LimitsDBv1/llms.txt

ai.model.context_window_tokens

Context window

Maximum input context length

unit
tokens
providers
8
facts
8
highest
Google AI · 1,048,576
lowest
Mistral AI · 128,000
providerkeyvalueplanstatusverifiedsource
Anthropicai.model.context_window_tokens200,000 tokens“200K token context window for Claude models”api/standardstale2026-10-04Anthropic models overview
Cohereai.model.context_window_tokens256,000 tokens“256k context window on Command A”api/productionverified2026-10-05Cohere rate limits
DeepSeekai.model.context_window_tokens131,072 tokens“128k context window on deepseek-chat”api/standardverified2026-10-05DeepSeek pricing
Fireworks AIai.model.context_window_tokens131,072 tokens“131,072 token context window”inference/serverlessverified2026-10-05Fireworks AI pricing
Google AIai.model.context_window_tokens1,048,576 tokens“1,048,576 token input context window”gemini-api/paidverified2026-10-04Gemini API models
Groqai.model.context_window_tokens131,072 tokens“131k context window on Llama 3.3 70B”api/developerstale2026-10-02GroqCloud rate limits
Mistral AIai.model.context_window_tokens128,000 tokens“128k context window on Mistral Large”api/standardverified2026-10-05Mistral models overview
OpenAIai.model.context_window_tokens400,000 tokens“GPT-5 family context window”api/standardverified2026-10-06OpenAI models

Agent view

GET /api/public/v1/keys/ai.model.context_window_tokens
{
  "key": "ai.model.context_window_tokens",
  "unit": "tokens",
  "values": [
    {
      "provider": "anthropic",
      "plan": "api/standard",
      "value": 200000,
      "status": "stale",
      "source": "https://docs.anthropic.com/en/docs/about-claude/models"
    },
    {
      "provider": "cohere",
      "plan": "api/production",
      "value": 256000,
      "status": "verified",
      "source": "https://docs.cohere.com/docs/rate-limits"
    },
    {
      "provider": "deepseek",
      "plan": "api/standard",
      "value": 131072,
      "status": "verified",
      "source": "https://api-docs.deepseek.com/quick_start/pricing"
    },
    {
      "provider": "fireworks-ai",
      "plan": "inference/serverless",
      "value": 131072,
      "status": "verified",
      "source": "https://fireworks.ai/pricing"
    },
    {
      "provider": "google-ai",
      "plan": "gemini-api/paid",
      "value": 1048576,
      "status": "verified",
      "source": "https://ai.google.dev/gemini-api/docs/models"
    },
    {
      "provider": "groq",
      "plan": "api/developer",
      "value": 131072,
      "status": "stale",
      "source": "https://console.groq.com/docs/rate-limits"
    },
    {
      "provider": "mistral",
      "plan": "api/standard",
      "value": 128000,
      "status": "verified",
      "source": "https://docs.mistral.ai/getting-started/models/models_overview/"
    },
    {
      "provider": "openai",
      "plan": "api/standard",
      "value": 400000,
      "status": "verified",
      "source": "https://platform.openai.com/docs/models"
    }
  ]
}