs",
"url": "https://docs.mistral.ai/inference/pricing"
},
"models": {
"name": "Models Overview | Mistral Docs",
"url": "https://docs.mistral.ai/models"
},
"card_large4": {
"name": "Mistral Large 4 | Mistral Docs",
"url": "https://docs.mistral.ai/models/mistral-large-4-0"
},
"card_medium": {
"name": "Mistral Medium 3.5 - Mistral AI | Mistral Docs",
"url": "https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04"
},
"card_small": {
"name": "Mistral Small 4 - Mistral AI | Mistral Docs",
"url": "https://docs.mistral.ai/models/model-cards/mistral-small-4-0-26-03"
},
"priority": {
"name": "Priority Tier | Mistral Docs",
"url": "https://docs.mistral.ai/inference/priority-tier"
},
"batch": {
"name": "Batch Processing | Mistral Docs",
"url": "https://docs.mistral.ai/studio-api/batch-processing"
},
"admin": {
"name": "Admin | Mistral Docs",
"url": "https://docs.mistral.ai/admin"
},
"billing": {
"name": "Billing and usage (subscriptions) | Mistral Docs",
"url": "https://docs.mistral.ai/admin/billing-usage/subscriptions"
}
},
"unit": {
"tag": "Per 1M tokens",
"definition": "Most models are priced per million tokens, with input (prompts) and output (responses) counted separately. OCR is priced per 1,000 pages, speech models per minute, and tool APIs per call.",
"source": "pricing",
"quote": "Most models are priced per million tokens, with both input (your prompts) and output (responses) counted separately."
},
"free": {
"summary": "A free API tier with restrictive rate limits, intended for trying and exploring the API. The Free plan includes access to Mistral Studio. No free credit amount is stated.",
"published": true,
"source": "tiers",
"quote": "We offer various tiers on the platform, including a free API tier with restrictive rate limits. The free API tier is designed to allow you to try and explore our API."
},
"plans": [
{
"id": "api-payg",
"name": "API (Standard Tier, pay per use)",
"priceUsd": null,
"priceNote": "Billed per million input and output tokens at per-model list prices",
"billing": "usage",
"included": "Input and output tokens are counted separately and priced per model",
"source": "pricing",
"quote": "Most models are priced per million tokens, with both input (your prompts) and output (responses) counted separately.",
"sourceUrl": "https://mistral.ai/pricing#api-pricing"
},
{
"id": "api-batch",
"name": "Batch",
"priceUsd": null,
"priceNote": "50% off standard prices",
"billing": "usage",
"included": "Asynchronous inference on large inputs at a 50% discount. Requests are queued and processed over a 24-hour period.",
"source": "batch",
"quote": "Batching allows you to run asynchronous inference on large inputs in parallel, reducing compute costs while running large workloads at a 50% discount.",
"sourceUrl": "https://docs.mistral.ai/studio-api/batch-processing"
},
{
"id": "api-priority",
"name": "Priority Tier",
"priceUsd": null,
"priceNote": "1.75x standard list pricing",
"billing": "usage",
"included": "Priority queueing, custom per-model rate limits, 99.5% uptime SLA. Requires account setup with Mistral.",
"source": "priority",
"quote": "The multiplier is 1.75x standard list pricing, which is a 75% premium on input, output, and cached tokens.",
"sourceUrl": "https://docs.mistral.ai/inference/priority-tier"
}
],
"rates": [
{
"item": "Mistral Large 4 input per 1M tokens",
"value": "$0.7",
"numeric": 0.7,
"unit": "USD/1M tokens",
"published": true,
"source": "docs_pricing",
"quote": "Mistral Large 4 ↗ | $0.7 | $0.07 | $2.1 (columns: Input | Cached input | Output; Prices /M Tokens)",
"verified": true,
"sourceUrl": "https://docs.mistral.ai/inference/pricing"
},
{
"item": "Mistral Large 4 cached input per 1M tokens",
"value": "$0.07",
"numeric": 0.07,
"unit": "USD/1M tokens",
"published": true,
"source": "docs_pricing",
"quote": "Mistral Large 4 ↗ | $0.7 | $0.07 | $2.1",
"verified": true,
"sourceUrl": "https://docs.mistral.ai/inference/pricing"
},
{
"item": "Mistral Large 4 output per 1M tokens",
"value": "$2.1",
"numeric": 2.1,
"unit": "USD/1M tokens",
"published": true,
"source": "docs_pricing",
"quote": "Mistral Large 4 ↗ | $0.7 | $0.07 | $2.1",
"verified": true,
"sourceUrl": "https://docs.mistral.ai/inference/pricing"
},
{
"item": "Mistral Large 4 context window",
"value": "1M",
"unit": "tokens",
"published": true,
"source": "card_large4",
"quote": "Context 1M",
"verified": true,
"sourceUrl": "https://docs.mistral.ai/models/mistral-large-4-0"
},
{
"item": "Mistral Medium 3.5 input per 1M tokens",
"value": "$1.5",
"numeric": 1.5,
"unit": "USD/1M tokens",
"published": true,
"source": "docs_pricing",
"quote": "Mistral Medium 3.5 ↗ | $1.5 | $0.15 | $7.5",
"verified": true,
"sourceUrl": "https://docs.mistral.ai/inference/pricing"
},
{
"item": "Mistral Medium 3.5 cached input per 1M tokens",
"value": "$0.15",
"numeric": 0.15,
"unit": "USD/1M tokens",
"published": true,
"source": "docs_pricing",
"quote": "Mistral Medium 3.5 ↗ | $1.5 | $0.15 | $7.5",
"verified": true,
"sourceUrl": "https://docs.mistral.ai/inference/pricing"
},
{
"item": "Mistral Medium 3.5 output per 1M tokens",
"value": "$7.5",
"numeric": 7.5,
"unit": "USD/1M tokens",
"published": true,
"source": "docs_pricing",
"quote": "Mistral Medium 3.5 ↗ | $1.5 | $0.15 | $7.5",
"verified": true,
"sourceUrl": "https://docs.mistral.ai/inference/pricing"
},
{
"item": "Mistral Medium 3.5 context window",
"value": "256k",
"unit": "tokens",
"published": true,
"source": "card_medium",
"quote": "Context 256k",
"verified": true,
"sourceUrl": "https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04"
},
{
"item": "Mistral Small 4 input per 1M tokens",
"value": "$0.15",
"numeric": 0.15,
"unit": "USD/1M tokens",
"published": true,
"source": "docs_pricing",
"quote": "Mistral Small 4 ↗ | $0.15 | $0.015 | $0.6",
"verified": true,
"sourceUrl": "https://docs.mistral.ai/inference/pricing"
},
{
"item": "Mistral Small 4 cached input per 1M tokens",
"value": "$0.015",
"numeric": 0.015,
"unit": "USD/1M tokens",
"published": true,
"source": "docs_pricing",
"quote": "Mistral Small 4 ↗ | $0.15 | $0.015 | $0.6",
"verified": true,
"sourceUrl": "https://docs.mistral.ai/inference/pricing"
},
{
"item": "Mistral Small 4 output per 1M tokens",
"value": "$0.6",
"numeric": 0.6,
"unit": "USD/1M tokens",
"published": true,
"source": "docs_pricing",
"quote": "Mistral Small 4 ↗ | $0.15 | $0.015 | $0.6",
"verified": true,
"sourceUrl": "https://docs.mistral.ai/inference/pricing"
},
{
"item": "Mistral Small 4 context window",
"value": "256k",
"unit": "tokens",
"published": true,
"source": "card_small",
"quote": "Context 256k",
"verified": true,
"sourceUrl": "https://docs.mistral.ai/models/model-cards/mistral-small-4-0-26-03"
},
{
"item": "Mistral Large 3 input / cached input / output per 1M tokens",
"value": "$0.5 / $0.05 / $1.5",
"unit": "USD/1M tokens",
"published": true,
"source": "docs_pricing",
"quote": "Mistral Large 3 ↗ | $0.5 | $0.05 | $1.5",
"verified": true,
"sourceUrl": "https://docs.mistral.ai/inference/pricing"
},
{
"item": "Ministral 3 14B input / cached input / output per 1M tokens",
"value": "$0.2 / $0.02 / $0.2",
"unit": "USD/1M tokens",
"published": true,
"source": "docs_pricing",
"quote": "Ministral 3 14B ↗ | $0.2 | $0.02 | $0.2",
"verified": true,
"sourceUrl": "https://docs.mistral.ai/inference/pricing"
},
{
"item": "Ministral 3 8B input / cached input / output per 1M tokens",
"value": "$0.15 / $0.015 / $0.15",
"unit": "USD/1M tokens",
"published": true,
"source": "docs_pricing",
"quote": "Ministral 3 8B ↗ | $0.15 | $0.015 | $0.15",
"verified": true,
"sourceUrl": "https://docs.mistral.ai/inference/pricing"
},
{
"item": "Ministral 3 3B input / cached input / output per 1M tokens",
"value": "$0.1 / $0.01 / $0.1",
"unit": "USD/1M tokens",
"published": true,
"source": "docs_pricing",
"quote": "Ministral 3 3B ↗ | $0.1 | $0.01 | $0.1",
"verified": true,
"sourceUrl": "https://docs.mistral.ai/inference/pricing"
},
{
"item": "Codestral input / cached input / output per 1M tokens",
"value": "$0.3 / $0.03 / $0.9",
"unit": "USD/1M tokens",
"published": true,
"source": "docs_pricing",
"quote": "Codestral ↗ | $0.3 | $0.03 | $0.9",
"verified": true,
"sourceUrl": "https://docs.mistral.ai/inference/pricing"
},
{
"item": "Batch discount",
"value": "50%",
"numeric": 50,
"unit": "percent off",
"published": true,
"source": "pricing",
"quote": "Batch processing, for high-volume work, reduces the price by 50%, and cached input tokens reduce input cost by up to 90% for repeated prompts.",
"verified": true,
"sourceUrl": "https://mistral.ai/pricing#api-pricing"
},
{
"item": "Cached input discount",
"value": "Up to 90% off input cost for repeated prompts",
"numeric": 90,
"unit": "percent off (maximum)",
"published": true,
"source": "pricing",
"quote": "cached input tokens reduce input cost by up to 90% for repeated prompts",
"verified": true,
"sourceUrl": "https://mistral.ai/pricing#api-pricing"
},
{
"item": "Priority Tier multiplier",
"value": "1.75x standard list pricing",
"numeric": 1.75,
"unit": "multiplier",
"published": true,
"source": "priority",
"quote": "The multiplier is 1.75x standard list pricing, which is a 75% premium on input, output, and cached tokens.",
"verified": true,
"sourceUrl": "https://docs.mistral.ai/inference/priority-tier"
},
{
"item": "Rate limits per tier (RPM / TPM / RPD)",
"value": "Please visit https://console.mistral.ai/limits/ for detailed information on the current rate limit and usage tiers for your workspace.",
"unit": "",
"published": false,
"source": "tiers",
"quote": "Please visit https://console.mistral.ai/limits/ for detailed information on the current rate limit and usage tiers for your workspace.",
"verified": true,
"sourceUrl": "https://docs.mistral.ai/deployment/laplateforme/tier/"
},
{
"item": "Rate limit types",
"value": "Requests per second (RPS); tokens per minute/month. Limits are set at the workspace level and defined by usage tier.",
"unit": "",
"published": true,
"source": "tiers",
"quote": "We offer two types of rate limits: Requests per second (RPS) Tokens per minute/month",
"verified": true,
"sourceUrl": "https://docs.mistral.ai/deployment/laplateforme/tier/"
},
{
"item": "Spend or deposit to unlock each tier",
"value": "In case you need to raise your usage limits, please feel free to contact us by utilizing the support button, providing details about your specific use case.",
"unit": "",
"published": false,
"source": "tiers",
"quote": "In case you need to raise your usage limits, please feel free to contact us by utilizing the support button, providing details about your specific use case.",
"verified": true,
"sourceUrl": "https://docs.mistral.ai/deployment/laplateforme/tier/"
},
{
"item": "OCR 4.1 per 1,000 pages",
"value": "$4",
"numeric": 4,
"unit": "USD/1000 pages",
"published": true,
"source": "docs_pricing",
"quote": "OCR 4.1 ↗ | $4 | $0.4 | — (Prices /1000 Pages)",
"verified": true,
"sourceUrl": "https://docs.mistral.ai/inference/pricing"
},
{
"item": "Voice Agents API, Mistral Small 4",
"value": "$0.04/min",
"numeric": 0.04,
"unit": "USD/min",
"published": true,
"source": "docs_pricing",
"quote": "Mistral Small 4 | $0.04/min",
"verified": true,
"sourceUrl": "https://docs.mistral.ai/inference/pricing"
},
{
"item": "Voice Agents API, larger models",
"value": "$0.08/min",
"numeric": 0.08,
"unit": "USD/min",
"published": true,
"source": "docs_pricing",
"quote": "Larger models | $0.08/min",
"verified": true,
"sourceUrl": "https://docs.mistral.ai/inference/pricing"
}
],
"overage": {
"policy": "not published",
"summary": "Not found on the pages fetched. The billing docs page could not be fetched.",
"source": "tiers",
"quote": "Rate limits are set at the workspace level."
},
"gotchas": [
{
"title": "Priority Tier costs 1.75x",
"detail": "Priority Tier is billed at 1.75x standard list pricing on input, output and cached tokens. The multiplier is applied after the prompt cache discount.",
"source": "priority",
"quote": "The 1.75x multiplier applies after the prompt cache discount is applied.",
"sourceUrl": "https://docs.mistral.ai/inference/priority-tier"
},
{
"title": "Priority Tier requires setup with Mistral",
"detail": "Priority Tier limits are custom and model-specific and must be configured by Mistral. Requests that exceed them fall back to Standard Tier.",
"source": "priority",
"quote": "Priority Tier requires account setup with Mistral.",
"sourceUrl": "https://docs.mistral.ai/inference/priority-tier"
},
{
"title": "Batch runs over up to 24 hours",
"detail": "Batch requests are queued and processed over a 24-hour period, with no uptime SLA.",
"source": "priority",
"quote": "Requests are queued and processed over a 24-hour period",
"sourceUrl": "https://docs.mistral.ai/inference/priority-tier"
},
{
"title": "Non-token pricing for some APIs",
"detail": "OCR is priced per 1,000 pages, speech models per minute, and tool APIs per call.",
"source": "pricing",
"quote": "A few APIs are priced differently: OCR is per 1,000 pages, speech models are per minute, and tool APIs are priced per call.",
"sourceUrl": "https://mistral.ai/pricing#api-pricing"
},
{
"title": "Rate limits shown only in console",
"detail": "Current rate limits and usage tiers are shown in the console for each workspace, not in the public docs.",
"source": "tiers",
"quote": "You can view the rate and usage limits for your workspace under the limits section on la Plateforme.",
"sourceUrl": "https://docs.mistral.ai/deployment/laplateforme/tier/"
}
]
},
{
"id": "xai-api",
"name": "xAI Grok API",
"vendor": "xAI",
"category": "llm-api",
"url": "https://x.ai/api",
"checked": "2026-10-30",
"sources": {
"home": {
"name": "xAI API",
"url": "https://x.ai/api"
},
"models": {
"name": "Grok Models & Pricing | SpaceXSI Docs",
"url": "https://docs.x.ai/docs/models"
},
"legacy_tiers": {
"name": "Usage, Tiers and Rate Limits",
"url": "https://docs.x.ai/docs/usage-tiers-and-rate-limits"
},
"pricing": {
"name": "Pricing | SpaceXSI Docs",
"url": "https://docs.x.ai/developers/pricing"
},
"ratelimits": {
"name": "Rate Limits | SpaceXSI Docs",
"url": "https://docs.x.ai/developers/rate-limits"
},
"model47": {
"name": "grok-4.7 | SpaceXSI Docs",
"url": "https://docs.x.ai/developers/models/grok-4.7"
},
"batch": {
"name": "Batch API | SpaceXSI Docs",
"url": "https://docs.x.ai/developers/advanced-api-usage/batch-api"
}
},
"unit": {
"tag": "Per 1M tokens",
"definition": "Text API prices are per 1M tokens, in USD.",
"source": "pricing",
"quote": "All prices are in USD. ... Prices per 1M tokens"
},
"free": {
"summary": "No free tier or trial credits are stated. Tier 0 is the default tier at $0 cumulative spend.",
"published": false,
"source": "ratelimits",
"quote": "| Tier 0 | $0 (default) |"
},
"plans": [
{
"id": "payg",
"name": "Pay-as-you-go (Build on your own)",
"priceUsd": null,
"priceNote": "Usage-based; per-token rates in rates[]",
"billing": "usage",
"included": "Access to all Grok models, usage-based pricing, automatically increasing rate limits",
"source": "home",
"quote": "Access to all Grok models\n • Usage-based pricing\n • Automatically increasing rate limits",
"sourceUrl": "https://x.ai/api"
},
{
"id": "enterprise",
"name": "Enterprise (Get extra support)",
"priceUsd": null,
"priceNote": "Price not published",
"billing": "monthly",
"included": "Dedicated onboarding support, custom rate limits, billing via monthly invoices, single sign-on and audit logging, data residency options",
"source": "home",
"quote": "Dedicated onboarding support\n • Custom rate limits\n • Billing via monthly invoices\n • Single sign-on and audit logging\n • Data residency options",
"sourceUrl": "https://x.ai/api"
}
],
"rates": [
{
"item": "grok-4.7 input (prompt < 200k tokens)",
"value": "$2.00 per 1M tokens",
"numeric": 2,
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "| grok-4.7 Long context ≥ 200k tokens | 500k | $2.00 | $0.50 | $6.00 | $4.00 | $1.00 | $12.00 |",
"verified": true,
"sourceUrl": "https://docs.x.ai/developers/pricing"
},
{
"item": "grok-4.7 cached input (prompt < 200k tokens)",
"value": "$0.50 per 1M tokens",
"numeric": 0.5,
"unit": "USD/1M tokens",
"published": true,
"source": "model47",
"quote": "Cached tokens\n\n$0.50/ 1M tokens",
"verified": true,
"sourceUrl": "https://docs.x.ai/developers/models/grok-4.7"
},
{
"item": "grok-4.7 output (prompt < 200k tokens)",
"value": "$6.00 per 1M tokens",
"numeric": 6,
"unit": "USD/1M tokens",
"published": true,
"source": "model47",
"quote": "$6.00/ 1M tokens",
"verified": true,
"sourceUrl": "https://docs.x.ai/developers/models/grok-4.7"
},
{
"item": "grok-4.7 input / cached / output (prompt ≥ 200k tokens)",
"value": "$4.00 / $1.00 / $12.00 per 1M tokens",
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "| grok-4.7 Long context ≥ 200k tokens | 500k | $2.00 | $0.50 | $6.00 | $4.00 | $1.00 | $12.00 |",
"verified": true,
"sourceUrl": "https://docs.x.ai/developers/pricing"
},
{
"item": "grok-4.7 context window",
"value": "500,000 tokens",
"numeric": 500000,
"unit": "tokens",
"published": true,
"source": "model47",
"quote": "Context window\n\n500,000",
"verified": true,
"sourceUrl": "https://docs.x.ai/developers/models/grok-4.7"
},
{
"item": "grok-build-0.1 input / cached / output (prompt < 200k tokens)",
"value": "$1.00 / $0.20 / $2.00 per 1M tokens",
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "| grok-build-0.1 Long context ≥ 200k tokens | 256k | $1.00 | $0.20 | $2.00 | $2.00 | $0.40 | $4.00 |",
"verified": true,
"sourceUrl": "https://docs.x.ai/developers/pricing"
},
{
"item": "grok-build-0.1 input / cached / output (prompt ≥ 200k tokens)",
"value": "$2.00 / $0.40 / $4.00 per 1M tokens",
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "| grok-build-0.1 Long context ≥ 200k tokens | 256k | $1.00 | $0.20 | $2.00 | $2.00 | $0.40 | $4.00 |",
"verified": true,
"sourceUrl": "https://docs.x.ai/developers/pricing"
},
{
"item": "grok-build-0.1 context window",
"value": "256k tokens",
"numeric": 256000,
"unit": "tokens",
"published": true,
"source": "pricing",
"quote": "| grok-build-0.1 Long context ≥ 200k tokens | 256k |",
"verified": true,
"sourceUrl": "https://docs.x.ai/developers/pricing"
},
{
"item": "grok-4.6 input / cached / output (prompt < 200k; ≥ 200k)",
"value": "$2.00 / $0.50 / $6.00; $4.00 / $1.00 / $12.00 per 1M tokens; context 500k",
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "| grok-4.6 Long context ≥ 200k tokens | 500k | $2.00 | $0.50 | $6.00 | $4.00 | $1.00 | $12.00 |",
"verified": true,
"sourceUrl": "https://docs.x.ai/developers/pricing"
},
{
"item": "grok-4.5 input / cached / output (prompt < 200k; ≥ 200k)",
"value": "$2.00 / $0.30 / $6.00; $4.00 / $0.60 / $12.00 per 1M tokens; context 500k",
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "| grok-4.5 Long context ≥ 200k tokens | 500k | $2.00 | $0.30 | $6.00 | $4.00 | $0.60 | $12.00 |",
"verified": true,
"sourceUrl": "https://docs.x.ai/developers/pricing"
},
{
"item": "grok-4.3 input / cached / output (prompt < 200k; ≥ 200k)",
"value": "$1.25 / $0.20 / $2.50; $2.50 / $0.40 / $5.00 per 1M tokens; context 1M",
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "| grok-4.3 Long context ≥ 200k tokens | 1M | $1.25 | $0.20 | $2.50 | $2.50 | $0.40 | $5.00 |",
"verified": true,
"sourceUrl": "https://docs.x.ai/developers/pricing"
},
{
"item": "grok-4.20-0309-reasoning input / cached / output (prompt < 200k; ≥ 200k)",
"value": "$1.25 / $0.20 / $2.50; $2.50 / $0.40 / $5.00 per 1M tokens; context 1M",
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "| grok-4.20-0309-reasoning Long context ≥ 200k tokens | 1M | $1.25 | $0.20 | $2.50 | $2.50 | $0.40 | $5.00 |",
"verified": true,
"sourceUrl": "https://docs.x.ai/developers/pricing"
},
{
"item": "grok-4.20-0309-non-reasoning input / cached / output (prompt < 200k; ≥ 200k)",
"value": "$1.25 / $0.20 / $2.50; $2.50 / $0.40 / $5.00 per 1M tokens; context 1M",
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "| grok-4.20-0309-non-reasoning Long context ≥ 200k tokens | 1M | $1.25 | $0.20 | $2.50 | $2.50 | $0.40 | $5.00 |",
"verified": true,
"sourceUrl": "https://docs.x.ai/developers/pricing"
},
{
"item": "grok-4.20-multi-agent-0309 input / cached / output (prompt < 200k; ≥ 200k)",
"value": "$1.25 / $0.20 / $2.50; $2.50 / $0.40 / $5.00 per 1M tokens; context 1M",
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "| grok-4.20-multi-agent-0309 Long context ≥ 200k tokens | 1M | $1.25 | $0.20 | $2.50 | $2.50 | $0.40 | $5.00 |",
"verified": true,
"sourceUrl": "https://docs.x.ai/developers/pricing"
},
{
"item": "Batch API discount (grok-4.7, grok-4.6, grok-4.5, grok-4.3, grok-4.20-0309-reasoning, grok-4.20-0309-non-reasoning, grok-4.20-multi-agent-0309)",
"value": "20% off all token types",
"numeric": 20,
"unit": "percent",
"published": true,
"source": "pricing",
"quote": "The batch discount applies to all token types — input tokens, output tokens, cached tokens, and reasoning tokens.",
"verified": true,
"sourceUrl": "https://docs.x.ai/developers/pricing"
},
{
"item": "Batch API discount (models not listed, incl. grok-build-0.1)",
"value": "No batch discount",
"unit": "percent",
"published": true,
"source": "pricing",
"quote": "Models not listed above have no batch discount.",
"verified": true,
"sourceUrl": "https://docs.x.ai/developers/pricing"
},
{
"item": "Priority Processing",
"value": "2x standard rates",
"numeric": 2,
"unit": "multiplier",
"published": true,
"source": "pricing",
"quote": "Priority requests are billed at a **2x** premium over standard rates.",
"verified": true,
"sourceUrl": "https://docs.x.ai/developers/pricing"
},
{
"item": "US regional endpoint",
"value": "1.1x global token rates (grok-4.7 and grok-4.6 only)",
"numeric": 1.1,
"unit": "multiplier",
"published": true,
"source": "pricing",
"quote": "their token usage is billed at **1.1x** the global token rates, a 10% premium.",
"verified": true,
"sourceUrl": "https://docs.x.ai/developers/pricing"
},
{
"item": "Rate-limit tier spend thresholds",
"value": "Tier 0 $0 (default); Tier 1 $50; Tier 2 $250; Tier 3 $1,000; Tier 4 $5,000; Enterprise available on request",
"unit": "USD cumulative spend",
"published": true,
"source": "ratelimits",
"quote": "| Tier 0 | $0 (default) |\n| Tier 1 | $50 |\n| Tier 2 | $250 |\n| Tier 3 | $1,000 |\n| Tier 4 | $5,000 |",
"verified": true,
"sourceUrl": "https://docs.x.ai/developers/rate-limits"
},
{
"item": "grok-4.7 / grok-4.6 / grok-4.5 rate limits by tier (RPS; TPM)",
"value": "T0 150 RPS, 50M TPM; T1 172, 53M; T2 208, 60M; T3 312, 74M; T4 500, 100M",
"unit": "requests/sec; tokens/min",
"published": true,
"source": "ratelimits",
"quote": "| grok-4.7 | T0T1T2T3T4 | 150172208312500 | 50M53M60M74M100M |",
"verified": true,
"sourceUrl": "https://docs.x.ai/developers/rate-limits"
},
{
"item": "Requests per minute / requests per day",
"value": "Limits are set as requests per second (RPS) and tokens per minute (TPM); RPS is derived as RPM / 48 with a minimum of 2. No requests-per-day limit is stated.",
"unit": "",
"published": false,
"source": "ratelimits",
"quote": "Your per-second limit is derived from your per-minute request budget (RPM / 48, with a minimum of 2)",
"verified": true,
"sourceUrl": "https://docs.x.ai/developers/rate-limits"
},
{
"item": "Web Search tool",
"value": "$5 per 1k calls",
"numeric": 5,
"unit": "USD/1k calls",
"published": true,
"source": "pricing",
"quote": "| Search the internet and browse web pages | $5 / 1k calls",
"verified": true,
"sourceUrl": "https://docs.x.ai/developers/pricing"
},
{
"item": "X Search tool",
"value": "$5 per 1k posts; $10 per 1k profiles",
"unit": "USD/1k items",
"published": true,
"source": "pricing",
"quote": "$5 / 1k posts$10 / 1k profiles",
"verified": true,
"sourceUrl": "https://docs.x.ai/developers/pricing"
},
{
"item": "Code Execution tool",
"value": "$5 per 1k calls",
"numeric": 5,
"unit": "USD/1k calls",
"published": true,
"source": "pricing",
"quote": "| Run Python code in a sandboxed environment | $5 / 1k calls",
"verified": true,
"sourceUrl": "https://docs.x.ai/developers/pricing"
},
{
"item": "Collections Search tool",
"value": "$2.50 per 1k calls",
"numeric": 2.5,
"unit": "USD/1k calls",
"published": true,
"source": "pricing",
"quote": "| Query your uploaded document collections (RAG) | $2.50 / 1k calls",
"verified": true,
"sourceUrl": "https://docs.x.ai/developers/pricing"
},
{
"item": "File storage / collection storage",
"value": "$0.025 per GiB per day / $0.10 per GiB per day",
"unit": "USD/GiB/day",
"published": true,
"source": "pricing",
"quote": "| File storage | $0.025 / GiB / day |\n| Collection storage | $0.10 / GiB / day |",
"verified": true,
"sourceUrl": "https://docs.x.ai/developers/pricing"
},
{
"item": "Usage guideline violation fee (Responses API, caught before generation)",
"value": "$0.05 per request",
"numeric": 0.05,
"unit": "USD/request",
"published": true,
"source": "pricing",
"quote": "we will charge a $0.05 usage guideline violation fee per request.",
"verified": true,
"sourceUrl": "https://docs.x.ai/developers/pricing"
}
],
"overage": {
"policy": "not published",
"summary": "Tier qualification counts prepaid credit purchases or paid invoices. Billing details are on a separate Manage Billing page.",
"source": "ratelimits",
"quote": "Qualification is based on total revenue received through prepaid credit purchases or successfully fulfilled invoices."
},
"gotchas": [
{
"title": "Long-context pricing applies to the whole request",
"detail": "Once a prompt reaches the model's long-context threshold (200k tokens), all tokens in that request are billed at the long-context rates.",
"source": "pricing",
"quote": "Models with long context pricing bill the long context rates for all tokens in a request once its prompt reaches the model's long context threshold.",
"sourceUrl": "https://docs.x.ai/developers/pricing"
},
{
"title": "Reasoning and image tokens are billed",
"detail": "Input, reasoning, completion, image and cached prompt tokens are all billed at the rates of the model used in the request.",
"source": "pricing",
"quote": "All standard token types are billed for the model used in the request:",
"sourceUrl": "https://docs.x.ai/developers/pricing"
},
{
"title": "Cached tokens count toward TPM",
"detail": "Cached prompt tokens still count toward the tokens-per-minute limit, even though they are billed at a reduced rate.",
"source": "ratelimits",
"quote": "**Cached prompt tokens** (still count toward TPM, though they are billed at a reduced rate)",
"sourceUrl": "https://docs.x.ai/developers/rate-limits"
},
{
"title": "Batch discount excludes image and video",
"detail": "The batch discount applies only to text and language models. Image and video generation in the Batch API are billed at standard rates.",
"source": "pricing",
"quote": "The batch discount applies to text and language models only. Image and video generation are supported in the Batch API but are billed at standard rates.",
"sourceUrl": "https://docs.x.ai/developers/pricing"
},
{
"title": "Batch requests are exempt from rate limits",
"detail": "Batch requests do not count towards rate limits, and most finish within 24 hours.",
"source": "pricing",
"quote": "| Rate limits | Per-minute limits apply | Requests don't count towards rate limits |",
"sourceUrl": "https://docs.x.ai/developers/pricing"
},
{
"title": "Policy-violating requests are still charged",
"detail": "Requests flagged as violating usage guidelines are still charged for generation. Violations caught before generation in the Responses API incur a $0.05 fee.",
"source": "pricing",
"quote": "When your request is deemed to be in violation of our usage guideline by our system, we will still charge for the generation of the request.",
"sourceUrl": "https://docs.x.ai/developers/pricing"
},
{
"title": "Tiers count spend since Jan 1, 2026 and never downgrade",
"detail": "Tier is based on cumulative API spend since January 1, 2026. Once you reach a tier you keep it permanently.",
"source": "ratelimits",
"quote": "Your tier is based on cumulative spend on the xAI API since January 1, 2026.",
"sourceUrl": "https://docs.x.ai/developers/rate-limits"
},
{
"title": "Rate-limit tiers don't cover Imagine",
"detail": "Tiers apply to text, embedding and voice models. Imagine API limit increases require contacting sales@x.ai.",
"source": "ratelimits",
"quote": "Rate limit tiers apply to text, embedding, and voice models. For increases to Imagine API limits, contact sales@x.ai.",
"sourceUrl": "https://docs.x.ai/developers/rate-limits"
},
{
"title": "Grok 4.7 Fast is not on the public API",
"detail": "Grok 4.7 Fast is offered only in Cursor and Grok Build at 2x standard rates (1.5x for long context). It is not available on the public xAI API.",
"source": "pricing",
"quote": "It is not available on the public xAI API, and Grok Build's free tier does not include it.",
"sourceUrl": "https://docs.x.ai/developers/pricing"
},
{
"title": "grok-4.7 always returns encrypted reasoning",
"detail": "On the Responses API, grok-4.7 always returns reasoning.encrypted_content, even when include does not list it.",
"source": "models",
"quote": "`grok-4.7` always returns `reasoning.encrypted_content`, even when `include` does not list it.",
"sourceUrl": "https://docs.x.ai/docs/models"
},
{
"title": "logprobs ignored on newer models",
"detail": "logprobs and top_logprobs are not supported by grok-4.20 and newer, and are silently ignored if set.",
"source": "models",
"quote": "`logprobs` and `top_logprobs` are not supported by models `grok-4.20` and newer. These fields will be silently ignored if set.",
"sourceUrl": "https://docs.x.ai/docs/models"
}
]
},
{
"id": "deepseek-api",
"name": "DeepSeek API",
"vendor": "DeepSeek",
"category": "llm-api",
"url": "https://api-docs.deepseek.com/",
"checked": "2026-10-30",
"sources": {
"home": {
"name": "Your First API Call | DeepSeek API Docs",
"url": "https://api-docs.deepseek.com/quick_start/pricing"
},
"ratelimit": {
"name": "Rate Limit & Isolation | DeepSeek API Docs",
"url": "https://api-docs.deepseek.com/quick_start/rate_limit"
},
"news": {
"name": "DeepSeek-V4.1-Flash-1017: Wish-Driven Programming Made Real | DeepSeek API Docs",
"url": "https://api-docs.deepseek.com/news/news261017"
},
"errors": {
"name": "Error Codes | DeepSeek API Docs",
"url": "https://api-docs.deepseek.com/quick_start/error_codes"
},
"tokens": {
"name": "Token & Token Usage | DeepSeek API Docs",
"url": "https://api-docs.deepseek.com/quick_start/token_usage"
}
},
"unit": {
"tag": "Per token",
"definition": "Tokens are the basic units used by models to represent natural language text, and also the units used for billing.",
"source": "tokens",
"quote": "Tokens are the basic units used by models to represent natural language text, and also the units we use for billing."
},
"free": {
"summary": "Not verified",
"published": false,
"source": "home",
"quote": ""
},
"plans": [
{
"id": "payg",
"name": "Pay-as-you-go API",
"priceUsd": null,
"priceNote": "Per-token prices not verified",
"billing": "usage",
"included": "Access to deepseek-flash and deepseek-v4-pro; account balance is topped up on the Top up page.",
"source": "errors",
"quote": "Cause: You have run out of balance. Solution: Please check your account's balance, and go to the Top up page to add funds.",
"sourceUrl": "https://api-docs.deepseek.com/quick_start/error_codes"
}
],
"rates": [
{
"item": "deepseek-flash concurrency limit per account",
"value": "2500",
"numeric": 2500,
"unit": "concurrent requests",
"published": true,
"source": "ratelimit",
"quote": "| Concurrency Limit | 2500 | 500 |",
"verified": true,
"sourceUrl": "https://api-docs.deepseek.com/quick_start/rate_limit"
},
{
"item": "deepseek-v4-pro concurrency limit per account",
"value": "500",
"numeric": 500,
"unit": "concurrent requests",
"published": true,
"source": "ratelimit",
"quote": "| Concurrency Limit | 2500 | 500 |",
"verified": true,
"sourceUrl": "https://api-docs.deepseek.com/quick_start/rate_limit"
},
{
"item": "Requests per minute / tokens per minute / requests per day",
"value": "Limits are stated as concurrency per account; higher concurrency is available by capacity expansion request at no additional cost.",
"unit": "",
"published": false,
"source": "ratelimit",
"quote": "For each account, the concurrency limits for different DeepSeek API models are shown in the table below.",
"verified": true,
"sourceUrl": "https://api-docs.deepseek.com/quick_start/rate_limit"
},
{
"item": "Capacity expansion (higher concurrency)",
"value": "No additional cost",
"numeric": 0,
"unit": "USD",
"published": true,
"source": "ratelimit",
"quote": "There is no additional cost for capacity expansion.",
"verified": true,
"sourceUrl": "https://api-docs.deepseek.com/quick_start/rate_limit"
},
{
"item": "Search API / Fetch API per 1,000 calls (each endpoint)",
"value": "$0.75 per 1,000 calls",
"numeric": 0.75,
"unit": "USD/1,000 calls",
"published": true,
"source": "news",
"quote": "💰 Each endpoint: $0.75 per 1,000 calls.",
"verified": true,
"sourceUrl": "https://api-docs.deepseek.com/news/news261017"
}
],
"overage": {
"policy": "hard-stop",
"summary": "When the account balance runs out, requests return error 402 Insufficient Balance; funds are added on the Top up page.",
"source": "errors",
"quote": "402 - Insufficient Balance | Cause: You have run out of balance. Solution: Please check your account's balance, and go to the Top up page to add funds."
},
"gotchas": [
{
"title": "Legacy Flash model names billed at Flash price",
"detail": "deepseek-v4-flash and deepseek-v4-flash-vision-exp are still accepted but retired; requests are served by DeepSeek-V4.1-Flash-1017 and billed at the Flash price.",
"source": "home",
"quote": "The legacy names `deepseek-v4-flash` and `deepseek-v4-flash-vision-exp` are still accepted, but the corresponding models have been retired; their requests are served by DeepSeek-V4.1-Flash-1017 and billed at the Flash price.",
"sourceUrl": "https://api-docs.deepseek.com/quick_start/pricing"
},
{
"title": "Concurrency is account-wide",
"detail": "Concurrency limits apply at the account level regardless of API key; exceeding them returns HTTP 429.",
"source": "ratelimit",
"quote": "Concurrency limits are calculated at the account level, regardless of which API Key is used",
"sourceUrl": "https://api-docs.deepseek.com/quick_start/rate_limit"
},
{
"title": "Per-user_id limits on expanded accounts",
"detail": "For accounts with increased concurrency, each user_id is limited to 2500 concurrent requests on deepseek-flash and 500 on deepseek-v4-pro.",
"source": "ratelimit",
"quote": "For each `user_id`, the concurrency limit for `deepseek-flash` is 2500, and for `deepseek-v4-pro` it is 500.",
"sourceUrl": "https://api-docs.deepseek.com/quick_start/rate_limit"
},
{
"title": "Requests closed after 10 minutes without inference",
"detail": "If inference has not started 10 minutes after the request, the server closes the connection.",
"source": "ratelimit",
"quote": "If the request has not started inference after 10 minutes, the server will close the connection.",
"sourceUrl": "https://api-docs.deepseek.com/quick_start/rate_limit"
},
{
"title": "Images consume tokens",
"detail": "Images are counted in tokens based on their dimensions, with an upper bound per image.",
"source": "tokens",
"quote": "Images are automatically resized before inference, and there is an upper bound on the number of tokens per image",
"sourceUrl": "https://api-docs.deepseek.com/quick_start/token_usage"
},
{
"title": "Search & Fetch billing in agent tools starts Oct 31, 2026",
"detail": "Search & Fetch calls via server-side tools in DeepSeek Harness, Claude Code, and Codex are free for DeepSeek API users until billing starts Oct 31, 2026, 16:00 UTC.",
"source": "news",
"quote": "Search & Fetch calls via server-side tools in DeepSeek Harness, Claude Code, and Codex are currently free for DeepSeek API users. Billing starts **Oct 31, 2026, at 16:00 UTC**.",
"sourceUrl": "https://api-docs.deepseek.com/news/news261017"
}
]
},
{
"id": "groq",
"name": "GroqCloud",
"vendor": "Groq",
"category": "llm-api",
"url": "https://groq.com",
"checked": "2026-10-30",
"sources": {
"pricing": {
"name": "Groq is the premier neocloud for fast inference",
"url": "https://groq.com/pricing"
},
"ratelimits": {
"name": "Rate Limits - GroqDocs",
"url": "https://console.groq.com/docs/rate-limits"
},
"models": {
"name": "Models - GroqDocs",
"url": "https://console.groq.com/docs/models"
},
"billing": {
"name": "Billing FAQs - GroqDocs",
"url": "https://console.groq.com/docs/billing-faqs"
},
"spend": {
"name": "Spend Limits - GroqDocs",
"url": "https://console.groq.com/docs/spend-limits"
},
"caching": {
"name": "Prompt Caching - GroqDocs",
"url": "https://console.groq.com/docs/prompt-caching"
},
"batch": {
"name": "Batch Processing - GroqDocs",
"url": "https://console.groq.com/docs/batch"
},
"m120b": {
"name": "OpenAI GPT-OSS 120B - GroqDocs",
"url": "https://console.groq.com/docs/model/openai/gpt-oss-120b"
},
"m20b": {
"name": "OpenAI GPT-OSS 20B - GroqDocs",
"url": "https://console.groq.com/docs/model/openai/gpt-oss-20b"
},
"mqwen": {
"name": "Qwen/Qwen3.8-27B - GroqDocs",
"url": "https://console.groq.com/docs/model/qwen/qwen3.8-27b"
},
"yourdata": {
"name": "Your Data - GroqDocs",
"url": "https://console.groq.com/docs/your-data"
}
},
"unit": {
"tag": "Per 1M tokens",
"definition": "Price per 1M tokens, listed separately for input and output; audio transcription priced per hour, text-to-speech per 1M characters.",
"source": "models",
"quote": "PRICE PER 1M TOKENS"
},
"free": {
"summary": "Free tier with its own lower rate limits. Upgrading to the Developer tier requires a valid payment method. Groq occasionally offers promotional credits, such as at hackathons and special events.",
"published": true,
"source": "billing",
"quote": "To upgrade from the Free tier to the Developer tier, you'll need to provide a valid payment method (credit card, US bank account, or SEPA debit account)."
},
"plans": [
{
"id": "free",
"name": "Free",
"priceUsd": null,
"priceNote": "No price printed; Free tier",
"billing": "usage",
"included": "Free plan rate limits (see rates).",
"source": "ratelimits",
"quote": "Free Plan Limits",
"sourceUrl": "https://console.groq.com/docs/rate-limits"
},
{
"id": "developer",
"name": "Developer",
"priceUsd": null,
"priceNote": "Pay-as-you-go per-token pricing; no upfront charge",
"billing": "usage",
"included": "Higher token limits, chat support, Flex service tier, Batch processing, Spend Limits.",
"source": "billing",
"quote": "The Developer tier is designed for developers and companies who want increased capacity and more features with pay-as-you-go pricing.",
"sourceUrl": "https://console.groq.com/docs/billing-faqs"
},
{
"id": "enterprise",
"name": "Enterprise",
"priceUsd": null,
"priceNote": "Contact sales",
"billing": "usage",
"included": "Higher limits for select workloads and enterprise use cases; Enterprise-only models.",
"source": "ratelimits",
"quote": "Note that the limits shown below are the base limits for the Developer plan, and higher limits are available for select workloads and enterprise use cases.",
"sourceUrl": "https://console.groq.com/docs/rate-limits"
}
],
"rates": [
{
"item": "openai/gpt-oss-120b input per 1M tokens",
"value": "$0.15",
"numeric": 0.15,
"unit": "USD/1M tokens",
"published": true,
"source": "models",
"quote": "$0.15 input$0.60 output",
"verified": true,
"sourceUrl": "https://console.groq.com/docs/models"
},
{
"item": "openai/gpt-oss-120b cached input per 1M tokens",
"value": "$0.075",
"numeric": 0.075,
"unit": "USD/1M tokens",
"published": true,
"source": "m120b",
"quote": "Cached Input\n\n$0.075",
"verified": true,
"sourceUrl": "https://console.groq.com/docs/model/openai/gpt-oss-120b"
},
{
"item": "openai/gpt-oss-120b output per 1M tokens",
"value": "$0.60",
"numeric": 0.6,
"unit": "USD/1M tokens",
"published": true,
"source": "models",
"quote": "$0.15 input$0.60 output",
"verified": true,
"sourceUrl": "https://console.groq.com/docs/models"
},
{
"item": "openai/gpt-oss-120b context window",
"value": "131,072 tokens",
"numeric": 131072,
"unit": "tokens",
"published": true,
"source": "m120b",
"quote": "CONTEXT WINDOW\n\n131,072",
"verified": true,
"sourceUrl": "https://console.groq.com/docs/model/openai/gpt-oss-120b"
},
{
"item": "openai/gpt-oss-120b max output tokens",
"value": "65,536 tokens",
"numeric": 65536,
"unit": "tokens",
"published": true,
"source": "m120b",
"quote": "MAX OUTPUT TOKENS\n\n65,536",
"verified": true,
"sourceUrl": "https://console.groq.com/docs/model/openai/gpt-oss-120b"
},
{
"item": "openai/gpt-oss-20b input per 1M tokens",
"value": "$0.075",
"numeric": 0.075,
"unit": "USD/1M tokens",
"published": true,
"source": "models",
"quote": "$0.075 input$0.30 output",
"verified": true,
"sourceUrl": "https://console.groq.com/docs/models"
},
{
"item": "openai/gpt-oss-20b cached input per 1M tokens",
"value": "$0.037",
"numeric": 0.037,
"unit": "USD/1M tokens",
"published": true,
"source": "m20b",
"quote": "Cached Input\n\n$0.037",
"verified": true,
"sourceUrl": "https://console.groq.com/docs/model/openai/gpt-oss-20b"
},
{
"item": "openai/gpt-oss-20b output per 1M tokens",
"value": "$0.30",
"numeric": 0.3,
"unit": "USD/1M tokens",
"published": true,
"source": "models",
"quote": "$0.075 input$0.30 output",
"verified": true,
"sourceUrl": "https://console.groq.com/docs/models"
},
{
"item": "openai/gpt-oss-20b context window / max output",
"value": "131,072 / 65,536 tokens",
"unit": "tokens",
"published": true,
"source": "m20b",
"quote": "CONTEXT WINDOW\n\n131,072\n\n* * *\n\nMAX OUTPUT TOKENS\n\n65,536",
"verified": true,
"sourceUrl": "https://console.groq.com/docs/model/openai/gpt-oss-20b"
},
{
"item": "openai/gpt-oss-safeguard-20b (Preview) input / output per 1M tokens",
"value": "$0.075 input, $0.30 output",
"unit": "USD/1M tokens",
"published": true,
"source": "models",
"quote": "$0.075 input$0.30 output",
"verified": true,
"sourceUrl": "https://console.groq.com/docs/models"
},
{
"item": "openai/gpt-oss-safeguard-20b context window / max completion",
"value": "131,072 / 65,536 tokens",
"unit": "tokens",
"published": true,
"source": "models",
"quote": "| 1000 | $0.075 input$0.30 output | 150K TPM1K RPM | 131,072 | 65,536 ",
"verified": true,
"sourceUrl": "https://console.groq.com/docs/models"
},
{
"item": "qwen/qwen3.8-27b (Preview) input per 1M tokens",
"value": "$0.80",
"numeric": 0.8,
"unit": "USD/1M tokens",
"published": true,
"source": "models",
"quote": "$0.80 input$4.00 output",
"verified": true,
"sourceUrl": "https://console.groq.com/docs/models"
},
{
"item": "qwen/qwen3.8-27b (Preview) output per 1M tokens",
"value": "$4.00",
"numeric": 4,
"unit": "USD/1M tokens",
"published": true,
"source": "models",
"quote": "$0.80 input$4.00 output",
"verified": true,
"sourceUrl": "https://console.groq.com/docs/models"
},
{
"item": "qwen/qwen3.8-27b context window / max output",
"value": "131,072 / 16,384 tokens",
"unit": "tokens",
"published": true,
"source": "mqwen",
"quote": "CONTEXT WINDOW\n\n131,072\n\n* * *\n\nMAX OUTPUT TOKENS\n\n16,384",
"verified": true,
"sourceUrl": "https://console.groq.com/docs/model/qwen/qwen3.8-27b"
},
{
"item": "meta-llama/llama-prompt-guard-2-22m (Preview) input / output per 1M tokens",
"value": "$0.03 input, $0.03 output; context 512, max completion 512",
"unit": "USD/1M tokens",
"published": true,
"source": "models",
"quote": "$0.03 input$0.03 output",
"verified": true,
"sourceUrl": "https://console.groq.com/docs/models"
},
{
"item": "meta-llama/llama-prompt-guard-2-86m (Preview) input / output per 1M tokens",
"value": "$0.04 input, $0.04 output; context 512, max completion 512",
"unit": "USD/1M tokens",
"published": true,
"source": "models",
"quote": "$0.04 input$0.04 output",
"verified": true,
"sourceUrl": "https://console.groq.com/docs/models"
},
{
"item": "whisper-large-v3 transcription",
"value": "$0.111 per hour; max file size 100 MB",
"numeric": 0.111,
"unit": "USD/audio hour",
"published": true,
"source": "models",
"quote": "$0.111 per hour",
"verified": true,
"sourceUrl": "https://console.groq.com/docs/models"
},
{
"item": "whisper-large-v3-turbo transcription",
"value": "$0.04 per hour; max file size 100 MB",
"numeric": 0.04,
"unit": "USD/audio hour",
"published": true,
"source": "models",
"quote": "$0.04 per hour",
"verified": true,
"sourceUrl": "https://console.groq.com/docs/models"
},
{
"item": "canopylabs/orpheus-v1-english (Preview) text-to-speech",
"value": "$22.00 per 1M characters",
"numeric": 22,
"unit": "USD/1M characters",
"published": true,
"source": "models",
"quote": "$22.00 per 1M characters",
"verified": true,
"sourceUrl": "https://console.groq.com/docs/models"
},
{
"item": "canopylabs/orpheus-arabic-saudi (Preview) text-to-speech",
"value": "$40.00 per 1M characters",
"numeric": 40,
"unit": "USD/1M characters",
"published": true,
"source": "models",
"quote": "$40.00 per 1M characters",
"verified": true,
"sourceUrl": "https://console.groq.com/docs/models"
},
{
"item": "llama-3.1-8b-instant (Enterprise) price",
"value": "Contact Sales; context 131,072, max completion 131,072",
"unit": "USD/1M tokens",
"published": false,
"source": "models",
"quote": "| 560 | ContactSales | ContactSales | 131,072 | 131,072 ",
"verified": true,
"sourceUrl": "https://console.groq.com/docs/models"
},
{
"item": "llama-3.3-70b-versatile (Enterprise) price",
"value": "Contact Sales; context 131,072, max completion 32,768",
"unit": "USD/1M tokens",
"published": false,
"source": "models",
"quote": "| 280 | ContactSales | ContactSales | 131,072 | 32,768 ",
"verified": true,
"sourceUrl": "https://console.groq.com/docs/models"
},
{
"item": "meta-models/muse-spark-open (Enterprise, Preview) price",
"value": "Contact Sales; context 131,072, max completion 131,072",
"unit": "USD/1M tokens",
"published": false,
"source": "models",
"quote": "| 350 | ContactSales | ContactSales | 131,072 | 131,072 ",
"verified": true,
"sourceUrl": "https://console.groq.com/docs/models"
},
{
"item": "minimaxai/minimax-m2.7 (Enterprise, Preview) price",
"value": "Contact Sales; context 196,608, max completion 131,072",
"unit": "USD/1M tokens",
"published": false,
"source": "models",
"quote": "| 260 | ContactSales | ContactSales | 196,608 | 131,072 ",
"verified": true,
"sourceUrl": "https://console.groq.com/docs/models"
},
{
"item": "Cached input discount",
"value": "50% discount for cached input tokens (supported models only)",
"numeric": 50,
"unit": "% off input",
"published": true,
"source": "caching",
"quote": "Prompt caching is provided at no additional cost. There is a 50% discount for cached input tokens.",
"verified": true,
"sourceUrl": "https://console.groq.com/docs/prompt-caching"
},
{
"item": "Batch discount",
"value": "50% cost discount compared to synchronous API pricing; 24-hour to 7-day processing window",
"numeric": 50,
"unit": "% off",
"published": true,
"source": "batch",
"quote": "Pricing is at a 50% cost discount compared to [synchronous API pricing.](https://groq.com/pricing)",
"verified": true,
"sourceUrl": "https://console.groq.com/docs/batch"
},
{
"item": "Developer plan rate limit: openai/gpt-oss-120b",
"value": "250K TPM, 1K RPM",
"unit": "TPM/RPM",
"published": true,
"source": "models",
"quote": "250K TPM1K RPM",
"verified": true,
"sourceUrl": "https://console.groq.com/docs/models"
},
{
"item": "Developer plan rate limit: openai/gpt-oss-20b",
"value": "250K TPM, 1K RPM",
"unit": "TPM/RPM",
"published": true,
"source": "models",
"quote": "250K TPM1K RPM",
"verified": true,
"sourceUrl": "https://console.groq.com/docs/models"
},
{
"item": "Developer plan rate limit: openai/gpt-oss-safeguard-20b",
"value": "150K TPM, 1K RPM",
"unit": "TPM/RPM",
"published": true,
"source": "models",
"quote": "150K TPM1K RPM",
"verified": true,
"sourceUrl": "https://console.groq.com/docs/models"
},
{
"item": "Developer plan rate limit: qwen/qwen3.8-27b",
"value": "250K TPM, 1K RPM",
"unit": "TPM/RPM",
"published": true,
"source": "models",
"quote": "250K TPM1K RPM",
"verified": true,
"sourceUrl": "https://console.groq.com/docs/models"
},
{
"item": "Developer plan rate limit: llama-prompt-guard-2-22m / 86m",
"value": "30K TPM, 100 RPM",
"unit": "TPM/RPM",
"published": true,
"source": "models",
"quote": "30K TPM100 RPM",
"verified": true,
"sourceUrl": "https://console.groq.com/docs/models"
},
{
"item": "Developer plan rate limit: whisper-large-v3",
"value": "200K ASH, 300 RPM",
"unit": "audio seconds per hour / RPM",
"published": true,
"source": "models",
"quote": "200K ASH300 RPM",
"verified": true,
"sourceUrl": "https://console.groq.com/docs/models"
},
{
"item": "Developer plan rate limit: whisper-large-v3-turbo",
"value": "400K ASH, 400 RPM",
"unit": "audio seconds per hour / RPM",
"published": true,
"source": "models",
"quote": "400K ASH400 RPM",
"verified": true,
"sourceUrl": "https://console.groq.com/docs/models"
},
{
"item": "Developer plan rate limit: Orpheus (English and Arabic Saudi)",
"value": "50K TPM, 250 RPM",
"unit": "TPM/RPM",
"published": true,
"source": "models",
"quote": "50K TPM250 RPM",
"verified": true,
"sourceUrl": "https://console.groq.com/docs/models"
},
{
"item": "Free plan rate limit: openai/gpt-oss-120b",
"value": "30 RPM, 1K RPD, 8K TPM, 200K TPD",
"unit": "RPM/RPD/TPM/TPD",
"published": true,
"source": "ratelimits",
"quote": "| openai/gpt-oss-120b | 30 | 1K | 8K | 200K | - | - |",
"verified": true,
"sourceUrl": "https://console.groq.com/docs/rate-limits"
},
{
"item": "Free plan rate limit: openai/gpt-oss-20b",
"value": "30 RPM, 1K RPD, 8K TPM, 200K TPD",
"unit": "RPM/RPD/TPM/TPD",
"published": true,
"source": "ratelimits",
"quote": "| openai/gpt-oss-20b | 30 | 1K | 8K | 200K | - | - |",
"verified": true,
"sourceUrl": "https://console.groq.com/docs/rate-limits"
},
{
"item": "Free plan rate limit: openai/gpt-oss-safeguard-20b",
"value": "3 RPM, 1K RPD, 2K TPM, 200K TPD",
"unit": "RPM/RPD/TPM/TPD",
"published": true,
"source": "ratelimits",
"quote": "| openai/gpt-oss-safeguard-20b | 3 | 1K | 2K | 200K | - | - |",
"verified": true,
"sourceUrl": "https://console.groq.com/docs/rate-limits"
},
{
"item": "Free plan rate limit: qwen/qwen3.8-27b",
"value": "30 RPM, 1K RPD, 8K TPM, 200K TPD",
"unit": "RPM/RPD/TPM/TPD",
"published": true,
"source": "ratelimits",
"quote": "| qwen/qwen3.8-27b | 30 | 1K | 8K | 200K | - | - |",
"verified": true,
"sourceUrl": "https://console.groq.com/docs/rate-limits"
},
{
"item": "Free plan rate limit: llama-prompt-guard-2-22m / 86m",
"value": "30 RPM, 14.4K RPD, 15K TPM, 500K TPD",
"unit": "RPM/RPD/TPM/TPD",
"published": true,
"source": "ratelimits",
"quote": "| meta-llama/llama-prompt-guard-2-22m | 30 | 14.4K | 15K | 500K | - | - |",
"verified": true,
"sourceUrl": "https://console.groq.com/docs/rate-limits"
},
{
"item": "Free plan rate limit: whisper-large-v3 and whisper-large-v3-turbo",
"value": "20 RPM, 2K RPD, 7.2K ASH, 28.8K ASD",
"unit": "RPM/RPD/ASH/ASD",
"published": true,
"source": "ratelimits",
"quote": "| whisper-large-v3 | 20 | 2K | - | - | 7.2K | 28.8K |",
"verified": true,
"sourceUrl": "https://console.groq.com/docs/rate-limits"
},
{
"item": "Free plan rate limit: Orpheus (English and Arabic Saudi)",
"value": "10 RPM, 100 RPD, 1.2K TPM, 3.6K TPD",
"unit": "RPM/RPD/TPM/TPD",
"published": true,
"source": "ratelimits",
"quote": "| canopylabs/orpheus-v1-english | 10 | 100 | 1.2K | 3.6K | - | - |",
"verified": true,
"sourceUrl": "https://console.groq.com/docs/rate-limits"
},
{
"item": "Tier unlock: Free to Developer",
"value": "Add a valid payment method; no immediate charge",
"published": true,
"source": "billing",
"quote": "When you upgrade, **there's no immediate charge** - you'll be billed for tokens at month-end or when you reach progressive billing thresholds",
"verified": true,
"sourceUrl": "https://console.groq.com/docs/billing-faqs"
},
{
"item": "Progressive billing thresholds (new Developer accounts)",
"value": "$1, $10, $100, $500, $1,000 cumulative usage",
"unit": "USD",
"published": true,
"source": "billing",
"quote": "an invoice is automatically triggered and payment is deducted when your cumulative usage reaches specific thresholds: $1, $10, $100, $500, and $1,000.",
"verified": true,
"sourceUrl": "https://console.groq.com/docs/billing-faqs"
},
{
"item": "Minimum billable amount",
"value": "Billed only once usage reaches at least $0.50",
"numeric": 0.5,
"unit": "USD",
"published": true,
"source": "billing",
"quote": "We only bill you once your usage has reached at least $0.50.",
"verified": true,
"sourceUrl": "https://console.groq.com/docs/billing-faqs"
}
],
"overage": {
"policy": "pay-as-you-go",
"summary": "Postpaid: usage is invoiced monthly in arrears (with early invoices at progressive thresholds for new accounts) and charged automatically to the payment method on file. Optional monthly spend limits block API access when reached.",
"source": "billing",
"quote": "Groq uses a monthly billing cycle, where you receive an invoice in arrears for usage."
},
"gotchas": [
{
"title": "Batch discount does not stack with caching",
"detail": "All batch tokens are billed at the 50% batch rate regardless of cache status.",
"source": "batch",
"quote": "**Note:** The batch discount does not stack with [prompt caching](https://console.groq.com/docs/prompt-caching) discounts. All batch tokens are billed at the 50% batch rate regardless of cache status.",
"sourceUrl": "https://console.groq.com/docs/batch"
},
{
"title": "Prompt caching limited to three models and not guaranteed",
"detail": "Prompt caching is only supported for openai/gpt-oss-20b, openai/gpt-oss-120b and openai/gpt-oss-safeguard-20b. Cache hits are not guaranteed, and the discount applies only on successful hits. Cached data expires after 2 hours without use.",
"source": "caching",
"quote": "Groq tries to maximize cache hits, but this is not guaranteed. Pricing discount will only apply on successful cache hits.",
"sourceUrl": "https://console.groq.com/docs/prompt-caching"
},
{
"title": "Cached tokens and rate limits",
"detail": "Cached tokens do not count toward rate limits but are subtracted from limits after processing.",
"source": "caching",
"quote": "Cached tokens do not count towards your rate limits. However, cached tokens are subtracted from your limits after processing",
"sourceUrl": "https://console.groq.com/docs/prompt-caching"
},
{
"title": "Spend limit can be overshot",
"detail": "Spend tracking has a 10-15 minute delay, so usage can exceed the limit by a small amount. When the limit is reached, API calls return 400 blocked_api_access. Spend limits are only available on paid plans.",
"source": "spend",
"quote": "There's a 10-15 minute delay in spend tracking. This means you might exceed your limit by a small amount during high usage periods.",
"sourceUrl": "https://console.groq.com/docs/spend-limits"
},
{
"title": "Different billing thresholds in India",
"detail": "Customers with an Indian billing address are billed at $1, $10, and then every $100.",
"source": "billing",
"quote": "For India customers, the thresholds are only $1, $10, and then $100 recurring.",
"sourceUrl": "https://console.groq.com/docs/billing-faqs"
},
{
"title": "Rate limits are per organization; separate input/output caps may apply",
"detail": "Limits apply at the organization level. Some organizations also have separate input (ITPM) and output (OTPM) token-per-minute limits.",
"source": "ratelimits",
"quote": "Rate limits apply at the organization level, not individual users.",
"sourceUrl": "https://console.groq.com/docs/rate-limits"
},
{
"title": "Some models are Enterprise-only",
"detail": "Llama 3.1 8B, Llama 3.3 70B, Muse Spark Open and MiniMax M2.7 are listed as Enterprise with Contact Sales pricing.",
"source": "models",
"quote": "ContactSales",
"sourceUrl": "https://console.groq.com/docs/models"
},
{
"title": "Preview models may be discontinued",
"detail": "Preview models are for evaluation only and may be discontinued at short notice.",
"source": "models",
"quote": "Preview models are intended for evaluation purposes only and should not be used in production environments as they may be discontinued at short notice.",
"sourceUrl": "https://console.groq.com/docs/models"
},
{
"title": "Expired batch jobs",
"detail": "If a batch job expires, only successfully completed requests are charged.",
"source": "batch",
"quote": "You are only charged for successfully completed requests",
"sourceUrl": "https://console.groq.com/docs/batch"
},
{
"title": "Image input limits on Qwen3.8-27B",
"detail": "Accepts text and images; max file size 20 MB, max 3 input images.",
"source": "mqwen",
"quote": "MAX INPUT IMAGES\n\n3",
"sourceUrl": "https://console.groq.com/docs/model/qwen/qwen3.8-27b"
}
]
},
{
"id": "together-ai",
"name": "Together AI",
"vendor": "Together AI",
"category": "llm-api",
"url": "https://www.together.ai/",
"checked": "2026-10-30",
"sources": {
"pricing": {
"name": "Pricing | Together AI",
"url": "https://www.together.ai/pricing"
},
"ratelimits": {
"name": "Rate limits (Together AI Docs)",
"url": "https://docs.together.ai/docs/rate-limits"
},
"models": {
"name": "Available models (Together AI Docs)",
"url": "https://docs.together.ai/docs/serverless/models.md"
},
"serverless": {
"name": "Serverless Overview (Together AI Docs)",
"url": "https://docs.together.ai/docs/serverless/overview.md"
},
"credits": {
"name": "Credits (Together AI Docs)",
"url": "https://docs.together.ai/docs/billing-credits.md"
},
"spend": {
"name": "Spend controls (Together AI Docs)",
"url": "https://docs.together.ai/docs/billing-spend-controls.md"
},
"batch": {
"name": "Batch Overview (Together AI Docs)",
"url": "https://docs.together.ai/docs/inference/batch/overview.md"
},
"kimik3": {
"name": "Kimi K3 | Together AI",
"url": "https://www.together.ai/models/kimi-k3"
}
},
"unit": {
"tag": "Per 1M tokens",
"definition": "Chat, language, embedding, and rerank models are billed per input and output token; prices are listed per 1M tokens.",
"source": "serverless",
"quote": "Chat, language, embedding, and rerank:** Per input and output token."
},
"free": {
"summary": "No free trial. Access requires a minimum $15 credit purchase.",
"published": true,
"source": "credits",
"quote": "Together AI does not currently offer free trials. Access to the Together platform requires a minimum \\$15 credit purchase."
},
"plans": [
{
"id": "prepaid-serverless",
"name": "Serverless (prepaid credits)",
"priceUsd": 15,
"priceNote": "Minimum first credit purchase; $5 minimum for later purchases. Usage billed per token.",
"billing": "usage",
"included": "Prepaid credits usable for API requests, dedicated model inference, fine-tuning, evaluation jobs and all other Together AI services.",
"source": "credits",
"quote": "The minimum is \\$15 for your organization's first purchase and \\$5 after that.",
"sourceUrl": "https://docs.together.ai/docs/billing-credits.md"
},
{
"id": "scale-enterprise",
"name": "Scale / Enterprise contract",
"priceUsd": null,
"priceNote": "Contact sales",
"billing": "usage",
"included": "Billed under contract terms; purchased rate limits stay in place until the contract expires.",
"source": "ratelimits",
"quote": "If you have an active Enterprise or Scale contract, your purchased rate limits stay in place until the contract expires.",
"sourceUrl": "https://docs.together.ai/docs/rate-limits"
}
],
"rates": [
{
"item": "Kimi K3 input per 1M tokens",
"value": "$3.00",
"numeric": 3,
"unit": "USD/1M tokens",
"published": true,
"source": "models",
"quote": "| Moonshot | Kimi K3 | moonshotai/Kimi-K3 | 1048576 | \\$3.00 | \\$0.30 | \\$15.00 |",
"verified": true,
"sourceUrl": "https://docs.together.ai/docs/serverless/models.md"
},
{
"item": "Kimi K3 cached input per 1M tokens",
"value": "$0.30",
"numeric": 0.3,
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "Kimi K3 | $3.00 $0.30 (cached) | $15.00",
"verified": true,
"sourceUrl": "https://www.together.ai/pricing"
},
{
"item": "Kimi K3 output per 1M tokens",
"value": "$15.00",
"numeric": 15,
"unit": "USD/1M tokens",
"published": true,
"source": "kimik3",
"quote": "On Together AI it costs $3.00 per 1M input tokens and $15.00 per 1M output tokens.",
"verified": true,
"sourceUrl": "https://www.together.ai/models/kimi-k3"
},
{
"item": "Kimi K3 context window",
"value": "1,048,576 tokens",
"numeric": 1048576,
"unit": "tokens",
"published": true,
"source": "models",
"quote": "| Moonshot | Kimi K3 | moonshotai/Kimi-K3 | 1048576 |",
"verified": true,
"sourceUrl": "https://docs.together.ai/docs/serverless/models.md"
},
{
"item": "Qwen3.8-2.4T-A95B input per 1M tokens",
"value": "$2.00",
"numeric": 2,
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "Qwen3.8-2.4T-A95B | $2.00 $0.25 (cached) | $6.00",
"verified": true,
"sourceUrl": "https://www.together.ai/pricing"
},
{
"item": "Qwen3.8-2.4T-A95B output per 1M tokens",
"value": "$6.00",
"numeric": 6,
"unit": "USD/1M tokens",
"published": true,
"source": "models",
"quote": "| Qwen | Qwen3.8-2.4T-A95B | Qwen/Qwen3.8-2.4T-A95B | - | \\$2.00 | \\$0.50 | \\$6.00 |",
"verified": true,
"sourceUrl": "https://docs.together.ai/docs/serverless/models.md"
},
{
"item": "GLM-5.3 input per 1M tokens",
"value": "$1.40",
"numeric": 1.4,
"unit": "USD/1M tokens",
"published": true,
"source": "models",
"quote": "| Z.ai | GLM-5.3 | zai-org/GLM-5.3 | 1048575 | \\$1.40 | \\$0.26 | \\$4.40 |",
"verified": true,
"sourceUrl": "https://docs.together.ai/docs/serverless/models.md"
},
{
"item": "GLM-5.3 cached input per 1M tokens",
"value": "$0.26",
"numeric": 0.26,
"unit": "USD/1M tokens",
"published": true,
"source": "models",
"quote": "| Z.ai | GLM-5.3 | zai-org/GLM-5.3 | 1048575 | \\$1.40 | \\$0.26 | \\$4.40 |",
"verified": true,
"sourceUrl": "https://docs.together.ai/docs/serverless/models.md"
},
{
"item": "GLM-5.3 output per 1M tokens",
"value": "$4.40",
"numeric": 4.4,
"unit": "USD/1M tokens",
"published": true,
"source": "models",
"quote": "| Z.ai | GLM-5.3 | zai-org/GLM-5.3 | 1048575 | \\$1.40 | \\$0.26 | \\$4.40 |",
"verified": true,
"sourceUrl": "https://docs.together.ai/docs/serverless/models.md"
},
{
"item": "GLM-5.3 context window",
"value": "1,048,575 tokens",
"numeric": 1048575,
"unit": "tokens",
"published": true,
"source": "models",
"quote": "| Z.ai | GLM-5.3 | zai-org/GLM-5.3 | 1048575 |",
"verified": true,
"sourceUrl": "https://docs.together.ai/docs/serverless/models.md"
},
{
"item": "GLM-5.3 Flash input per 1M tokens",
"value": "$0.15",
"numeric": 0.15,
"unit": "USD/1M tokens",
"published": true,
"source": "models",
"quote": "| Z.ai | GLM-5.3 Flash | zai-org/GLM-5.3-Flash | 1048575 | \\$0.15 | \\$0.03 | \\$0.50 |",
"verified": true,
"sourceUrl": "https://docs.together.ai/docs/serverless/models.md"
},
{
"item": "GLM-5.3 Flash cached input per 1M tokens",
"value": "$0.03",
"numeric": 0.03,
"unit": "USD/1M tokens",
"published": true,
"source": "models",
"quote": "| Z.ai | GLM-5.3 Flash | zai-org/GLM-5.3-Flash | 1048575 | \\$0.15 | \\$0.03 | \\$0.50 |",
"verified": true,
"sourceUrl": "https://docs.together.ai/docs/serverless/models.md"
},
{
"item": "GLM-5.3 Flash output per 1M tokens",
"value": "$0.50",
"numeric": 0.5,
"unit": "USD/1M tokens",
"published": true,
"source": "models",
"quote": "| Z.ai | GLM-5.3 Flash | zai-org/GLM-5.3-Flash | 1048575 | \\$0.15 | \\$0.03 | \\$0.50 |",
"verified": true,
"sourceUrl": "https://docs.together.ai/docs/serverless/models.md"
},
{
"item": "GLM-5.3 Flash context window",
"value": "1,048,575 tokens",
"numeric": 1048575,
"unit": "tokens",
"published": true,
"source": "models",
"quote": "| Z.ai | GLM-5.3 Flash | zai-org/GLM-5.3-Flash | 1048575 |",
"verified": true,
"sourceUrl": "https://docs.together.ai/docs/serverless/models.md"
},
{
"item": "DeepSeek V4 Pro 0813 input per 1M tokens",
"value": "$1.32",
"numeric": 1.32,
"unit": "USD/1M tokens",
"published": true,
"source": "models",
"quote": "| DeepSeek | DeepSeek V4 Pro 0813 | deepseek-ai/DeepSeek-V4-Pro-0813 | 1048576 | \\$1.32 | \\$0.13 | \\$3.96 |",
"verified": true,
"sourceUrl": "https://docs.together.ai/docs/serverless/models.md"
},
{
"item": "DeepSeek V4 Pro 0813 cached input per 1M tokens",
"value": "$0.13",
"numeric": 0.13,
"unit": "USD/1M tokens",
"published": true,
"source": "models",
"quote": "| DeepSeek | DeepSeek V4 Pro 0813 | deepseek-ai/DeepSeek-V4-Pro-0813 | 1048576 | \\$1.32 | \\$0.13 | \\$3.96 |",
"verified": true,
"sourceUrl": "https://docs.together.ai/docs/serverless/models.md"
},
{
"item": "DeepSeek V4 Pro 0813 output per 1M tokens",
"value": "$3.96",
"numeric": 3.96,
"unit": "USD/1M tokens",
"published": true,
"source": "models",
"quote": "| DeepSeek | DeepSeek V4 Pro 0813 | deepseek-ai/DeepSeek-V4-Pro-0813 | 1048576 | \\$1.32 | \\$0.13 | \\$3.96 |",
"verified": true,
"sourceUrl": "https://docs.together.ai/docs/serverless/models.md"
},
{
"item": "DeepSeek V4 Pro 0813 context window",
"value": "1,048,576 tokens",
"numeric": 1048576,
"unit": "tokens",
"published": true,
"source": "models",
"quote": "| DeepSeek | DeepSeek V4 Pro 0813 | deepseek-ai/DeepSeek-V4-Pro-0813 | 1048576 |",
"verified": true,
"sourceUrl": "https://docs.together.ai/docs/serverless/models.md"
},
{
"item": "DeepSeek V4.1 Flash input per 1M tokens",
"value": "$0.30",
"numeric": 0.3,
"unit": "USD/1M tokens",
"published": true,
"source": "models",
"quote": "| DeepSeek | DeepSeek V4.1 Flash | deepseek-ai/DeepSeek-V4.1-Flash | 1000000 | \\$0.30 | \\$0.006 | \\$1.20 |",
"verified": true,
"sourceUrl": "https://docs.together.ai/docs/serverless/models.md"
},
{
"item": "DeepSeek V4.1 Flash cached input per 1M tokens",
"value": "$0.006",
"numeric": 0.006,
"unit": "USD/1M tokens",
"published": true,
"source": "models",
"quote": "| DeepSeek | DeepSeek V4.1 Flash | deepseek-ai/DeepSeek-V4.1-Flash | 1000000 | \\$0.30 | \\$0.006 | \\$1.20 |",
"verified": true,
"sourceUrl": "https://docs.together.ai/docs/serverless/models.md"
},
{
"item": "DeepSeek V4.1 Flash output per 1M tokens",
"value": "$1.20",
"numeric": 1.2,
"unit": "USD/1M tokens",
"published": true,
"source": "models",
"quote": "| DeepSeek | DeepSeek V4.1 Flash | deepseek-ai/DeepSeek-V4.1-Flash | 1000000 | \\$0.30 | \\$0.006 | \\$1.20 |",
"verified": true,
"sourceUrl": "https://docs.together.ai/docs/serverless/models.md"
},
{
"item": "DeepSeek V4.1 Flash context window",
"value": "1,000,000 tokens",
"numeric": 1000000,
"unit": "tokens",
"published": true,
"source": "models",
"quote": "| DeepSeek | DeepSeek V4.1 Flash | deepseek-ai/DeepSeek-V4.1-Flash | 1000000 |",
"verified": true,
"sourceUrl": "https://docs.together.ai/docs/serverless/models.md"
},
{
"item": "MiniMax M3.1 Flash input per 1M tokens",
"value": "$0.15",
"numeric": 0.15,
"unit": "USD/1M tokens",
"published": true,
"source": "models",
"quote": "| Minimax | Minimax M3.1 Flash | MiniMaxAI/MiniMax-M3.1-Flash | 1048576 | \\$0.15 | \\$0.015 | \\$0.60 |",
"verified": true,
"sourceUrl": "https://docs.together.ai/docs/serverless/models.md"
},
{
"item": "MiniMax M3.1 Flash cached input per 1M tokens",
"value": "$0.015",
"numeric": 0.015,
"unit": "USD/1M tokens",
"published": true,
"source": "models",
"quote": "| Minimax | Minimax M3.1 Flash | MiniMaxAI/MiniMax-M3.1-Flash | 1048576 | \\$0.15 | \\$0.015 | \\$0.60 |",
"verified": true,
"sourceUrl": "https://docs.together.ai/docs/serverless/models.md"
},
{
"item": "MiniMax M3.1 Flash output per 1M tokens",
"value": "$0.60",
"numeric": 0.6,
"unit": "USD/1M tokens",
"published": true,
"source": "models",
"quote": "| Minimax | Minimax M3.1 Flash | MiniMaxAI/MiniMax-M3.1-Flash | 1048576 | \\$0.15 | \\$0.015 | \\$0.60 |",
"verified": true,
"sourceUrl": "https://docs.together.ai/docs/serverless/models.md"
},
{
"item": "MiniMax M3.1 Flash context window",
"value": "1,048,576 tokens",
"numeric": 1048576,
"unit": "tokens",
"published": true,
"source": "models",
"quote": "| Minimax | Minimax M3.1 Flash | MiniMaxAI/MiniMax-M3.1-Flash | 1048576 |",
"verified": true,
"sourceUrl": "https://docs.together.ai/docs/serverless/models.md"
},
{
"item": "Muse Spark Open 816B A42B input per 1M tokens",
"value": "$1.25",
"numeric": 1.25,
"unit": "USD/1M tokens",
"published": true,
"source": "models",
"quote": "| Meta | Muse Spark Open 816B A42B | meta-models/Muse-Spark-Open-816B-A42B | 1048576 | \\$1.25 | \\$0.15 | \\$4.25 |",
"verified": true,
"sourceUrl": "https://docs.together.ai/docs/serverless/models.md"
},
{
"item": "Muse Spark Open 816B A42B cached input per 1M tokens",
"value": "$0.15",
"numeric": 0.15,
"unit": "USD/1M tokens",
"published": true,
"source": "models",
"quote": "| Meta | Muse Spark Open 816B A42B | meta-models/Muse-Spark-Open-816B-A42B | 1048576 | \\$1.25 | \\$0.15 | \\$4.25 |",
"verified": true,
"sourceUrl": "https://docs.together.ai/docs/serverless/models.md"
},
{
"item": "Muse Spark Open 816B A42B output per 1M tokens",
"value": "$4.25",
"numeric": 4.25,
"unit": "USD/1M tokens",
"published": true,
"source": "models",
"quote": "| Meta | Muse Spark Open 816B A42B | meta-models/Muse-Spark-Open-816B-A42B | 1048576 | \\$1.25 | \\$0.15 | \\$4.25 |",
"verified": true,
"sourceUrl": "https://docs.together.ai/docs/serverless/models.md"
},
{
"item": "GPT-OSS 120B input per 1M tokens",
"value": "$0.15",
"numeric": 0.15,
"unit": "USD/1M tokens",
"published": true,
"source": "models",
"quote": "| OpenAI | GPT-OSS 120B | openai/gpt-oss-120b | 131072 | \\$0.15 | - | \\$0.60 |",
"verified": true,
"sourceUrl": "https://docs.together.ai/docs/serverless/models.md"
},
{
"item": "GPT-OSS 120B output per 1M tokens",
"value": "$0.60",
"numeric": 0.6,
"unit": "USD/1M tokens",
"published": true,
"source": "models",
"quote": "| OpenAI | GPT-OSS 120B | openai/gpt-oss-120b | 131072 | \\$0.15 | - | \\$0.60 |",
"verified": true,
"sourceUrl": "https://docs.together.ai/docs/serverless/models.md"
},
{
"item": "GPT-OSS 120B context window",
"value": "131,072 tokens",
"numeric": 131072,
"unit": "tokens",
"published": true,
"source": "models",
"quote": "| OpenAI | GPT-OSS 120B | openai/gpt-oss-120b | 131072 |",
"verified": true,
"sourceUrl": "https://docs.together.ai/docs/serverless/models.md"
},
{
"item": "Qwen3.5 9B input per 1M tokens",
"value": "$0.17",
"numeric": 0.17,
"unit": "USD/1M tokens",
"published": true,
"source": "models",
"quote": "| Qwen | Qwen3.5 9B | Qwen/Qwen3.5-9B | 262144 | \\$0.17 | - | \\$0.25 |",
"verified": true,
"sourceUrl": "https://docs.together.ai/docs/serverless/models.md"
},
{
"item": "Qwen3.5 9B output per 1M tokens",
"value": "$0.25",
"numeric": 0.25,
"unit": "USD/1M tokens",
"published": true,
"source": "models",
"quote": "| Qwen | Qwen3.5 9B | Qwen/Qwen3.5-9B | 262144 | \\$0.17 | - | \\$0.25 |",
"verified": true,
"sourceUrl": "https://docs.together.ai/docs/serverless/models.md"
},
{
"item": "Qwen3.5 9B context window",
"value": "262,144 tokens",
"numeric": 262144,
"unit": "tokens",
"published": true,
"source": "models",
"quote": "| Qwen | Qwen3.5 9B | Qwen/Qwen3.5-9B | 262144 |",
"verified": true,
"sourceUrl": "https://docs.together.ai/docs/serverless/models.md"
},
{
"item": "Ternary Bonsai 27B input/output",
"value": "Free",
"numeric": 0,
"unit": "USD/1M tokens",
"published": true,
"source": "models",
"quote": "| Prism ML | Ternary Bonsai 27B | Prism-ML/Ternary-Bonsai-27B | 262144 | Free | - | Free |",
"verified": true,
"sourceUrl": "https://docs.together.ai/docs/serverless/models.md"
},
{
"item": "Max output tokens (all models)",
"value": "Not stated",
"unit": "tokens",
"published": false,
"source": "models",
"quote": "| Organization | Model name | API model string | Context length | Input pricing (per 1M tokens) | Cached input pricing (per 1M tokens) | Output pricing (per 1M tokens) |",
"verified": true,
"sourceUrl": "https://docs.together.ai/docs/serverless/models.md"
},
{
"item": "Batch discount",
"value": "Up to 50% off serverless rates; selected models only (listed: openai/whisper-large-v3). Models not listed run at standard rates.",
"numeric": 50,
"unit": "% off",
"published": true,
"source": "batch",
"quote": "Selected serverless models run at 50% off batch rates: | `openai/whisper-large-v3` | Models not listed run at standard rates.",
"verified": true,
"sourceUrl": "https://docs.together.ai/docs/inference/batch/overview.md"
},
{
"item": "Batch: requests per batch",
"value": "Up to 50,000",
"numeric": 50000,
"unit": "requests/batch",
"published": true,
"source": "batch",
"quote": "Up to 50,000 requests per batch.",
"verified": true,
"sourceUrl": "https://docs.together.ai/docs/inference/batch/overview.md"
},
{
"item": "Batch: tokens enqueued per model",
"value": "Up to 30B",
"numeric": 30000000000,
"unit": "tokens",
"published": true,
"source": "batch",
"quote": "Up to 30B tokens enqueued per model at any time.",
"verified": true,
"sourceUrl": "https://docs.together.ai/docs/inference/batch/overview.md"
},
{
"item": "Batch: input file size",
"value": "Up to 100 MB",
"numeric": 100,
"unit": "MB",
"published": true,
"source": "batch",
"quote": "Up to 100 MB per input file.",
"verified": true,
"sourceUrl": "https://docs.together.ai/docs/inference/batch/overview.md"
},
{
"item": "Serverless rate limits (RPM/TPM/RPD) per tier",
"value": "Rate limiting may occasionally occur with high request volumes or large bursts of traffic.",
"unit": "",
"published": false,
"source": "ratelimits",
"quote": "In most cases, you can use Together AI serverless inference without encountering rate limits. Rate limiting may occasionally occur with high request volumes or large bursts of traffic.",
"verified": true,
"sourceUrl": "https://docs.together.ai/docs/rate-limits"
},
{
"item": "Tier unlock (spend/deposit)",
"value": "No usage tiers described; committed throughput available via provisioned throughput (contact sales).",
"unit": "",
"published": false,
"source": "ratelimits",
"quote": "Serverless performance is best-effort. For committed throughput and reliability guarantees, see provisioned throughput.",
"verified": true,
"sourceUrl": "https://docs.together.ai/docs/rate-limits"
},
{
"item": "US-only (geo-specific) inference multiplier",
"value": "1.25x standard serverless rates",
"numeric": 1.25,
"unit": "multiplier",
"published": true,
"source": "serverless",
"quote": "US-only inference costs 1.25× standard serverless rates for input, cached input, and output tokens.",
"verified": true,
"sourceUrl": "https://docs.together.ai/docs/serverless/overview.md"
}
],
"overage": {
"policy": "hard-stop",
"summary": "Fully prepaid. API access stops when the balance reaches zero and resumes after credits are added. Optional auto-recharge (card only) buys credits when the balance falls below a threshold and does not cap spend.",
"source": "credits",
"quote": "Together AI is **fully prepaid**. You need a positive credit balance to use the platform."
},
"gotchas": [
{
"title": "Zero-balance cut-off is not an exact cap",
"detail": "Metering has a short delay, so usage can arrive after the balance reaches zero, and the customer remains responsible for it.",
"source": "spend",
"quote": "Metering has a short delay, so some usage can arrive after the balance reaches zero. You remain responsible for that usage.",
"sourceUrl": "https://docs.together.ai/docs/billing-spend-controls.md"
},
{
"title": "Batch discount applies only to listed models",
"detail": "Batch is advertised at up to 50% off, but only listed models are discounted; others run at standard rates. The discount does not apply to dedicated model inference.",
"source": "batch",
"quote": "Models not listed run at standard rates.",
"sourceUrl": "https://docs.together.ai/docs/inference/batch/overview.md"
},
{
"title": "Cached input is best-effort",
"detail": "Caching is automatic and prefix-based on supported models; cache hits are not guaranteed and there is no configurable retention window.",
"source": "serverless",
"quote": "cache hits aren't guaranteed and there's no configurable retention window.",
"sourceUrl": "https://docs.together.ai/docs/serverless/overview.md"
},
{
"title": "US-only inference costs 25% more",
"detail": "Requests sent to us-api.together.ai cost 25% more than standard rates.",
"source": "models",
"quote": "These requests cost 25% more than the standard rates in the chat models table.",
"sourceUrl": "https://docs.together.ai/docs/serverless/models.md"
},
{
"title": "Per-image prices are estimates",
"detail": "Image models billed by image pass through the provider's per-request charge, which varies with resolution, quality and other parameters.",
"source": "models",
"quote": "Prices for models billed by `image` are estimates, not rates.",
"sourceUrl": "https://docs.together.ai/docs/serverless/models.md"
},
{
"title": "Model-specific limits",
"detail": "When a model is in especially high demand, Together may apply custom rate limits or access restrictions to that model.",
"source": "ratelimits",
"quote": "When a model is in especially high demand, Together may apply custom rate limits or access restrictions to that model.",
"sourceUrl": "https://docs.together.ai/docs/rate-limits"
},
{
"title": "Free credits do not grant access",
"detail": "Platform access requires the minimum $15 credit purchase even if the balance contains free credits.",
"source": "credits",
"quote": "Platform access requires the minimum \\$15 credit purchase described above.",
"sourceUrl": "https://docs.together.ai/docs/billing-credits.md"
},
{
"title": "Batch files retained 7 days",
"detail": "Batch input, output and error files are retained for 7 days, then are no longer accessible.",
"source": "batch",
"quote": "Together retains the file you upload for a batch job, along with the output and error files the job produces, for 7 days.",
"sourceUrl": "https://docs.together.ai/docs/inference/batch/overview.md"
}
]
},
{
"id": "fireworks-ai",
"name": "Fireworks AI",
"vendor": "Fireworks AI",
"category": "llm-api",
"url": "https://fireworks.ai",
"checked": "2026-10-30",
"sources": {
"serverless_pricing": {
"name": "Serverless Pricing",
"url": "https://docs.fireworks.ai/serverless/pricing.md"
},
"account_quotas": {
"name": "Account quotas",
"url": "https://docs.fireworks.ai/guides/quotas_usage/rate-limits"
},
"serverless_rate_limits": {
"name": "Serverless Rate Limits",
"url": "https://docs.fireworks.ai/serverless/rate-limits.md"
},
"docs_index": {
"name": "Fireworks Documentation Index (llms.txt)",
"url": "https://docs.fireworks.ai/llms.txt"
},
"pricing_page": {
"name": "Pricing (fireworks.ai/pricing)",
"url": "https://fireworks.ai/pricing"
}
},
"unit": {
"tag": "Per 1M tokens",
"definition": "Serverless inference is priced per token; prices are per 1 million tokens in US dollars, billed across input tokens, cached input tokens and output tokens.",
"source": "serverless_pricing",
"quote": "Prices below are **per 1 million tokens** in US dollars."
},
"free": {
"summary": "$1 starter credit",
"published": true,
"source": "docs_index",
"quote": "What happens when your $1 starter credit is depleted on Fireworks, how to add a payment method, enable auto top-up, and lift account spend tier limits."
},
"plans": [
{
"id": "serverless-standard",
"name": "Serverless — Standard",
"priceUsd": null,
"priceNote": "Pay per token; see rates",
"billing": "usage",
"included": "Per-token pricing for input, cached input and output tokens.",
"source": "serverless_pricing",
"quote": "Serverless inference is priced per token.",
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"id": "serverless-priority",
"name": "Serverless — Priority",
"priceUsd": null,
"priceNote": "Higher per-token rates listed in the Priority column",
"billing": "usage",
"included": "Priority tier is prioritized during high load to decrease the chance of being load shed.",
"source": "serverless_rate_limits",
"quote": "To **decrease the chance** of being load shed, you can use [Priority tier](https://docs.fireworks.ai/serverless/serverless-modes.md), which is prioritized during high load.",
"sourceUrl": "https://docs.fireworks.ai/serverless/rate-limits.md"
},
{
"id": "batch",
"name": "Batch inference",
"priceUsd": null,
"priceNote": "50% of serverless pricing",
"billing": "usage",
"included": "Billed at 50% of serverless pricing on both input and output.",
"source": "serverless_pricing",
"quote": "**Batch inference** is billed at **50% of serverless pricing** on both input and output.",
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"id": "enterprise",
"name": "Unlimited / Enterprise",
"priceUsd": null,
"priceNote": "Contact sales",
"billing": "usage",
"included": "Enterprise accounts get higher upper bounds on adaptive rate limits automatically.",
"source": "serverless_rate_limits",
"quote": "A higher account [Spending Tier](https://docs.fireworks.ai/guides/quotas_usage/account-quotas.md#spending-tiers) correlates with higher upper bound rate limits; **enterprise accounts** get higher upper bounds automatically.",
"sourceUrl": "https://docs.fireworks.ai/serverless/rate-limits.md"
}
],
"rates": [
{
"item": "Ember-1 — Standard input per 1M tokens",
"value": "$3.00",
"numeric": 3,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "Ember-1 | $3.00 / $0.30 / $15.00 | $3.75 / $0.375 / $18.75",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "Ember-1 — Standard cached input per 1M tokens",
"value": "$0.30",
"numeric": 0.3,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "Ember-1 | $3.00 / $0.30 / $15.00 | $3.75 / $0.375 / $18.75",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "Ember-1 — Standard output per 1M tokens",
"value": "$15.00",
"numeric": 15,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "Ember-1 | $3.00 / $0.30 / $15.00 | $3.75 / $0.375 / $18.75",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "Muse Spark Open — Standard input per 1M tokens",
"value": "$1.25",
"numeric": 1.25,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "Muse Spark Open | $1.25 / $0.15 / $4.25 | $1.875 / $0.225 / $6.375",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "Muse Spark Open — Standard cached input per 1M tokens",
"value": "$0.15",
"numeric": 0.15,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "Muse Spark Open | $1.25 / $0.15 / $4.25 | $1.875 / $0.225 / $6.375",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "Muse Spark Open — Standard output per 1M tokens",
"value": "$4.25",
"numeric": 4.25,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "Muse Spark Open | $1.25 / $0.15 / $4.25 | $1.875 / $0.225 / $6.375",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "Kimi K3 — Standard input per 1M tokens",
"value": "$3.00",
"numeric": 3,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "Kimi K3 | $3.00 / $0.30 / $15.00 | $3.75 / $0.375 / $18.75",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "Kimi K3 — Standard cached input per 1M tokens",
"value": "$0.30",
"numeric": 0.3,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "Kimi K3 | $3.00 / $0.30 / $15.00 | $3.75 / $0.375 / $18.75",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "Kimi K3 — Standard output per 1M tokens",
"value": "$15.00",
"numeric": 15,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "Kimi K3 | $3.00 / $0.30 / $15.00 | $3.75 / $0.375 / $18.75",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "Kimi K3 Fast — Standard input per 1M tokens",
"value": "$4.50",
"numeric": 4.5,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "Kimi K3 Fast | $4.50 / $0.45 / $22.50 | —",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "Kimi K3 Fast — Standard cached input per 1M tokens",
"value": "$0.45",
"numeric": 0.45,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "Kimi K3 Fast | $4.50 / $0.45 / $22.50 | —",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "Kimi K3 Fast — Standard output per 1M tokens",
"value": "$22.50",
"numeric": 22.5,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "Kimi K3 Fast | $4.50 / $0.45 / $22.50 | —",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "Kimi K3 (US) — Standard input per 1M tokens",
"value": "$4.50",
"numeric": 4.5,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "Kimi K3 (US) | $4.50 / $0.45 / $22.50 | $5.625 / $0.5625 / $28.125",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "Kimi K3 (US) — Standard cached input per 1M tokens",
"value": "$0.45",
"numeric": 0.45,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "Kimi K3 (US) | $4.50 / $0.45 / $22.50 | $5.625 / $0.5625 / $28.125",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "Kimi K3 (US) — Standard output per 1M tokens",
"value": "$22.50",
"numeric": 22.5,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "Kimi K3 (US) | $4.50 / $0.45 / $22.50 | $5.625 / $0.5625 / $28.125",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "DeepSeek V4.1 Flash — Standard input per 1M tokens",
"value": "$0.30",
"numeric": 0.3,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "DeepSeek V4.1 Flash | $0.30 / $0.006 / $1.20 | $0.375 / $0.0075 / $1.50",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "DeepSeek V4.1 Flash — Standard cached input per 1M tokens",
"value": "$0.006",
"numeric": 0.006,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "DeepSeek V4.1 Flash | $0.30 / $0.006 / $1.20 | $0.375 / $0.0075 / $1.50",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "DeepSeek V4.1 Flash — Standard output per 1M tokens",
"value": "$1.20",
"numeric": 1.2,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "DeepSeek V4.1 Flash | $0.30 / $0.006 / $1.20 | $0.375 / $0.0075 / $1.50",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "DeepSeek V4.1 Flash (US) — Standard input per 1M tokens",
"value": "$0.45",
"numeric": 0.45,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "DeepSeek V4.1 Flash (US) | $0.45 / $0.009 / $1.80 | $0.5625 / $0.01125 / $2.25",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "DeepSeek V4.1 Flash (US) — Standard cached input per 1M tokens",
"value": "$0.009",
"numeric": 0.009,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "DeepSeek V4.1 Flash (US) | $0.45 / $0.009 / $1.80 | $0.5625 / $0.01125 / $2.25",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "DeepSeek V4.1 Flash (US) — Standard output per 1M tokens",
"value": "$1.80",
"numeric": 1.8,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "DeepSeek V4.1 Flash (US) | $0.45 / $0.009 / $1.80 | $0.5625 / $0.01125 / $2.25",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "DeepSeek V4.1 Flash 1017 — Standard input per 1M tokens",
"value": "$0.30",
"numeric": 0.3,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "DeepSeek V4.1 Flash 1017 | $0.30 / $0.006 / $1.20 | $0.375 / $0.0075 / $1.50",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "DeepSeek V4.1 Flash 1017 — Standard cached input per 1M tokens",
"value": "$0.006",
"numeric": 0.006,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "DeepSeek V4.1 Flash 1017 | $0.30 / $0.006 / $1.20 | $0.375 / $0.0075 / $1.50",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "DeepSeek V4.1 Flash 1017 — Standard output per 1M tokens",
"value": "$1.20",
"numeric": 1.2,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "DeepSeek V4.1 Flash 1017 | $0.30 / $0.006 / $1.20 | $0.375 / $0.0075 / $1.50",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "DeepSeek V4.1 Flash 1017 (US) — Standard input per 1M tokens",
"value": "$0.45",
"numeric": 0.45,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "DeepSeek V4.1 Flash 1017 (US) | $0.45 / $0.009 / $1.80 | $0.5625 / $0.01125 / $2.25",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "DeepSeek V4.1 Flash 1017 (US) — Standard cached input per 1M tokens",
"value": "$0.009",
"numeric": 0.009,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "DeepSeek V4.1 Flash 1017 (US) | $0.45 / $0.009 / $1.80 | $0.5625 / $0.01125 / $2.25",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "DeepSeek V4.1 Flash 1017 (US) — Standard output per 1M tokens",
"value": "$1.80",
"numeric": 1.8,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "DeepSeek V4.1 Flash 1017 (US) | $0.45 / $0.009 / $1.80 | $0.5625 / $0.01125 / $2.25",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "GLM 5.3 Flash — Standard input per 1M tokens",
"value": "$0.15",
"numeric": 0.15,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "GLM 5.3 Flash | $0.15 / $0.03 / $0.50 | $0.1875 / $0.0375 / $0.625",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "GLM 5.3 Flash — Standard cached input per 1M tokens",
"value": "$0.03",
"numeric": 0.03,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "GLM 5.3 Flash | $0.15 / $0.03 / $0.50 | $0.1875 / $0.0375 / $0.625",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "GLM 5.3 Flash — Standard output per 1M tokens",
"value": "$0.50",
"numeric": 0.5,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "GLM 5.3 Flash | $0.15 / $0.03 / $0.50 | $0.1875 / $0.0375 / $0.625",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "GLM 5.3 Flash (US) — Standard input per 1M tokens",
"value": "$0.225",
"numeric": 0.225,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "GLM 5.3 Flash (US) | $0.225 / $0.045 / $0.75 | $0.28125 / $0.05625 / $0.9375",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "GLM 5.3 Flash (US) — Standard cached input per 1M tokens",
"value": "$0.045",
"numeric": 0.045,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "GLM 5.3 Flash (US) | $0.225 / $0.045 / $0.75 | $0.28125 / $0.05625 / $0.9375",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "GLM 5.3 Flash (US) — Standard output per 1M tokens",
"value": "$0.75",
"numeric": 0.75,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "GLM 5.3 Flash (US) | $0.225 / $0.045 / $0.75 | $0.28125 / $0.05625 / $0.9375",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "Ultramarine 1 Flash (US) — Standard input per 1M tokens",
"value": "$0.225",
"numeric": 0.225,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "Ultramarine 1 Flash (US) | $0.225 / $0.045 / $0.75 | $0.28125 / $0.05625 / $0.9375",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "Ultramarine 1 Flash (US) — Standard cached input per 1M tokens",
"value": "$0.045",
"numeric": 0.045,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "Ultramarine 1 Flash (US) | $0.225 / $0.045 / $0.75 | $0.28125 / $0.05625 / $0.9375",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "Ultramarine 1 Flash (US) — Standard output per 1M tokens",
"value": "$0.75",
"numeric": 0.75,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "Ultramarine 1 Flash (US) | $0.225 / $0.045 / $0.75 | $0.28125 / $0.05625 / $0.9375",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "GLM 5.3 — Standard input per 1M tokens",
"value": "$1.40",
"numeric": 1.4,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "GLM 5.3 | $1.40 / $0.26 / $4.40 | $1.75 / $0.325 / $5.50",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "GLM 5.3 — Standard cached input per 1M tokens",
"value": "$0.26",
"numeric": 0.26,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "GLM 5.3 | $1.40 / $0.26 / $4.40 | $1.75 / $0.325 / $5.50",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "GLM 5.3 — Standard output per 1M tokens",
"value": "$4.40",
"numeric": 4.4,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "GLM 5.3 | $1.40 / $0.26 / $4.40 | $1.75 / $0.325 / $5.50",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "GLM 5.3 (US) — Standard input per 1M tokens",
"value": "$2.10",
"numeric": 2.1,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "GLM 5.3 (US) | $2.10 / $0.39 / $6.60 | $2.625 / $0.4875 / $8.25",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "GLM 5.3 (US) — Standard cached input per 1M tokens",
"value": "$0.39",
"numeric": 0.39,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "GLM 5.3 (US) | $2.10 / $0.39 / $6.60 | $2.625 / $0.4875 / $8.25",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "GLM 5.3 (US) — Standard output per 1M tokens",
"value": "$6.60",
"numeric": 6.6,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "GLM 5.3 (US) | $2.10 / $0.39 / $6.60 | $2.625 / $0.4875 / $8.25",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "GLM 5.3 Fast — Standard input per 1M tokens",
"value": "$2.10",
"numeric": 2.1,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "GLM 5.3 Fast | $2.10 / $0.39 / $6.60 | —",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "GLM 5.3 Fast — Standard cached input per 1M tokens",
"value": "$0.39",
"numeric": 0.39,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "GLM 5.3 Fast | $2.10 / $0.39 / $6.60 | —",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "GLM 5.3 Fast — Standard output per 1M tokens",
"value": "$6.60",
"numeric": 6.6,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "GLM 5.3 Fast | $2.10 / $0.39 / $6.60 | —",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "Qwen 3.8 Max — Standard input per 1M tokens",
"value": "$2.00",
"numeric": 2,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "Qwen 3.8 Max | $2.00 / $0.25 / $6.00 | $3.00 / $0.375 / $9.00",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "Qwen 3.8 Max — Standard cached input per 1M tokens",
"value": "$0.25",
"numeric": 0.25,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "Qwen 3.8 Max | $2.00 / $0.25 / $6.00 | $3.00 / $0.375 / $9.00",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "Qwen 3.8 Max — Standard output per 1M tokens",
"value": "$6.00",
"numeric": 6,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "Qwen 3.8 Max | $2.00 / $0.25 / $6.00 | $3.00 / $0.375 / $9.00",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "MiniMax M3 — Standard input per 1M tokens",
"value": "$0.30",
"numeric": 0.3,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "MiniMax M3 | $0.30 / $0.06 / $1.20 | $0.45 / $0.09 / $1.80",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "MiniMax M3 — Standard cached input per 1M tokens",
"value": "$0.06",
"numeric": 0.06,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "MiniMax M3 | $0.30 / $0.06 / $1.20 | $0.45 / $0.09 / $1.80",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "MiniMax M3 — Standard output per 1M tokens",
"value": "$1.20",
"numeric": 1.2,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "MiniMax M3 | $0.30 / $0.06 / $1.20 | $0.45 / $0.09 / $1.80",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "OpenAI GPT OSS 120B — Standard input per 1M tokens",
"value": "$0.15",
"numeric": 0.15,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "OpenAI GPT OSS 120B | $0.15 / $0.015 / $0.60 | $0.18 / $0.018 / $0.72",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "OpenAI GPT OSS 120B — Standard cached input per 1M tokens",
"value": "$0.015",
"numeric": 0.015,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "OpenAI GPT OSS 120B | $0.15 / $0.015 / $0.60 | $0.18 / $0.018 / $0.72",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "OpenAI GPT OSS 120B — Standard output per 1M tokens",
"value": "$0.60",
"numeric": 0.6,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "OpenAI GPT OSS 120B | $0.15 / $0.015 / $0.60 | $0.18 / $0.018 / $0.72",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "NVIDIA Nemotron 3.5 Lightning 30B A3B — Standard input per 1M tokens",
"value": "$0.05",
"numeric": 0.05,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "NVIDIA Nemotron 3.5 Lightning 30B A3B | $0.05 / $0.01 / $0.20 | $0.0625 / $0.0125 / $0.25",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "NVIDIA Nemotron 3.5 Lightning 30B A3B — Standard cached input per 1M tokens",
"value": "$0.01",
"numeric": 0.01,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "NVIDIA Nemotron 3.5 Lightning 30B A3B | $0.05 / $0.01 / $0.20 | $0.0625 / $0.0125 / $0.25",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "NVIDIA Nemotron 3.5 Lightning 30B A3B — Standard output per 1M tokens",
"value": "$0.20",
"numeric": 0.2,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "NVIDIA Nemotron 3.5 Lightning 30B A3B | $0.05 / $0.01 / $0.20 | $0.0625 / $0.0125 / $0.25",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "NVIDIA Nemotron 3 Ultra (Preview) — Standard input per 1M tokens",
"value": "$0.60",
"numeric": 0.6,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "NVIDIA Nemotron 3 Ultra (Preview) | $0.60 / $0.12 / $2.40 | $0.75 / $0.15 / $3.00",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "NVIDIA Nemotron 3 Ultra (Preview) — Standard cached input per 1M tokens",
"value": "$0.12",
"numeric": 0.12,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "NVIDIA Nemotron 3 Ultra (Preview) | $0.60 / $0.12 / $2.40 | $0.75 / $0.15 / $3.00",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "NVIDIA Nemotron 3 Ultra (Preview) — Standard output per 1M tokens",
"value": "$2.40",
"numeric": 2.4,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "NVIDIA Nemotron 3 Ultra (Preview) | $0.60 / $0.12 / $2.40 | $0.75 / $0.15 / $3.00",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "Rune 26B-A4B — Standard input per 1M tokens",
"value": "$0.042",
"numeric": 0.042,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "Rune 26B-A4B | $0.042 / $0.0084 / $0.00 | —",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "Rune 26B-A4B — Standard cached input per 1M tokens",
"value": "$0.0084",
"numeric": 0.0084,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "Rune 26B-A4B | $0.042 / $0.0084 / $0.00 | —",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "Rune 26B-A4B — Standard output per 1M tokens",
"value": "$0.00",
"numeric": 0,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "Rune 26B-A4B | $0.042 / $0.0084 / $0.00 | —",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "Batch inference discount",
"value": "50% of serverless pricing on both input and output",
"numeric": 50,
"unit": "% of serverless price",
"published": true,
"source": "serverless_pricing",
"quote": "**Batch inference** is billed at **50% of serverless pricing** on both input and output.",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "Other base models <4B parameters (input and output)",
"value": "$0.10",
"numeric": 0.1,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "Less than 4B parameters | $0.10",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "Other base models 4B–16B parameters (input and output)",
"value": "$0.20",
"numeric": 0.2,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "4B – 16B parameters | $0.20",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "Other base models >16B parameters (input and output)",
"value": "$0.90",
"numeric": 0.9,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "More than 16B parameters | $0.90",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "Other MoE models up to 56B parameters (input and output)",
"value": "$0.50",
"numeric": 0.5,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "MoE up to 56B parameters (e.g. Mixtral 8x7B) | $0.50",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "Other MoE models 56.1B–176B parameters (input and output)",
"value": "$1.20",
"numeric": 1.2,
"unit": "USD/1M tokens",
"published": true,
"source": "serverless_pricing",
"quote": "MoE 56.1B – 176B parameters (e.g. DBRX, Mixtral 8x22B) | $1.20",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "Embeddings up to 150M parameters",
"value": "$0.008",
"numeric": 0.008,
"unit": "USD/1M input tokens",
"published": true,
"source": "serverless_pricing",
"quote": "up to 150M | $0.008",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "Embeddings 150M–350M parameters",
"value": "$0.016",
"numeric": 0.016,
"unit": "USD/1M input tokens",
"published": true,
"source": "serverless_pricing",
"quote": "150M – 350M | $0.016",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "Embeddings Qwen3 8B",
"value": "$0.10",
"numeric": 0.1,
"unit": "USD/1M input tokens",
"published": true,
"source": "serverless_pricing",
"quote": "Qwen3 8B | $0.10",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"item": "Spending Tier 1 — criteria",
"value": "Valid payment method and billing profile",
"unit": "criteria",
"published": true,
"source": "account_quotas",
"quote": "Tier 1 | Valid payment method and billing profile | $50",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/guides/quotas_usage/rate-limits"
},
{
"item": "Spending Tier 2 — criteria",
"value": "Spend or add $50 in credits",
"numeric": 50,
"unit": "USD spent or added",
"published": true,
"source": "account_quotas",
"quote": "Tier 2 | Spend or add $50 in credits | $500",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/guides/quotas_usage/rate-limits"
},
{
"item": "Spending Tier 3 — criteria",
"value": "Spend or add $500 in credits",
"numeric": 500,
"unit": "USD spent or added",
"published": true,
"source": "account_quotas",
"quote": "Tier 3 | Spend or add $500 in credits | $5,000",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/guides/quotas_usage/rate-limits"
},
{
"item": "Spending Tier 4 — criteria",
"value": "Spend or add $5,000 in credits",
"numeric": 5000,
"unit": "USD spent or added",
"published": true,
"source": "account_quotas",
"quote": "Tier 4 | Spend or add $5,000 in credits | $50,000",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/guides/quotas_usage/rate-limits"
},
{
"item": "Unlimited tier — criteria",
"value": "Contact us",
"unit": "criteria",
"published": true,
"source": "account_quotas",
"quote": "Unlimited | Contact us | Unlimited",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/guides/quotas_usage/rate-limits"
},
{
"item": "Legacy postpaid max monthly spend limit — Tier 1",
"value": "$50",
"numeric": 50,
"unit": "USD/month",
"published": true,
"source": "account_quotas",
"quote": "Tier 1 | Valid payment method and billing profile | $50",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/guides/quotas_usage/rate-limits"
},
{
"item": "Legacy postpaid max monthly spend limit — Tier 2",
"value": "$500",
"numeric": 500,
"unit": "USD/month",
"published": true,
"source": "account_quotas",
"quote": "Tier 2 | Spend or add $50 in credits | $500",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/guides/quotas_usage/rate-limits"
},
{
"item": "Legacy postpaid max monthly spend limit — Tier 3",
"value": "$5,000",
"numeric": 5000,
"unit": "USD/month",
"published": true,
"source": "account_quotas",
"quote": "Tier 3 | Spend or add $500 in credits | $5,000",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/guides/quotas_usage/rate-limits"
},
{
"item": "Legacy postpaid max monthly spend limit — Tier 4",
"value": "$50,000",
"numeric": 50000,
"unit": "USD/month",
"published": true,
"source": "account_quotas",
"quote": "Tier 4 | Spend or add $5,000 in credits | $50,000",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/guides/quotas_usage/rate-limits"
},
{
"item": "Account-wide request limit — no payment method or no credits",
"value": "10 RPM",
"numeric": 10,
"unit": "requests/min",
"published": true,
"source": "account_quotas",
"quote": "No payment method or no credits | 10 RPM",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/guides/quotas_usage/rate-limits"
},
{
"item": "Account-wide request limit — payment method and active credits",
"value": "6,000 RPM (maximum)",
"numeric": 6000,
"unit": "requests/min",
"published": true,
"source": "account_quotas",
"quote": "Payment method and active credits | 6,000 RPM (maximum)",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/guides/quotas_usage/rate-limits"
},
{
"item": "Serverless Small models (<800B params) — Total Prompt TPM base ceiling",
"value": "216M",
"numeric": 216000000,
"unit": "tokens/min",
"published": true,
"source": "serverless_rate_limits",
"quote": "Small | < 800B | 216M | 54M | 2.16M",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/rate-limits.md"
},
{
"item": "Serverless Small models (<800B params) — Uncached Prompt TPM base ceiling",
"value": "54M",
"numeric": 54000000,
"unit": "tokens/min",
"published": true,
"source": "serverless_rate_limits",
"quote": "Small | < 800B | 216M | 54M | 2.16M",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/rate-limits.md"
},
{
"item": "Serverless Small models (<800B params) — Generated TPM base ceiling",
"value": "2.16M",
"numeric": 2160000,
"unit": "tokens/min",
"published": true,
"source": "serverless_rate_limits",
"quote": "Small | < 800B | 216M | 54M | 2.16M",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/rate-limits.md"
},
{
"item": "Serverless Medium models (800B–<1.6T params) — Total Prompt TPM base ceiling",
"value": "43.2M",
"numeric": 43200000,
"unit": "tokens/min",
"published": true,
"source": "serverless_rate_limits",
"quote": "Medium | 800B – < 1.6T | 43.2M | 10.8M | 432k",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/rate-limits.md"
},
{
"item": "Serverless Medium models (800B–<1.6T params) — Uncached Prompt TPM base ceiling",
"value": "10.8M",
"numeric": 10800000,
"unit": "tokens/min",
"published": true,
"source": "serverless_rate_limits",
"quote": "Medium | 800B – < 1.6T | 43.2M | 10.8M | 432k",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/rate-limits.md"
},
{
"item": "Serverless Medium models (800B–<1.6T params) — Generated TPM base ceiling",
"value": "432k",
"numeric": 432000,
"unit": "tokens/min",
"published": true,
"source": "serverless_rate_limits",
"quote": "Medium | 800B – < 1.6T | 43.2M | 10.8M | 432k",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/rate-limits.md"
},
{
"item": "Serverless Large models (≥1.6T params) — Total Prompt TPM base ceiling",
"value": "21.6M",
"numeric": 21600000,
"unit": "tokens/min",
"published": true,
"source": "serverless_rate_limits",
"quote": "Large | ≥ 1.6T | 21.6M | 5.4M | 216k",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/rate-limits.md"
},
{
"item": "Serverless Large models (≥1.6T params) — Uncached Prompt TPM base ceiling",
"value": "5.4M",
"numeric": 5400000,
"unit": "tokens/min",
"published": true,
"source": "serverless_rate_limits",
"quote": "Large | ≥ 1.6T | 21.6M | 5.4M | 216k",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/rate-limits.md"
},
{
"item": "Serverless Large models (≥1.6T params) — Generated TPM base ceiling",
"value": "216k",
"numeric": 216000,
"unit": "tokens/min",
"published": true,
"source": "serverless_rate_limits",
"quote": "Large | ≥ 1.6T | 21.6M | 5.4M | 216k",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/rate-limits.md"
},
{
"item": "TPM ceilings for Tier 1 and Tier 2",
"value": "Tiers below Tier 3 have lower ceilings (figures not stated)",
"unit": "tokens/min",
"published": false,
"source": "serverless_rate_limits",
"quote": "The table shows the maximum ceilings, available at Tier 3 and above. Tiers below Tier 3 have lower ceilings.",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/rate-limits.md"
},
{
"item": "Requests per day",
"value": "Not stated; limits are enforced in tokens per minute per model",
"unit": "requests/day",
"published": false,
"source": "serverless_rate_limits",
"quote": "All limits are measured and enforced in **tokens per minute (TPM)**, per model.",
"verified": true,
"sourceUrl": "https://docs.fireworks.ai/serverless/rate-limits.md"
}
],
"overage": {
"policy": "hard-stop",
"summary": "Fireworks uses prepaid credits. When usage reaches 100% of the monthly spend limit, all API requests pause automatically; raise the limit to resume, and add credits if the balance is also depleted. Auto Reload can buy credits when the balance is low. Enterprise spend alerts do not pause service.",
"source": "account_quotas",
"quote": "When usage reaches 100% of the limit, all API requests pause automatically across serverless inference, deployments, and training."
},
"gotchas": [
{
"title": "Prepaid credits billing",
"detail": "Fireworks operates on a pre-paid credits billing system; contracted customers may be able to move to post-paid billing.",
"source": "account_quotas",
"quote": "Fireworks operates on a pre-paid credits billing system.",
"sourceUrl": "https://docs.fireworks.ai/guides/quotas_usage/rate-limits"
},
{
"title": "Auto Reload does not raise the spend limit",
"detail": "Auto Reload purchases credits when the balance is low; it does not change how much usage the account can accrue in the month. Adding credits does not raise or reset the monthly spend limit.",
"source": "account_quotas",
"quote": "Auto Reload purchases credits when your balance is low; it does not change how much usage your account can accrue during the month.",
"sourceUrl": "https://docs.fireworks.ai/guides/quotas_usage/rate-limits"
},
{
"title": "US-only variants cost more",
"detail": "(US) rows are priced higher than the standard rows; Muse Spark Open runs on US-only capacity with the 50% US-only premium waived.",
"source": "serverless_pricing",
"quote": "Muse Spark Open runs on US-only capacity. The 50% US-only premium is waived, so the rates in that row are what you pay.",
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"title": "Priority mode costs more and is not available on every model",
"detail": "Priority rates are listed per model; a dash means Priority is not available for that model.",
"source": "serverless_pricing",
"quote": "**—** in the Priority column means Priority is not available for that model.",
"sourceUrl": "https://docs.fireworks.ai/serverless/pricing.md"
},
{
"title": "Rate limits are per model and adaptive",
"detail": "Limits are per account and per model, in tokens per minute, and start at a default that grows 25% at most every 15 minutes when usage is above 50% of the limit; they reset after more than 72 hours without traffic.",
"source": "serverless_rate_limits",
"quote": "If your recent one-minute usage is above 50% of your current limit, the limit increases by 25%, and no more than once every 15 minutes, until it reaches your base ceiling.",
"sourceUrl": "https://docs.fireworks.ai/serverless/rate-limits.md"
},
{
"title": "Fast variants have separate limits",
"detail": "Fast and regular model variants have separate limits; Priority and regular requests share the same limits.",
"source": "serverless_rate_limits",
"quote": "**Fast** and **regular** model variants have **separate** limits.",
"sourceUrl": "https://docs.fireworks.ai/serverless/rate-limits.md"
}
]
},
{
"id": "openrouter",
"name": "OpenRouter",
"vendor": "OpenRouter, Inc",
"category": "llm-api",
"url": "https://openrouter.ai/",
"checked": "2026-10-30",
"sources": {
"limits": {
"name": "Limits — OpenRouter Docs",
"url": "https://openrouter.ai/docs/api-reference/limits"
},
"faq": {
"name": "Frequently Asked Questions — OpenRouter Docs",
"url": "https://openrouter.ai/docs/faq"
},
"pricing": {
"name": "Pricing | OpenRouter",
"url": "https://openrouter.ai/pricing"
},
"models_api": {
"name": "OpenRouter Models API (GET /api/v1/models)",
"url": "https://openrouter.ai/api/v1/models"
},
"batch": {
"name": "Batch API Quickstart — OpenRouter Docs",
"url": "https://openrouter.ai/docs/batch-quickstart.md"
},
"prompt_caching": {
"name": "Prompt Caching — OpenRouter Docs",
"url": "https://openrouter.ai/docs/features/prompt-caching"
},
"free_variant": {
"name": "Free Variant — OpenRouter Docs",
"url": "https://openrouter.ai/docs/guides/routing/model-variants/free.md"
}
},
"unit": {
"tag": "Per million tokens (prepaid USD credits)",
"definition": "Each model and provider has its own price per million tokens, usually different for prompt (input) and completion (output) tokens; the request cost is deducted from prepaid USD credits.",
"source": "faq",
"quote": "For each model we have the pricing displayed per million tokens. There is usually a different price for prompt and completion tokens."
},
"free": {
"summary": "Free plan: 25+ free models (:free variants) from 4 free providers, 50 requests/day (20 requests/minute); 1,000 requests/day once at least 10 credits have been purchased. New users receive a small free allowance (amount not stated).",
"published": true,
"source": "faq",
"quote": "All new users receive a small free allowance to test out OpenRouter."
},
"plans": [
{
"id": "free",
"name": "Free",
"priceUsd": 0,
"priceNote": "Platform fees: N/A",
"billing": "usage",
"included": "25+ free models, 4 free providers, chat and API access, activity logs & export, 5 workspaces, 50 requests/day, community support. No prompt caching, budgets or auto-routing.",
"source": "pricing",
"quote": "| Rate limits | Free 50 requests/day |",
"sourceUrl": "https://openrouter.ai/pricing"
},
{
"id": "standard",
"name": "Standard",
"priceUsd": null,
"priceNote": "Pay-as-you-go; 5.5% platform fee; model prices passed through from providers",
"billing": "usage",
"included": "500+ models, 80+ providers, prompt caching, budgets & spend controls, auto-routing, management API key, admin controls, data-policy-based routing, 5 workspaces, BYOK $25,000/month list-price inference with no fees then 5%, rate limits passthrough from the provider(s), email support. Payment by credit card, crypto & more.",
"source": "pricing",
"quote": "Standard 5.5%",
"sourceUrl": "https://openrouter.ai/pricing"
},
{
"id": "business",
"name": "Business",
"priceUsd": null,
"priceNote": "Pay-as-you-go; 8% platform fee; model prices passed through from providers",
"billing": "usage",
"included": "Everything in Standard plus advanced notifications, EU and US in-region routing, workload identity federation, 1,000 workspaces, signed DPA on request, email support.",
"source": "pricing",
"quote": "Business 8%",
"sourceUrl": "https://openrouter.ai/pricing"
},
{
"id": "enterprise",
"name": "Enterprise",
"priceUsd": null,
"priceNote": "Contact sales; fee discounts available",
"billing": "usage",
"included": "500+ models, 80+ providers, private endpoints add-on, custom workspaces, managed policy enforcement, SSO/SAML, contractual SLAs, invoicing options, custom BYOK limits, higher rate-limit allowances, dedicated support team.",
"source": "pricing",
"quote": "Enterprise [Fee discounts available]",
"sourceUrl": "https://openrouter.ai/pricing"
}
],
"rates": [
{
"item": "Platform fee — Standard (pay-as-you-go)",
"value": "5.5%",
"numeric": 5.5,
"unit": "percent",
"published": true,
"source": "pricing",
"quote": "Standard 5.5%",
"verified": true,
"sourceUrl": "https://openrouter.ai/pricing"
},
{
"item": "Platform fee — Business (pay-as-you-go)",
"value": "8%",
"numeric": 8,
"unit": "percent",
"published": true,
"source": "pricing",
"quote": "Business 8%",
"verified": true,
"sourceUrl": "https://openrouter.ai/pricing"
},
{
"item": "Platform fee — Enterprise",
"value": "Fee discounts available",
"unit": "percent",
"published": false,
"source": "pricing",
"quote": "Enterprise [Fee discounts available]",
"verified": true,
"sourceUrl": "https://openrouter.ai/pricing"
},
{
"item": "Inference markup over provider pricing",
"value": "No markup; provider pricing passed through",
"numeric": 0,
"unit": "percent",
"published": true,
"source": "faq",
"quote": "We pass through the pricing of the underlying providers; there is no markup on inference pricing",
"verified": true,
"sourceUrl": "https://openrouter.ai/docs/faq"
},
{
"item": "Free-model (:free) rate limit — less than 10 credits purchased (all time)",
"value": "20 requests per minute, 50 requests per day",
"numeric": 50,
"unit": "requests/day",
"published": true,
"source": "limits",
"quote": "| Less than 10 | 20 | 50 |",
"verified": true,
"sourceUrl": "https://openrouter.ai/docs/api-reference/limits"
},
{
"item": "Free-model (:free) rate limit — at least 10 credits purchased (all time)",
"value": "20 requests per minute, 1000 requests per day",
"numeric": 1000,
"unit": "requests/day",
"published": true,
"source": "limits",
"quote": "| At least 10 | 20 | 1000 |",
"verified": true,
"sourceUrl": "https://openrouter.ai/docs/api-reference/limits"
},
{
"item": "Rate limits on paid models (Standard and Business)",
"value": "Passthrough from the provider(s)",
"unit": "requests",
"published": false,
"source": "pricing",
"quote": "Standard Passthrough from the provider(s)",
"verified": true,
"sourceUrl": "https://openrouter.ai/pricing"
},
{
"item": "Rate limits — Enterprise",
"value": "Higher allowances available",
"unit": "requests",
"published": false,
"source": "pricing",
"quote": "Enterprise Higher allowances available",
"verified": true,
"sourceUrl": "https://openrouter.ai/pricing"
},
{
"item": "Tokens per minute (TPM) limit",
"value": "No TPM figure published by OpenRouter; paid-model rate limits are passed through from the provider(s)",
"unit": "tokens/min",
"published": false,
"source": "pricing",
"quote": "Standard Passthrough from the provider(s)",
"verified": true,
"sourceUrl": "https://openrouter.ai/pricing"
},
{
"item": "BYOK fee-free allowance (Standard and Business)",
"value": "$25,000 of list price inference per month with no fees, 5% fee after",
"numeric": 25000,
"unit": "USD/month",
"published": true,
"source": "pricing",
"quote": "Standard $25,000 of list price inference / month with no fees, 5% fee after",
"verified": true,
"sourceUrl": "https://openrouter.ai/pricing"
},
{
"item": "BYOK fee above allowance",
"value": "5% of what the same model and provider would normally cost on OpenRouter",
"numeric": 5,
"unit": "percent",
"published": true,
"source": "faq",
"quote": "Usage above the allowance has a fee of 5% of what the same model and provider would normally cost on OpenRouter.",
"verified": true,
"sourceUrl": "https://openrouter.ai/docs/faq"
},
{
"item": "Prompt logging opt-in discount",
"value": "1% discount on usage costs",
"numeric": 1,
"unit": "percent",
"published": true,
"source": "faq",
"quote": "lets users opt-in to log their prompts and completions in exchange for a 1% discount on usage costs.",
"verified": true,
"sourceUrl": "https://openrouter.ai/docs/faq"
},
{
"item": "Cache read pricing (Anthropic models)",
"value": "0.1x the price of the original input pricing",
"numeric": 0.1,
"unit": "multiplier of input price",
"published": true,
"source": "prompt_caching",
"quote": "**Cache reads**: charged at 0.1x the price of the original input pricing",
"verified": true,
"sourceUrl": "https://openrouter.ai/docs/features/prompt-caching"
},
{
"item": "Cache read pricing (OpenAI models)",
"value": "0.25x or 0.50x the price of the original input pricing, depending on the model",
"unit": "multiplier of input price",
"published": true,
"source": "prompt_caching",
"quote": "**Cache reads**: (depending on the model) charged at 0.25x or 0.50x the price of the original input pricing",
"verified": true,
"sourceUrl": "https://openrouter.ai/docs/features/prompt-caching"
},
{
"item": "Cache writes (OpenAI GPT-5.6 and later)",
"value": "1.25x the price of the original input pricing",
"numeric": 1.25,
"unit": "multiplier of input price",
"published": true,
"source": "prompt_caching",
"quote": "GPT-5.6 and later charge cache writes at 1.25x the price of the original input pricing",
"verified": true,
"sourceUrl": "https://openrouter.ai/docs/features/prompt-caching"
},
{
"item": "Cache writes (Anthropic, 1-hour TTL)",
"value": "2x the price of the original input pricing",
"numeric": 2,
"unit": "multiplier of input price",
"published": true,
"source": "prompt_caching",
"quote": "**Cache writes (1-hour TTL)**: charged at 2x the price of the original input pricing",
"verified": true,
"sourceUrl": "https://openrouter.ai/docs/features/prompt-caching"
},
{
"item": "Batch API discount",
"value": "No general batch discount percentage stated; batch-priced versions are separate :batch model entries with their own prices",
"unit": "percent",
"published": false,
"source": "faq",
"quote": "`:batch` - The batch-priced version of the model used by the [Batch API]",
"verified": true,
"sourceUrl": "https://openrouter.ai/docs/faq"
},
{
"item": "Volume discounts",
"value": "OpenRouter does not currently offer volume discounts",
"unit": "percent",
"published": false,
"source": "faq",
"quote": "OpenRouter does not currently offer volume discounts",
"verified": true,
"sourceUrl": "https://openrouter.ai/docs/faq"
},
{
"item": "Anthropic: Claude Opus 5.5 — price per 1M input tokens",
"value": "$4 per 1M input tokens (listed as 0.000004 USD per token)",
"numeric": 4,
"unit": "USD per 1M tokens",
"published": true,
"source": "models_api",
"quote": "\"pricing\":{\"prompt\":\"0.000004\",\"completion\":\"0.00002\",\"web_search\":\"0.01\",\"input_cache_read\":\"0.0000002\",\"input_cache_write\":\"0.000005\",\"input_cache_write_1h\":\"0.000008\"}",
"verified": true,
"sourceUrl": "https://openrouter.ai/api/v1/models"
},
{
"item": "Anthropic: Claude Opus 5.5 — price per 1M output tokens",
"value": "$20 per 1M output tokens (listed as 0.00002 USD per token)",
"numeric": 20,
"unit": "USD per 1M tokens",
"published": true,
"source": "models_api",
"quote": "\"pricing\":{\"prompt\":\"0.000004\",\"completion\":\"0.00002\",\"web_search\":\"0.01\",\"input_cache_read\":\"0.0000002\",\"input_cache_write\":\"0.000005\",\"input_cache_write_1h\":\"0.000008\"}",
"verified": true,
"sourceUrl": "https://openrouter.ai/api/v1/models"
},
{
"item": "Anthropic: Claude Opus 5.5 — price per 1M cached input (cache read) tokens",
"value": "$0.2 per 1M cached input (cache read) tokens (listed as 0.0000002 USD per token)",
"numeric": 0.2,
"unit": "USD per 1M tokens",
"published": true,
"source": "models_api",
"quote": "\"pricing\":{\"prompt\":\"0.000004\",\"completion\":\"0.00002\",\"web_search\":\"0.01\",\"input_cache_read\":\"0.0000002\",\"input_cache_write\":\"0.000005\",\"input_cache_write_1h\":\"0.000008\"}",
"verified": true,
"sourceUrl": "https://openrouter.ai/api/v1/models"
},
{
"item": "Anthropic: Claude Opus 5.5 — context window",
"value": "1,000,000 tokens",
"numeric": 1000000,
"unit": "tokens",
"published": true,
"source": "models_api",
"quote": "\"context_length\":1000000",
"verified": true,
"sourceUrl": "https://openrouter.ai/api/v1/models"
},
{
"item": "Anthropic: Claude Opus 5.5 — max output tokens",
"value": "128,000 tokens",
"numeric": 128000,
"unit": "tokens",
"published": true,
"source": "models_api",
"quote": "\"top_provider\":{\"context_length\":1000000,\"max_completion_tokens\":128000,\"is_moderated\":true}",
"verified": true,
"sourceUrl": "https://openrouter.ai/api/v1/models"
},
{
"item": "Anthropic: Claude Sonnet 5.5 — price per 1M input tokens",
"value": "$2 per 1M input tokens (listed as 0.000002 USD per token)",
"numeric": 2,
"unit": "USD per 1M tokens",
"published": true,
"source": "models_api",
"quote": "\"pricing\":{\"prompt\":\"0.000002\",\"completion\":\"0.00001\",\"web_search\":\"0.01\",\"input_cache_read\":\"0.0000001\",\"input_cache_write\":\"0.0000025\",\"input_cache_write_1h\":\"0.000004\"}",
"verified": true,
"sourceUrl": "https://openrouter.ai/api/v1/models"
},
{
"item": "Anthropic: Claude Sonnet 5.5 — price per 1M output tokens",
"value": "$10 per 1M output tokens (listed as 0.00001 USD per token)",
"numeric": 10,
"unit": "USD per 1M tokens",
"published": true,
"source": "models_api",
"quote": "\"pricing\":{\"prompt\":\"0.000002\",\"completion\":\"0.00001\",\"web_search\":\"0.01\",\"input_cache_read\":\"0.0000001\",\"input_cache_write\":\"0.0000025\",\"input_cache_write_1h\":\"0.000004\"}",
"verified": true,
"sourceUrl": "https://openrouter.ai/api/v1/models"
},
{
"item": "Anthropic: Claude Sonnet 5.5 — price per 1M cached input (cache read) tokens",
"value": "$0.1 per 1M cached input (cache read) tokens (listed as 0.0000001 USD per token)",
"numeric": 0.1,
"unit": "USD per 1M tokens",
"published": true,
"source": "models_api",
"quote": "\"pricing\":{\"prompt\":\"0.000002\",\"completion\":\"0.00001\",\"web_search\":\"0.01\",\"input_cache_read\":\"0.0000001\",\"input_cache_write\":\"0.0000025\",\"input_cache_write_1h\":\"0.000004\"}",
"verified": true,
"sourceUrl": "https://openrouter.ai/api/v1/models"
},
{
"item": "Anthropic: Claude Sonnet 5.5 — context window",
"value": "1,000,000 tokens",
"numeric": 1000000,
"unit": "tokens",
"published": true,
"source": "models_api",
"quote": "\"context_length\":1000000",
"verified": true,
"sourceUrl": "https://openrouter.ai/api/v1/models"
},
{
"item": "Anthropic: Claude Sonnet 5.5 — max output tokens",
"value": "128,000 tokens",
"numeric": 128000,
"unit": "tokens",
"published": true,
"source": "models_api",
"quote": "\"top_provider\":{\"context_length\":1000000,\"max_completion_tokens\":128000,\"is_moderated\":true}",
"verified": true,
"sourceUrl": "https://openrouter.ai/api/v1/models"
},
{
"item": "Anthropic: Claude Sonnet 5.5 (batch) — price per 1M input tokens",
"value": "$1 per 1M input tokens (listed as 0.000001 USD per token)",
"numeric": 1,
"unit": "USD per 1M tokens",
"published": true,
"source": "models_api",
"quote": "\"pricing\":{\"prompt\":\"0.000001\",\"completion\":\"0.000005\",\"web_search\":\"0.01\",\"input_cache_read\":\"0.00000005\",\"input_cache_write\":\"0.00000125\",\"input_cache_write_1h\":\"0.000002\"}",
"verified": true,
"sourceUrl": "https://openrouter.ai/api/v1/models"
},
{
"item": "Anthropic: Claude Sonnet 5.5 (batch) — price per 1M output tokens",
"value": "$5 per 1M output tokens (listed as 0.000005 USD per token)",
"numeric": 5,
"unit": "USD per 1M tokens",
"published": true,
"source": "models_api",
"quote": "\"pricing\":{\"prompt\":\"0.000001\",\"completion\":\"0.000005\",\"web_search\":\"0.01\",\"input_cache_read\":\"0.00000005\",\"input_cache_write\":\"0.00000125\",\"input_cache_write_1h\":\"0.000002\"}",
"verified": true,
"sourceUrl": "https://openrouter.ai/api/v1/models"
},
{
"item": "Anthropic: Claude Haiku 5.5 — price per 1M input tokens",
"value": "$0.1 per 1M input tokens (listed as 0.0000001 USD per token)",
"numeric": 0.1,
"unit": "USD per 1M tokens",
"published": true,
"source": "models_api",
"quote": "\"pricing\":{\"prompt\":\"0.0000001\",\"completion\":\"0.0000005\",\"web_search\":\"0.01\",\"input_cache_read\":\"0.00000001\",\"input_cache_write\":\"0.000000125\",\"input_cache_write_1h\":\"0.0000002\",\"overrides\":[{\"min_prompt_tokens\":100000,\"prompt\":\"0.0000005\",\"completion\":\"0.0000025\",\"input_cache_read\":\"0.00000005\",\"input_cache_write\":\"0.000000625\",\"input_cache_write_1h\":\"0.000001\"}",
"verified": true,
"sourceUrl": "https://openrouter.ai/api/v1/models"
},
{
"item": "Anthropic: Claude Haiku 5.5 — price per 1M output tokens",
"value": "$0.5 per 1M output tokens (listed as 0.0000005 USD per token)",
"numeric": 0.5,
"unit": "USD per 1M tokens",
"published": true,
"source": "models_api",
"quote": "\"pricing\":{\"prompt\":\"0.0000001\",\"completion\":\"0.0000005\",\"web_search\":\"0.01\",\"input_cache_read\":\"0.00000001\",\"input_cache_write\":\"0.000000125\",\"input_cache_write_1h\":\"0.0000002\",\"overrides\":[{\"min_prompt_tokens\":100000,\"prompt\":\"0.0000005\",\"completion\":\"0.0000025\",\"input_cache_read\":\"0.00000005\",\"input_cache_write\":\"0.000000625\",\"input_cache_write_1h\":\"0.000001\"}",
"verified": true,
"sourceUrl": "https://openrouter.ai/api/v1/models"
},
{
"item": "Anthropic: Claude Haiku 5.5 — price per 1M cached input (cache read) tokens",
"value": "$0.01 per 1M cached input (cache read) tokens (listed as 0.00000001 USD per token)",
"numeric": 0.01,
"unit": "USD per 1M tokens",
"published": true,
"source": "models_api",
"quote": "\"pricing\":{\"prompt\":\"0.0000001\",\"completion\":\"0.0000005\",\"web_search\":\"0.01\",\"input_cache_read\":\"0.00000001\",\"input_cache_write\":\"0.000000125\",\"input_cache_write_1h\":\"0.0000002\",\"overrides\":[{\"min_prompt_tokens\":100000,\"prompt\":\"0.0000005\",\"completion\":\"0.0000025\",\"input_cache_read\":\"0.00000005\",\"input_cache_write\":\"0.000000625\",\"input_cache_write_1h\":\"0.000001\"}",
"verified": true,
"sourceUrl": "https://openrouter.ai/api/v1/models"
},
{
"item": "Anthropic: Claude Haiku 5.5 — long-context price per 1M input / output tokens (prompts of 100,000+ tokens)",
"value": "$0.5 input / $2.5 output per 1M tokens when prompt is at least 100,000 tokens",
"numeric": 0.5,
"unit": "USD per 1M tokens",
"published": true,
"source": "models_api",
"quote": "\"pricing\":{\"prompt\":\"0.0000001\",\"completion\":\"0.0000005\",\"web_search\":\"0.01\",\"input_cache_read\":\"0.00000001\",\"input_cache_write\":\"0.000000125\",\"input_cache_write_1h\":\"0.0000002\",\"overrides\":[{\"min_prompt_tokens\":100000,\"prompt\":\"0.0000005\",\"completion\":\"0.0000025\",\"input_cache_read\":\"0.00000005\",\"input_cache_write\":\"0.000000625\",\"input_cache_write_1h\":\"0.000001\"}",
"verified": true,
"sourceUrl": "https://openrouter.ai/api/v1/models"
},
{
"item": "Anthropic: Claude Haiku 5.5 — context window",
"value": "1,000,000 tokens",
"numeric": 1000000,
"unit": "tokens",
"published": true,
"source": "models_api",
"quote": "\"context_length\":1000000",
"verified": true,
"sourceUrl": "https://openrouter.ai/api/v1/models"
},
{
"item": "Anthropic: Claude Haiku 5.5 — max output tokens",
"value": "128,000 tokens",
"numeric": 128000,
"unit": "tokens",
"published": true,
"source": "models_api",
"quote": "\"top_provider\":{\"context_length\":1000000,\"max_completion_tokens\":128000,\"is_moderated\":true}",
"verified": true,
"sourceUrl": "https://openrouter.ai/api/v1/models"
},
{
"item": "Anthropic: Claude Haiku 5.5 (batch) — price per 1M input tokens",
"value": "$0.05 per 1M input tokens (listed as 0.00000005 USD per token)",
"numeric": 0.05,
"unit": "USD per 1M tokens",
"published": true,
"source": "models_api",
"quote": "\"pricing\":{\"prompt\":\"0.00000005\",\"completion\":\"0.00000025\",\"web_search\":\"0.01\",\"input_cache_read\":\"0.000000005\",\"input_cache_write\":\"0.0000000625\",\"input_cache_write_1h\":\"0.0000001\",\"overrides\":[{\"min_prompt_tokens\":100000,\"prompt\":\"0.00000025\",\"completion\":\"0.00000125\",\"input_cache_read\":\"0.000000025\",\"input_cache_write\":\"0.0000003125\",\"input_cache_write_1h\":\"0.0000005\"}",
"verified": true,
"sourceUrl": "https://openrouter.ai/api/v1/models"
},
{
"item": "Anthropic: Claude Haiku 5.5 (batch) — price per 1M output tokens",
"value": "$0.25 per 1M output tokens (listed as 0.00000025 USD per token)",
"numeric": 0.25,
"unit": "USD per 1M tokens",
"published": true,
"source": "models_api",
"quote": "\"pricing\":{\"prompt\":\"0.00000005\",\"completion\":\"0.00000025\",\"web_search\":\"0.01\",\"input_cache_read\":\"0.000000005\",\"input_cache_write\":\"0.0000000625\",\"input_cache_write_1h\":\"0.0000001\",\"overrides\":[{\"min_prompt_tokens\":100000,\"prompt\":\"0.00000025\",\"completion\":\"0.00000125\",\"input_cache_read\":\"0.000000025\",\"input_cache_write\":\"0.0000003125\",\"input_cache_write_1h\":\"0.0000005\"}",
"verified": true,
"sourceUrl": "https://openrouter.ai/api/v1/models"
},
{
"item": "OpenAI: GPT-6.1 Sol — price per 1M input tokens",
"value": "$2 per 1M input tokens (listed as 0.000002 USD per token)",
"numeric": 2,
"unit": "USD per 1M tokens",
"published": true,
"source": "models_api",
"quote": "\"pricing\":{\"prompt\":\"0.000002\",\"completion\":\"0.00001\",\"web_search\":\"0.01\",\"input_cache_read\":\"0.0000001\",\"input_cache_write\":\"0.0000025\",\"overrides\":[{\"min_prompt_tokens\":272000,\"prompt\":\"0.000004\",\"completion\":\"0.000015\",\"input_cache_read\":\"0.0000002\",\"input_cache_write\":\"0.000005\"}",
"verified": true,
"sourceUrl": "https://openrouter.ai/api/v1/models"
},
{
"item": "OpenAI: GPT-6.1 Sol — price per 1M output tokens",
"value": "$10 per 1M output tokens (listed as 0.00001 USD per token)",
"numeric": 10,
"unit": "USD per 1M tokens",
"published": true,
"source": "models_api",
"quote": "\"pricing\":{\"prompt\":\"0.000002\",\"completion\":\"0.00001\",\"web_search\":\"0.01\",\"input_cache_read\":\"0.0000001\",\"input_cache_write\":\"0.0000025\",\"overrides\":[{\"min_prompt_tokens\":272000,\"prompt\":\"0.000004\",\"completion\":\"0.000015\",\"input_cache_read\":\"0.0000002\",\"input_cache_write\":\"0.000005\"}",
"verified": true,
"sourceUrl": "https://openrouter.ai/api/v1/models"
},
{
"item": "OpenAI: GPT-6.1 Sol — price per 1M cached input (cache read) tokens",
"value": "$0.1 per 1M cached input (cache read) tokens (listed as 0.0000001 USD per token)",
"numeric": 0.1,
"unit": "USD per 1M tokens",
"published": true,
"source": "models_api",
"quote": "\"pricing\":{\"prompt\":\"0.000002\",\"completion\":\"0.00001\",\"web_search\":\"0.01\",\"input_cache_read\":\"0.0000001\",\"input_cache_write\":\"0.0000025\",\"overrides\":[{\"min_prompt_tokens\":272000,\"prompt\":\"0.000004\",\"completion\":\"0.000015\",\"input_cache_read\":\"0.0000002\",\"input_cache_write\":\"0.000005\"}",
"verified": true,
"sourceUrl": "https://openrouter.ai/api/v1/models"
},
{
"item": "OpenAI: GPT-6.1 Sol — long-context price per 1M input / output tokens (prompts of 272,000+ tokens)",
"value": "$4 input / $15 output per 1M tokens when prompt is at least 272,000 tokens",
"numeric": 4,
"unit": "USD per 1M tokens",
"published": true,
"source": "models_api",
"quote": "\"pricing\":{\"prompt\":\"0.000002\",\"completion\":\"0.00001\",\"web_search\":\"0.01\",\"input_cache_read\":\"0.0000001\",\"input_cache_write\":\"0.0000025\",\"overrides\":[{\"min_prompt_tokens\":272000,\"prompt\":\"0.000004\",\"completion\":\"0.000015\",\"input_cache_read\":\"0.0000002\",\"input_cache_write\":\"0.000005\"}",
"verified": true,
"sourceUrl": "https://openrouter.ai/api/v1/models"
},
{
"item": "OpenAI: GPT-6.1 Sol — context window",
"value": "1,050,000 tokens",
"numeric": 1050000,
"unit": "tokens",
"published": true,
"source": "models_api",
"quote": "\"context_length\":1050000",
"verified": true,
"sourceUrl": "https://openrouter.ai/api/v1/models"
},
{
"item": "OpenAI: GPT-6.1 Sol — max output tokens",
"value": "128,000 tokens",
"numeric": 128000,
"unit": "tokens",
"published": true,
"source": "models_api",
"quote": "\"top_provider\":{\"context_length\":1050000,\"max_completion_tokens\":128000,\"is_moderated\":true}",
"verified": true,
"sourceUrl": "https://openrouter.ai/api/v1/models"
},
{
"item": "OpenAI: GPT-6.1 Sol (batch) — price per 1M input tokens",
"value": "$1 per 1M input tokens (listed as 0.000001 USD per token)",
"numeric": 1,
"unit": "USD per 1M tokens",
"published": true,
"source": "models_api",
"quote": "\"pricing\":{\"prompt\":\"0.000001\",\"completion\":\"0.000005\",\"web_search\":\"0.01\",\"input_cache_read\":\"0.00000005\",\"input_cache_write\":\"0.00000125\",\"overrides\":[{\"min_prompt_tokens\":272000,\"prompt\":\"0.000002\",\"completion\":\"0.0000075\",\"input_cache_read\":\"0.0000001\",\"input_cache_write\":\"0.0000025\"}",
"verified": true,
"sourceUrl": "https://openrouter.ai/api/v1/models"
},
{
"item": "OpenAI: GPT-6.1 Sol (batch) — price per 1M output tokens",
"value": "$5 per 1M output tokens (listed as 0.000005 USD per token)",
"numeric": 5,
"unit": "USD per 1M tokens",
"published": true,
"source": "models_api",
"quote": "\"pricing\":{\"prompt\":\"0.000001\",\"completion\":\"0.000005\",\"web_search\":\"0.01\",\"input_cache_read\":\"0.00000005\",\"input_cache_write\":\"0.00000125\",\"overrides\":[{\"min_prompt_tokens\":272000,\"prompt\":\"0.000002\",\"completion\":\"0.0000075\",\"input_cache_read\":\"0.0000001\",\"input_cache_write\":\"0.0000025\"}",
"verified": true,
"sourceUrl": "https://openrouter.ai/api/v1/models"
},
{
"item": "OpenAI: GPT-6.1 Terra — price per 1M input tokens",
"value": "$1 per 1M input tokens (listed as 0.000001 USD per token)",
"numeric": 1,
"unit": "USD per 1M tokens",
"published": true,
"source": "models_api",
"quote": "\"pricing\":{\"prompt\":\"0.000001\",\"completion\":\"0.000005\",\"web_search\":\"0.01\",\"input_cache_read\":\"0.00000005\",\"input_cache_write\":\"0.00000125\",\"overrides\":[{\"min_prompt_tokens\":272000,\"prompt\":\"0.000002\",\"completion\":\"0.0000075\",\"input_cache_read\":\"0.0000001\",\"input_cache_write\":\"0.0000025\"}",
"verified": true,
"sourceUrl": "https://openrouter.ai/api/v1/models"
},
{
"item": "OpenAI: GPT-6.1 Terra — price per 1M output tokens",
"value": "$5 per 1M output tokens (listed as 0.000005 USD per token)",
"numeric": 5,
"unit": "USD per 1M tokens",
"published": true,
"source": "models_api",
"quote": "\"pricing\":{\"prompt\":\"0.000001\",\"completion\":\"0.000005\",\"web_search\":\"0.01\",\"input_cache_read\":\"0.00000005\",\"input_cache_write\":\"0.00000125\",\"overrides\":[{\"min_prompt_tokens\":272000,\"prompt\":\"0.000002\",\"completion\":\"0.0000075\",\"input_cache_read\":\"0.0000001\",\"input_cache_write\":\"0.0000025\"}",
"verified": true,
"sourceUrl": "https://openrouter.ai/api/v1/models"
},
{
"item": "OpenAI: GPT-6.1 Terra — price per 1M cached input (cache read) tokens",
"value": "$0.05 per 1M cached input (cache read) tokens (listed as 0.00000005 USD per token)",
"numeric": 0.05,
"unit": "USD per 1M tokens",
"published": true,
"source": "models_api",
"quote": "\"pricing\":{\"prompt\":\"0.000001\",\"completion\":\"0.000005\",\"web_search\":\"0.01\",\"input_cache_read\":\"0.00000005\",\"input_cache_write\":\"0.00000125\",\"overrides\":[{\"min_prompt_tokens\":272000,\"prompt\":\"0.000002\",\"completion\":\"0.0000075\",\"input_cache_read\":\"0.0000001\",\"input_cache_write\":\"0.0000025\"}",
"verified": true,
"sourceUrl": "https://openrouter.ai/api/v1/models"
},
{
"item": "OpenAI: GPT-6.1 Terra — long-context price per 1M input / output tokens (prompts of 272,000+ tokens)",
"value": "$2 input / $7.5 output per 1M tokens when prompt is at least 272,000 tokens",
"numeric": 2,
"unit": "USD per 1M tokens",
"published": true,
"source": "models_api",
"quote": "\"pricing\":{\"prompt\":\"0.000001\",\"completion\":\"0.000005\",\"web_search\":\"0.01\",\"input_cache_read\":\"0.00000005\",\"input_cache_write\":\"0.00000125\",\"overrides\":[{\"min_prompt_tokens\":272000,\"prompt\":\"0.000002\",\"completion\":\"0.0000075\",\"input_cache_read\":\"0.0000001\",\"input_cache_write\":\"0.0000025\"}",
"verified": true,
"sourceUrl": "https://openrouter.ai/api/v1/models"
},
{
"item": "OpenAI: GPT-6.1 Terra — context window",
"value": "1,050,000 tokens",
"numeric": 1050000,
"unit": "tokens",
"published": true,
"source": "models_api",
"quote": "\"context_length\":1050000",
"verified": true,
"sourceUrl": "https://openrouter.ai/api/v1/models"
},
{
"item": "OpenAI: GPT-6.1 Terra — max output tokens",
"value": "128,000 tokens",
"numeric": 128000,
"unit": "tokens",
"published": true,
"source": "models_api",
"quote": "\"top_provider\":{\"context_length\":1050000,\"max_completion_tokens\":128000,\"is_moderated\":true}",
"verified": true,
"sourceUrl": "https://openrouter.ai/api/v1/models"
},
{
"item": "OpenAI: GPT-6.1 Terra (batch) — price per 1M input tokens",
"value": "$0.5 per 1M input tokens (listed as 0.0000005 USD per token)",
"numeric": 0.5,
"unit": "USD per 1M tokens",
"published": true,
"source": "models_api",
"quote": "\"pricing\":{\"prompt\":\"0.0000005\",\"completion\":\"0.0000025\",\"web_search\":\"0.01\",\"input_cache_read\":\"0.000000025\",\"input_cache_write\":\"0.000000625\",\"overrides\":[{\"min_prompt_tokens\":272000,\"prompt\":\"0.000001\",\"completion\":\"0.00000375\",\"input_cache_read\":\"0.00000005\",\"input_cache_write\":\"0.00000125\"}",
"verified": true,
"sourceUrl": "https://openrouter.ai/api/v1/models"
},
{
"item": "OpenAI: GPT-6.1 Terra (batch) — price per 1M output tokens",
"value": "$2.5 per 1M output tokens (listed as 0.0000025 USD per token)",
"numeric": 2.5,
"unit": "USD per 1M tokens",
"published": true,
"source": "models_api",
"quote": "\"pricing\":{\"prompt\":\"0.0000005\",\"completion\":\"0.0000025\",\"web_search\":\"0.01\",\"input_cache_read\":\"0.000000025\",\"input_cache_write\":\"0.000000625\",\"overrides\":[{\"min_prompt_tokens\":272000,\"prompt\":\"0.000001\",\"completion\":\"0.00000375\",\"input_cache_read\":\"0.00000005\",\"input_cache_write\":\"0.00000125\"}",
"verified": true,
"sourceUrl": "https://openrouter.ai/api/v1/models"
},
{
"item": "OpenAI: GPT-6 Luna — price per 1M input tokens",
"value": "$0.1 per 1M input tokens (listed as 0.0000001 USD per token)",
"numeric": 0.1,
"unit": "USD per 1M tokens",
"published": true,
"source": "models_api",
"quote": "\"pricing\":{\"prompt\":\"0.0000001\",\"completion\":\"0.0000005\",\"web_search\":\"0.01\",\"input_cache_read\":\"0.00000001\",\"input_cache_write\":\"0.000000125\",\"overrides\":[{\"min_prompt_tokens\":272000,\"prompt\":\"0.0000002\",\"completion\":\"0.00000075\",\"input_cache_read\":\"0.00000002\",\"input_cache_write\":\"0.00000025\"}",
"verified": true,
"sourceUrl": "https://openrouter.ai/api/v1/models"
},
{
"item": "OpenAI: GPT-6 Luna — price per 1M output tokens",
"value": "$0.5 per 1M output tokens (listed as 0.0000005 USD per token)",
"numeric": 0.5,
"unit": "USD per 1M tokens",
"published": true,
"source": "models_api",
"quote": "\"pricing\":{\"prompt\":\"0.0000001\",\"completion\":\"0.0000005\",\"web_search\":\"0.01\",\"input_cache_read\":\"0.00000001\",\"input_cache_write\":\"0.000000125\",\"overrides\":[{\"min_prompt_tokens\":272000,\"prompt\":\"0.0000002\",\"completion\":\"0.00000075\",\"input_cache_read\":\"0.00000002\",\"input_cache_write\":\"0.00000025\"}",
"verified": true,
"sourceUrl": "https://openrouter.ai/api/v1/models"
},
{
"item": "OpenAI: GPT-6 Luna — price per 1M cached input (cache read) tokens",
"value": "$0.01 per 1M cached input (cache read) tokens (listed as 0.00000001 USD per token)",
"numeric": 0.01,
"unit": "USD per 1M tokens",
"published": true,
"source": "models_api",
"quote": "\"pricing\":{\"prompt\":\"0.0000001\",\"completion\":\"0.0000005\",\"web_search\":\"0.01\",\"input_cache_read\":\"0.00000001\",\"input_cache_write\":\"0.000000125\",\"overrides\":[{\"min_prompt_tokens\":272000,\"prompt\":\"0.0000002\",\"completion\":\"0.00000075\",\"input_cache_read\":\"0.00000002\",\"input_cache_write\":\"0.00000025\"}",
"verified": true,
"sourceUrl": "https://openrouter.ai/api/v1/models"
},
{
"item": "OpenAI: GPT-6 Luna — long-context price per 1M input / output tokens (prompts of 272,000+ tokens)",
"value": "$0.2 input / $0.75 output per 1M tokens when prompt is at least 272,000 tokens",
"numeric": 0.2,
"unit": "USD per 1M tokens",
"published": true,
"source": "models_api",
"quote": "\"pricing\":{\"prompt\":\"0.0000001\",\"completion\":\"0.0000005\",\"web_search\":\"0.01\",\"input_cache_read\":\"0.00000001\",\"input_cache_write\":\"0.000000125\",\"overrides\":[{\"min_prompt_tokens\":272000,\"prompt\":\"0.0000002\",\"completion\":\"0.00000075\",\"input_cache_read\":\"0.00000002\",\"input_cache_write\":\"0.00000025\"}",
"verified": true,
"sourceUrl": "https://openrouter.ai/api/v1/models"
},
{
"item": "OpenAI: GPT-6 Luna — context window",
"value": "1,050,000 tokens",
"numeric": 1050000,
"unit": "tokens",
"published": true,
"source": "models_api",
"quote": "\"context_length\":1050000",
"verified": true,
"sourceUrl": "https://openrouter.ai/api/v1/models"
},
{
"item": "OpenAI: GPT-6 Luna — max output tokens",
"value": "128,000 tokens",
"numeric": 128000,
"unit": "tokens",
"published": true,
"source": "models_api",
"quote": "\"top_provider\":{\"context_length\":1050000,\"max_completion_tokens\":128000,\"is_moderated\":true}",
"verified": true,
"sourceUrl": "https://openrouter.ai/api/v1/models"
},
{
"item": "OpenAI: GPT-6 Luna (batch) — price per 1M input tokens",
"value": "$0.05 per 1M input tokens (listed as 0.00000005 USD per token)",
"numeric": 0.05,
"unit": "USD per 1M tokens",
"published": true,
"source": "models_api",
"quote": "\"pricing\":{\"prompt\":\"0.00000005\",\"completion\":\"0.00000025\",\"web_search\":\"0.01\",\"input_cache_read\":\"0.000000005\",\"input_cache_write\":\"0.0000000625\",\"overrides\":[{\"min_prompt_tokens\":272000,\"prompt\":\"0.0000001\",\"completion\":\"0.000000375\",\"input_cache_read\":\"0.00000001\",\"input_cache_write\":\"0.000000125\"}",
"verified": true,
"sourceUrl": "https://openrouter.ai/api/v1/models"
},
{
"item": "OpenAI: GPT-6 Luna (batch) — price per 1M output tokens",
"value": "$0.25 per 1M output tokens (listed as 0.00000025 USD per token)",
"numeric": 0.25,
"unit": "USD per 1M tokens",
"published": true,
"source": "models_api",
"quote": "\"pricing\":{\"prompt\":\"0.00000005\",\"completion\":\"0.00000025\",\"web_search\":\"0.01\",\"input_cache_read\":\"0.000000005\",\"input_cache_write\":\"0.0000000625\",\"overrides\":[{\"min_prompt_tokens\":272000,\"prompt\":\"0.0000001\",\"completion\":\"0.000000375\",\"input_cache_read\":\"0.00000001\",\"input_cache_write\":\"0.000000125\"}",
"verified": true,
"sourceUrl": "https://openrouter.ai/api/v1/models"
},
{
"item": "Google: Gemini 4 Argon — price per 1M input tokens",
"value": "$2 per 1M input tokens (listed as 0.000002 USD per token)",
"numeric": 2,
"unit": "USD per 1M tokens",
"published": true,
"source": "models_api",
"quote": "\"pricing\":{\"prompt\":\"0.000002\",\"completion\":\"0.00001\",\"image\":\"0.000002\",\"audio\":\"0.000002\",\"input_audio_cache\":\"0.0000001\",\"web_search\":\"0.014\",\"internal_reasoning\":\"0.00001\",\"input_cache_read\":\"0.0000001\",\"input_cache_write\":\"0.0000001875\"}",
"verified": true,
"sourceUrl": "https://openrouter.ai/api/v1/models"
}
],
"overage": {
"policy": "not published"
},
"gotchas": []
},
{
"id": "cohere",
"name": "Cohere API",
"vendor": "Cohere",
"category": "llm-api",
"url": "https://cohere.com",
"checked": "2026-10-30",
"sources": {
"pricing": {
"name": "Pricing | Secure and Scalable Enterprise AI | Cohere",
"url": "https://cohere.com/pricing"
},
"ratelimits": {
"name": "Different Types of API Keys and Rate Limits",
"url": "https://docs.cohere.com/docs/rate-limits"
},
"pricingdocs": {
"name": "How Does Cohere's Pricing Work?",
"url": "https://docs.cohere.com/docs/how-does-cohere-pricing-work"
},
"models": {
"name": "An Overview of Cohere's Models",
"url": "https://docs.cohere.com/docs/models"
},
"golive": {
"name": "Going Live",
"url": "https://docs.cohere.com/docs/going-live"
},
"faqs": {
"name": "Cohere FAQs",
"url": "https://docs.cohere.com/docs/cohere-faqs"
},
"commanda": {
"name": "Command A",
"url": "https://docs.cohere.com/docs/command-a"
},
"commandr7b": {
"name": "Cohere's Command R7B Model",
"url": "https://docs.cohere.com/docs/command-r7b"
},
"commandaplus": {
"name": "Command A+",
"url": "https://docs.cohere.com/docs/command-a-plus"
},
"command": {
"name": "Command | Cohere",
"url": "https://cohere.com/command"
}
},
"unit": {
"tag": "Per 1M tokens",
"definition": "Generative models are priced per token, with input tokens (text sent to the model) and output tokens (text generated by the model) priced differently. Simple text may approach 1 token per word on average, while complex texts may use 3-4 tokens per word on average.",
"source": "pricingdocs",
"quote": "Our generative models, such as Command A+, Command A, Command R7B, Command R, and Command R+, are priced on a per-token basis. Be aware that input tokens (i.e. tokens generated from text sent to the model) and output tokens (i.e. text generated by the model) are priced differently."
},
"free": {
"summary": "A free Trial API key is created automatically when you sign up. Trial calls are free but rate limited (20 requests/min for Chat models), limited to 1,000 API calls a month, and may not be used for production or commercial purposes.",
"published": true,
"source": "pricing",
"quote": "API calls made from a Trial API key are free. However, trial keys are rate limited and are not permitted to be used for production or commercial purposes."
},
"plans": [
{
"id": "trial",
"name": "Trial API key",
"priceUsd": 0,
"priceNote": "Free",
"billing": "usage",
"included": "Free API calls on all models and APIs. Rate limited and limited to 1,000 API calls a month. Not for production or commercial use.",
"source": "ratelimits",
"quote": "Trial keys (and prod keys on newer Chat model variants) are limited to 1,000 API calls a month.",
"sourceUrl": "https://docs.cohere.com/docs/rate-limits"
},
{
"id": "production",
"name": "Production API key",
"priceUsd": null,
"priceNote": "Pay-as-you-go at per-model token prices",
"billing": "usage",
"included": "Charged pay-as-you-go and designed for production use at scale. You get it by completing the Go to Production workflow on the Billing and Usage page.",
"source": "pricing",
"quote": "API calls made from a Production API key will be charged on a pay-as-you-go basis. Production API keys are designed for production use at scale.",
"sourceUrl": "https://cohere.com/pricing"
}
],
"rates": [
{
"item": "Command A (command-a-03-2025) input per 1M tokens",
"value": "$2.5 / 1M tokens",
"numeric": 2.5,
"unit": "USD/1M tokens",
"published": true,
"source": "commanda",
"quote": "Input\n\n$2.5 / 1M tokens",
"verified": true,
"sourceUrl": "https://docs.cohere.com/docs/command-a"
},
{
"item": "Command A (command-a-03-2025) output per 1M tokens",
"value": "$10 / 1M tokens",
"numeric": 10,
"unit": "USD/1M tokens",
"published": true,
"source": "commanda",
"quote": "Output\n\n$10 / 1M tokens",
"verified": true,
"sourceUrl": "https://docs.cohere.com/docs/command-a"
},
{
"item": "Command R7B (command-r7b-12-2024) input per 1M tokens",
"value": "$0.0375 / 1M tokens",
"numeric": 0.0375,
"unit": "USD/1M tokens",
"published": true,
"source": "commandr7b",
"quote": "Input\n\n$0.0375 / 1M tokens",
"verified": true,
"sourceUrl": "https://docs.cohere.com/docs/command-r7b"
},
{
"item": "Command R7B (command-r7b-12-2024) output per 1M tokens",
"value": "$0.15 / 1M tokens",
"numeric": 0.15,
"unit": "USD/1M tokens",
"published": true,
"source": "commandr7b",
"quote": "Output\n\n$0.15 / 1M tokens",
"verified": true,
"sourceUrl": "https://docs.cohere.com/docs/command-r7b"
},
{
"item": "Command R+ 08-2024 input per 1M tokens",
"value": "$2.50/1M tokens",
"numeric": 2.5,
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "Command R+ 08-2024 pricing is $2.50/1M tokens for input and $10.00/1M tokens for output",
"verified": true,
"sourceUrl": "https://cohere.com/pricing"
},
{
"item": "Command R+ 08-2024 output per 1M tokens",
"value": "$10.00/1M tokens",
"numeric": 10,
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "Command R+ 08-2024 pricing is $2.50/1M tokens for input and $10.00/1M tokens for output",
"verified": true,
"sourceUrl": "https://cohere.com/pricing"
},
{
"item": "Aya Expanse (8B and 32B) input per 1M tokens",
"value": "$0.50/1M tokens",
"numeric": 0.5,
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "Aya Expanse models (8B and 32B) on the API are charged at $0.50/1M tokens for input and $1.50/1M tokens for output.",
"verified": true,
"sourceUrl": "https://cohere.com/pricing"
},
{
"item": "Aya Expanse (8B and 32B) output per 1M tokens",
"value": "$1.50/1M tokens",
"numeric": 1.5,
"unit": "USD/1M tokens",
"published": true,
"source": "pricing",
"quote": "Aya Expanse models (8B and 32B) on the API are charged at $0.50/1M tokens for input and $1.50/1M tokens for output.",
"verified": true,
"sourceUrl": "https://cohere.com/pricing"
},
{
"item": "Command A+ (command-a-plus-05-2026) price",
"value": "For both trial keys and production keys, Command A+ is free until rate limits are reached. It can be used in production through Cohere's Model Vault.",
"unit": "USD/1M tokens",
"published": false,
"source": "commandaplus",
"quote": "For both trial keys and production keys, Command A+ is free until rate limits are reached.",
"verified": true,
"sourceUrl": "https://docs.cohere.com/docs/command-a-plus"
},
{
"item": "Trial rate limit: Chat (Command A+, A Reasoning, A Translate, A Vision, A, R+, R, R7B, North Mini Code)",
"value": "20 req / min",
"numeric": 20,
"unit": "requests/min",
"published": true,
"source": "ratelimits",
"quote": "| Command A | 20 req / min | 500 req / min |",
"verified": true,
"sourceUrl": "https://docs.cohere.com/docs/rate-limits"
},
{
"item": "Production rate limit: Command A, Command R+, Command R, Command R7B, North Mini Code",
"value": "500 req / min",
"numeric": 500,
"unit": "requests/min",
"published": true,
"source": "ratelimits",
"quote": "| Command R7B | 20 req / min | 500 req / min |",
"verified": true,
"sourceUrl": "https://docs.cohere.com/docs/rate-limits"
},
{
"item": "Production rate limit: Command A+, Command A Reasoning, Command A Translate, Command A Vision",
"value": "Contact sales@cohere.com",
"unit": "requests/min",
"published": false,
"source": "ratelimits",
"quote": "| Command A Reasoning | 20 req / min | Contact sales@cohere.com |",
"verified": true,
"sourceUrl": "https://docs.cohere.com/docs/rate-limits"
},
{
"item": "Trial monthly call cap",
"value": "1,000 API calls a month",
"numeric": 1000,
"unit": "calls/month",
"published": true,
"source": "ratelimits",
"quote": "Trial keys (and prod keys on newer Chat model variants) are limited to 1,000 API calls a month.",
"verified": true,
"sourceUrl": "https://docs.cohere.com/docs/rate-limits"
},
{
"item": "Rate-limit tier unlock (spend or deposit)",
"value": "No spend-based tiers. Production key obtained via the Go to Production workflow; for rate limit increases contact support@cohere.com.",
"unit": "",
"published": false,
"source": "ratelimits",
"quote": "If you have any questions or want to speak about getting a rate limit increase, reach out to support@cohere.com.",
"verified": true,
"sourceUrl": "https://docs.cohere.com/docs/rate-limits"
},
{
"item": "Context window: Command A+ (command-a-plus-05-2026)",
"value": "128,000 tokens",
"numeric": 128000,
"unit": "tokens",
"published": true,
"source": "commandaplus",
"quote": "**Context Window:** 128,000 tokens",
"verified": true,
"sourceUrl": "https://docs.cohere.com/docs/command-a-plus"
},
{
"item": "Max output: Command A+ (command-a-plus-05-2026)",
"value": "64,000 tokens",
"numeric": 64000,
"unit": "tokens",
"published": true,
"source": "commandaplus",
"quote": "**Max Output Tokens:** 64,000 tokens",
"verified": true,
"sourceUrl": "https://docs.cohere.com/docs/command-a-plus"
},
{
"item": "Context window: Command A (command-a-03-2025)",
"value": "256,000 tokens",
"numeric": 256000,
"unit": "tokens",
"published": true,
"source": "commanda",
"quote": "**Context Window:** 256,000 tokens",
"verified": true,
"sourceUrl": "https://docs.cohere.com/docs/command-a"
},
{
"item": "Max output: Command A (command-a-03-2025)",
"value": "8,000 tokens",
"numeric": 8000,
"unit": "tokens",
"published": true,
"source": "commanda",
"quote": "**Max Output Tokens:** 8,000 tokens",
"verified": true,
"sourceUrl": "https://docs.cohere.com/docs/command-a"
},
{
"item": "Context window: Command R7B (command-r7b-12-2024)",
"value": "128,000 tokens",
"numeric": 128000,
"unit": "tokens",
"published": true,
"source": "commandr7b",
"quote": "**Context Window:** 128,000 tokens",
"verified": true,
"sourceUrl": "https://docs.cohere.com/docs/command-r7b"
},
{
"item": "Max output: Command R7B (command-r7b-12-2024)",
"value": "4,000 tokens",
"numeric": 4000,
"unit": "tokens",
"published": true,
"source": "commandr7b",
"quote": "**Max Output Tokens:** 4,000 tokens",
"verified": true,
"sourceUrl": "https://docs.cohere.com/docs/command-r7b"
},
{
"item": "Context window / max output: Command A Reasoning (command-a-reasoning-08-2025)",
"value": "256k context / 32k max output",
"unit": "tokens",
"published": true,
"source": "models",
"quote": "| `command-a-reasoning-08-2025` | Live | ... | Text | 256k | 32k |",
"verified": true,
"sourceUrl": "https://docs.cohere.com/docs/models"
},
{
"item": "Context window / max output: Command A Vision (command-a-vision-07-2025)",
"value": "128K context / 8K max output",
"unit": "tokens",
"published": true,
"source": "models",
"quote": "| `command-a-vision-07-2025` | Live | ... | Text, Images | 128K | 8K |",
"verified": true,
"sourceUrl": "https://docs.cohere.com/docs/models"
},
{
"item": "Context window / max output: Command A Translate (command-a-translate-08-2025)",
"value": "8K context / 8k max output",
"unit": "tokens",
"published": true,
"source": "models",
"quote": "| `command-a-translate-08-2025` | Live | ... | Text | 8K | 8k |",
"verified": true,
"sourceUrl": "https://docs.cohere.com/docs/models"
},
{
"item": "Context window / max output: Command R+ (command-r-plus-08-2024) and Command R (command-r-08-2024)",
"value": "128k context / 4k max output",
"unit": "tokens",
"published": true,
"source": "models",
"quote": "| `command-r-plus-08-2024` | Live | ... | Text | 128k | 4k |",
"verified": true,
"sourceUrl": "https://docs.cohere.com/docs/models"
},
{
"item": "Context window / max output: North Mini Code (north-mini-code-1.0)",
"value": "256k context / 64k max output",
"unit": "tokens",
"published": true,
"source": "models",
"quote": "| `north-mini-code-1.0` | Live | ... | Text | 256k | 64k |",
"verified": true,
"sourceUrl": "https://docs.cohere.com/docs/models"
},
{
"item": "Context window / max output: North Small Translate (north-small-translate-1.0)",
"value": "16k context / 16k max output",
"unit": "tokens",
"published": true,
"source": "models",
"quote": "| `north-small-translate-1.0` | Live | ... | Text | 16k | 16k |",
"verified": true,
"sourceUrl": "https://docs.cohere.com/docs/models"
}
],
"overage": {
"policy": "pay-as-you-go",
"summary": "Production usage is billed pay-as-you-go. The bill is issued at the end of each calendar month, or when outstanding balances reach $250. A monthly spending limit can be set in the Billing & Usage section of the dashboard.",
"source": "pricing",
"quote": "Your bill will be issued at the end of every calendar month or when you reach $250 in outstanding balances."
},
"gotchas": [
{
"title": "Production keys act like trial keys on newer models",
"detail": "Production keys work like trial keys for newer model variants such as Command A Reasoning. Contact sales@cohere.com to use those models in production.",
"source": "ratelimits",
"quote": "Prod keys work like trial keys for newer model variants such as Command A Reasoning. Please contact sales@cohere.com if you intend to use those models in production.",
"sourceUrl": "https://docs.cohere.com/docs/rate-limits"
},
{
"title": "Command A+ production use is via Model Vault",
"detail": "Command A+ is free on trial and production keys until rate limits are reached. For production use, run it through Cohere's Model Vault.",
"source": "commandaplus",
"quote": "Command A+ can be used in production through Cohere's Model Vault.",
"sourceUrl": "https://docs.cohere.com/docs/command-a-plus"
},
{
"title": "Trial keys not for commercial use",
"detail": "Trial keys are rate limited and are not permitted to be used for production or commercial purposes.",
"source": "pricing",
"quote": "trial keys are rate limited and are not permitted to be used for production or commercial purposes.",
"sourceUrl": "https://cohere.com/pricing"
},
{
"title": "Sensitive use cases may be rate limited",
"detail": "If you indicate your usage involves a sensitive use case, your production key may be rate limited the same as a trial key until Cohere's safety team approves it. Reviews take no longer than 72 business hours.",
"source": "golive",
"quote": "if you indicate your usage involves a sensitive use case, your production key may be rate limited the same as a trial key until our safety team reaches out and manually approves your use case.",
"sourceUrl": "https://docs.cohere.com/docs/going-live"
},
{
"title": "Billed tokens can differ from total tokens",
"detail": "Chat responses report both total tokens and billed tokens. Tokens that Cohere adds under the hood, or special tokens the model is trained to output, are not charged.",
"source": "pricingdocs",
"quote": "Since these are tokens you don't have control over, you are not charged for them.",
"sourceUrl": "https://docs.cohere.com/docs/how-does-cohere-pricing-work"
},
{
"title": "Production key requires Owner and application",
"detail": "Getting a Production key requires Owner privileges and completing the Go to Production workflow. Organizations do not get Production key access automatically.",
"source": "pricing",
"quote": "Organizations are not automatically given Production API key access, and a member of the organization must still fill out our application form for production access.",
"sourceUrl": "https://cohere.com/pricing"
}
]
},
{
"id": "cerebras",
"name": "Cerebras Inference",
"vendor": "Cerebras",
"category": "llm-api",
"url": "https://www.cerebras.ai",
"checked": "2026-10-30",
"sources": {
"pricing": {
"name": "Cerebras Inference Pricing | API and Enterprise Plans",
"url": "https://www.cerebras.ai/pricing"
},
"ratelimits": {
"name": "Rate Limits",
"url": "https://inference-docs.cerebras.ai/support/rate-limits"
},
"models": {
"name": "Model Catalog",
"url": "https://inference-docs.cerebras.ai/models/overview.md"
},
"gptoss": {
"name": "OpenAI GPT OSS",
"url": "https://inference-docs.cerebras.ai/models/openai-oss.md"
},
"qwen": {
"name": "Qwen 3.8 27B",
"url": "https://inference-docs.cerebras.ai/models/qwen-3.8-27b.md"
},
"caching": {
"name": "Prompt Caching",
"url": "https://inference-docs.cerebras.ai/capabilities/prompt-caching.md"
},
"batch": {
"name": "Batch",
"url": "https://inference-docs.cerebras.ai/capabilities/batch.md"
}
},
"unit": {
"tag": "Per 1M tokens",
"definition": "Price per million input tokens and per million output tokens, per model (Developer pricing).",
"source": "gptoss",
"quote": "Pricing: $0.35 per million input tokens, $0.75 per million output tokens."
},
"free": {
"summary": "Free Trial: one-time $5 credit after adding a verified payment method, expiring 30 days after it is granted, usable on all public models. No permanently free tier.",
"published": true,
"source": "ratelimits",
"quote": "New accounts receive **\\$5 in free credits** after adding a verified payment method. These credits expire 30 days after they're granted and can be used across all public models."
},
"plans": [
{
"id": "free-trial",
"name": "Free Trial",
"priceUsd": 0,
"priceNote": "One-time $5 promotional credit; expires 30 days after activation",
"billing": "usage",
"included": "$5 in credits usable on all Shared Inference models, subject to Free Trial rate limits. For development, evaluation, and experimentation; not intended for production use.",
"source": "pricing",
"quote": "Add a valid payment method to receive a one-time $5 promotional credit. The credit expires 30 days after activation. You will not be charged or automatically enrolled in paid usage.",
"sourceUrl": "https://www.cerebras.ai/pricing"
},
{
"id": "developer",
"name": "Developer (Pay as You Go)",
"priceUsd": null,
"priceNote": "Per-token pricing per model; credits purchased from the Billing tab",
"billing": "usage",
"included": "Higher per-model rate limits; no hourly or daily token caps.",
"source": "ratelimits",
"quote": "Your first purchase moves you to the Developer tier with significantly higher rate limits and no hourly or daily token caps.",
"sourceUrl": "https://inference-docs.cerebras.ai/support/rate-limits"
},
{
"id": "enterprise",
"name": "Enterprise",
"priceUsd": null,
"priceNote": "Contact sales",
"billing": "usage",
"included": "Rate limits provisioned per organization based on usage profile; custom pricing, dedicated support.",
"source": "ratelimits",
"quote": "Enterprise rate limits are provisioned per organization based on your usage profile.",
"sourceUrl": "https://inference-docs.cerebras.ai/support/rate-limits"
}
],
"rates": [
{
"item": "gpt-oss-120b input per 1M tokens",
"value": "$0.35",
"numeric": 0.35,
"unit": "USD/1M tokens",
"published": true,
"source": "gptoss",
"quote": "Pricing: $0.35 per million input tokens, $0.75 per million output tokens.",
"verified": true,
"sourceUrl": "https://inference-docs.cerebras.ai/models/openai-oss.md"
},
{
"item": "gpt-oss-120b output per 1M tokens",
"value": "$0.75",
"numeric": 0.75,
"unit": "USD/1M tokens",
"published": true,
"source": "gptoss",
"quote": "Pricing: $0.35 per million input tokens, $0.75 per million output tokens.",
"verified": true,
"sourceUrl": "https://inference-docs.cerebras.ai/models/openai-oss.md"
},
{
"item": "qwen-3.8-27b input per 1M tokens",
"value": "$0.99",
"numeric": 0.99,
"unit": "USD/1M tokens",
"published": true,
"source": "qwen",
"quote": "Pricing: $0.99 per million input tokens and $1.49 per million output tokens.",
"verified": true,
"sourceUrl": "https://inference-docs.cerebras.ai/models/qwen-3.8-27b.md"
},
{
"item": "qwen-3.8-27b output per 1M tokens",
"value": "$1.49",
"numeric": 1.49,
"unit": "USD/1M tokens",
"published": true,
"source": "qwen",
"quote": "Pricing: $0.99 per million input tokens and $1.49 per million output tokens.",
"verified": true,
"sourceUrl": "https://inference-docs.cerebras.ai/models/qwen-3.8-27b.md"
},
{
"item": "Cached input price",
"value": "Same as standard input rate; no additional fee for prompt caching",
"unit": "USD/1M tokens",
"published": true,
"source": "caching",
"quote": "Input tokens, whether served from the cache or processed fresh, are billed at the standard input token rate for the respective model.",
"verified": true,
"sourceUrl": "https://inference-docs.cerebras.ai/capabilities/prompt-caching.md"
},
{
"item": "Batch discount",
"value": "Batch is in Private Preview; no batch price or discount stated",
"published": false,
"source": "batch",
"quote": "This feature is in [Private Preview](https://inference-docs.cerebras.ai/support/preview-releases.md).",
"verified": true,
"sourceUrl": "https://inference-docs.cerebras.ai/capabilities/batch.md"
},
{
"item": "gpt-oss-120b context window (Free / Paid)",
"value": "65k / 131k tokens",
"unit": "tokens",
"published": true,
"source": "models",
"quote": "| `gpt-oss-120b` | 120 billion | 65k / 131k | \\~3000 |",
"verified": true,
"sourceUrl": "https://inference-docs.cerebras.ai/models/overview.md"
},
{
"item": "gpt-oss-120b max output (Free / Paid)",
"value": "32k / 40k tokens",
"unit": "tokens",
"published": true,
"source": "gptoss",
"quote": "Max output: 32k tokens (free tier), 40k tokens (paid).",
"verified": true,
"sourceUrl": "https://inference-docs.cerebras.ai/models/openai-oss.md"
},
{
"item": "qwen-3.8-27b context window (Free / Paid)",
"value": "65,536 / 131,072 tokens",
"numeric": 131072,
"unit": "tokens",
"published": true,
"source": "qwen",
"quote": "Context window: 64K tokens (65,536) for Free Trial and 128K tokens (131,072) for paid tiers and trial customers.",
"verified": true,
"sourceUrl": "https://inference-docs.cerebras.ai/models/qwen-3.8-27b.md"
},
{
"item": "qwen-3.8-27b max output (Free / Paid)",
"value": "32,768 / 40,960 tokens",
"numeric": 40960,
"unit": "tokens",
"published": true,
"source": "qwen",
"quote": "Maximum output: 32K tokens (32,768) for Free Trial and 40K tokens (40,960) for paid tiers and trial customers.",
"verified": true,
"sourceUrl": "https://inference-docs.cerebras.ai/models/qwen-3.8-27b.md"
},
{
"item": "Free Trial gpt-oss-120b: RPM / Uncached TPM / Total TPM / TPH / TPD",
"value": "5 RPM / 30K / 90K / 1M / 1M",
"unit": "requests, tokens",
"published": true,
"source": "ratelimits",
"quote": "| `gpt-oss-120b` | 5 | 30K | 90K | 1M | 1M |",
"verified": true,
"sourceUrl": "https://inference-docs.cerebras.ai/support/rate-limits"
},
{
"item": "Free Trial qwen-3.8-27b: RPM / Uncached TPM / Total TPM / TPH / TPD",
"value": "5 RPM / 30K / 90K / 1M / 1M",
"unit": "requests, tokens",
"published": true,
"source": "ratelimits",
"quote": "| `qwen-3.8-27b`1 | 5 | 30K | 90K | 1M | 1M |",
"verified": true,
"sourceUrl": "https://inference-docs.cerebras.ai/support/rate-limits"
},
{
"item": "Developer gpt-oss-120b: Uncached TPM / Total TPM / RPM",
"value": "1M / 3M / 1K",
"unit": "tokens/min, requests/min",
"published": true,
"source": "ratelimits",
"quote": "| `gpt-oss-120b` | 1M | 3M | 1K |",
"verified": true,
"sourceUrl": "https://inference-docs.cerebras.ai/support/rate-limits"
},
{
"item": "Developer qwen-3.8-27b: Uncached TPM / Total TPM / RPM",
"value": "150K / 750K (temporarily increased from 450K) / 300",
"unit": "tokens/min, requests/min",
"published": true,
"source": "ratelimits",
"quote": "| `qwen-3.8-27b`1 | 150K | 750K2 | 300 |",
"verified": true,
"sourceUrl": "https://inference-docs.cerebras.ai/support/rate-limits"
},
{
"item": "Developer hourly/daily token limits",
"value": "Hourly and daily restrictions don't apply to Developer (Pay as You Go)",
"published": true,
"source": "ratelimits",
"quote": "Hourly and daily restrictions don't apply to Developer (Pay as You Go) tier users.",
"verified": true,
"sourceUrl": "https://inference-docs.cerebras.ai/support/rate-limits"
},
{
"item": "Developer tier unlock",
"value": "First credit purchase (Pay as You Go); no minimum amount stated",
"published": false,
"source": "ratelimits",
"quote": "Your first purchase moves you to the Developer tier with significantly higher rate limits and no hourly or daily token caps.",
"verified": true,
"sourceUrl": "https://inference-docs.cerebras.ai/support/rate-limits"
},
{
"item": "Enterprise rate limits",
"value": "Provisioned per organization based on usage profile",
"published": false,
"source": "ratelimits",
"quote": "Enterprise rate limits are provisioned per organization based on your usage profile.",
"verified": true,
"sourceUrl": "https://inference-docs.cerebras.ai/support/rate-limits"
}
],
"overage": {
"policy": "not published",
"summary": "Usage is paid by purchasing credits (Pay as You Go); Developer users can use as many tokens as needed within their budget. Free Trial access stops when credits are used up or expire until credits are purchased.",
"source": "ratelimits",
"quote": "You can use as many tokens as needed within your budget."
},
"gotchas": [
{
"title": "Free Trial access stops at credit exhaustion or expiry",
"detail": "API and Playground access stop on the Free Trial tier until you purchase credits.",
"source": "ratelimits",
"quote": "API and Playground access stop on the Free Trial tier until you purchase credits.",
"sourceUrl": "https://inference-docs.cerebras.ai/support/rate-limits"
},
{
"title": "Free Trial has smaller context and output",
"detail": "Free Trial context windows are about 64k-65k tokens and max output 32k, versus about 128k-131k context and 40k output on paid tiers.",
"source": "models",
"quote": "| `gpt-oss-120b` | 120 billion | 65k / 131k | \\~3000 |",
"sourceUrl": "https://inference-docs.cerebras.ai/models/overview.md"
},
{
"title": "Max completion tokens counted up front against rate limits",
"detail": "Requests are rate limited using estimated input tokens plus max_completion_tokens (or an estimated upper bound) before processing.",
"source": "ratelimits",
"quote": "If this estimated token consumption would exceed your available token quota, the request is rate limited before processing begins.",
"sourceUrl": "https://inference-docs.cerebras.ai/support/rate-limits"
},
{
"title": "Dual-bucket rate limits",
"detail": "Each organization has an uncached TPM limit and a total TPM limit (default 3x uncached); cached tokens count only toward the total limit.",
"source": "ratelimits",
"quote": "Cerebras uses a **dual-bucket model**: every organization has both an **uncached token limit** and a **total token limit**.",
"sourceUrl": "https://inference-docs.cerebras.ai/support/rate-limits"
},
{
"title": "Image input limits on qwen-3.8-27b",
"detail": "Up to 2 images per request on Free Trial and 10 on Developer and Enterprise Shared Inference, with a 10 MiB maximum request payload.",
"source": "qwen",
"quote": "Maximum images per request: 2 for Free Trial, 10 for Developer and Enterprise accounts using Shared Inference.",
"sourceUrl": "https://inference-docs.cerebras.ai/models/qwen-3.8-27b.md"
},
{
"title": "Reasoning on by default",
"detail": "qwen-3.8-27b reasoning defaults to high; gpt-oss-120b default reasoning effort is medium.",
"source": "qwen",
"quote": "Reasoning defaults to `high`. Set `reasoning_effort` to `none` to disable it.",
"sourceUrl": "https://inference-docs.cerebras.ai/models/qwen-3.8-27b.md"
},
{
"title": "Free Trial not for production",
"detail": "Free Trial is for development, evaluation, and experimentation; not intended for production use.",
"source": "pricing",
"quote": "For development, evaluation, and experimentation; not intended for production use.",
"sourceUrl": "https://www.cerebras.ai/pricing"
},
{
"title": "Batch results deleted after 7 days",
"detail": "Batch results are retained for 7 days after completion, then automatically deleted; only completed requests are charged.",
"source": "batch",
"quote": "Results retained for 7 days after completion",
"sourceUrl": "https://inference-docs.cerebras.ai/capabilities/batch.md"
}
]
}
]
}