LimitsDBv1/llms.txt

ai.model.max_output_tokens

Max output tokens

Maximum tokens generated in a single response

unit
tokens
providers
5
facts
5
highest
OpenAI · 128,000
lowest
DeepSeek · 8,192
providerkeyvalueplanstatusverifiedsource
Anthropicai.model.max_output_tokens64,000 tokens“Maximum output tokens per response”api/standardstale2026-10-04Anthropic models overview
DeepSeekai.model.max_output_tokens8,192 tokens“Default 4k, up to 8k output tokens”api/standardverified2026-10-05DeepSeek pricing
Google AIai.model.max_output_tokens65,536 tokens“65,536 maximum output tokens”gemini-api/paidverified2026-10-04Gemini API models
Mistral AIai.model.max_output_tokens8,192 tokens“Maximum generated tokens per response”api/standardverified2026-10-05Mistral models overview
OpenAIai.model.max_output_tokens128,000 tokens“Maximum output tokens for GPT-5 family”api/standardverified2026-10-06OpenAI models

Agent view

GET /api/public/v1/keys/ai.model.max_output_tokens
{
  "key": "ai.model.max_output_tokens",
  "unit": "tokens",
  "values": [
    {
      "provider": "anthropic",
      "plan": "api/standard",
      "value": 64000,
      "status": "stale",
      "source": "https://docs.anthropic.com/en/docs/about-claude/models"
    },
    {
      "provider": "deepseek",
      "plan": "api/standard",
      "value": 8192,
      "status": "verified",
      "source": "https://api-docs.deepseek.com/quick_start/pricing"
    },
    {
      "provider": "google-ai",
      "plan": "gemini-api/paid",
      "value": 65536,
      "status": "verified",
      "source": "https://ai.google.dev/gemini-api/docs/models"
    },
    {
      "provider": "mistral",
      "plan": "api/standard",
      "value": 8192,
      "status": "verified",
      "source": "https://docs.mistral.ai/getting-started/models/models_overview/"
    },
    {
      "provider": "openai",
      "plan": "api/standard",
      "value": 128000,
      "status": "verified",
      "source": "https://platform.openai.com/docs/models"
    }
  ]
}