{
  "verified": "2026-11-04",
  "sources": [
    {
      "name": "OpenRouter models API",
      "url": "https://openrouter.ai/api/v1/models",
      "type": "api",
      "observes": "free models appear/disappear - filter pricing.prompt == 0"
    },
    {
      "name": "Vercel AI Gateway models API",
      "url": "https://ai-gateway.vercel.sh/v1/models",
      "type": "api",
      "observes": "zero-priced models - filter pricing.input == 0"
    },
    {
      "name": "Cloudflare Workers AI catalog",
      "url": "https://developers.cloudflare.com/workers-ai/models/",
      "type": "docs",
      "observes": "open-weight model catalog"
    },
    {
      "name": "Groq models docs",
      "url": "https://console.groq.com/docs/models",
      "type": "docs",
      "observes": "model list"
    },
    {
      "name": "Google AI Studio rate limits",
      "url": "https://aistudio.google.com/docs/rate-limits",
      "type": "docs",
      "observes": "free-tier models + limits"
    },
    {
      "name": "NVIDIA build catalog",
      "url": "https://build.nvidia.com/explore/discover",
      "type": "docs",
      "observes": "model catalog"
    },
    {
      "name": "Mistral models docs",
      "url": "https://docs.mistral.ai/models",
      "type": "docs",
      "observes": "model list"
    },
    {
      "name": "Cohere models docs",
      "url": "https://docs.cohere.com/docs/models",
      "type": "docs",
      "observes": "model list"
    },
    {
      "name": "Cerebras models docs",
      "url": "https://inference-docs.cerebras.ai/models",
      "type": "docs",
      "observes": "model list + free-tier context caps"
    },
    {
      "name": "free-llm-api-resources (GitHub)",
      "url": "https://github.com/raullenchai/free-llm-api-resources",
      "type": "repo",
      "observes": "community signal - commits flag landscape changes"
    }
  ],
  "providers": [
    {
      "name": "Google AI Studio",
      "url": "https://aistudio.google.com/",
      "docs": "https://aistudio.google.com/docs/rate-limits",
      "limits_short": "~1,500 req/day (Flash)",
      "limits_detail": "Most generous permanent free tier. Per-model daily request caps (≈1,500/day for Flash-class); up to 1M token context. No card required. Exact per-model limits shown in your AI Studio rate-limit page.",
      "free_until": {
        "type": "ongoing",
        "detail": "No announced end date; limits change without notice."
      },
      "caveats": [
        {
          "flag": "training",
          "text": "Free-tier prompts may be used to improve Google products - don't send sensitive data."
        }
      ],
      "models": [
        {
          "name": "Gemini 3.8 Flash",
          "context": "1M",
          "added": "2026-11-04",
          "caps": [
            "vision"
          ],
          "released": "2026-09"
        },
        {
          "name": "Gemini 3.6 Flash",
          "context": "1M",
          "added": "2026-11-04",
          "caps": [
            "vision"
          ],
          "released": "2026-07"
        },
        {
          "name": "Gemini 3.5 Flash-Lite",
          "context": "1M",
          "added": "2026-11-04",
          "caps": [
            "vision"
          ],
          "released": "2026-07"
        },
        {
          "name": "Gemini 3.1 Flash-Lite",
          "context": "1M",
          "added": "2026-11-04",
          "caps": [
            "vision"
          ],
          "released": "2026-05"
        },
        {
          "name": "Gemini 2.5 Pro",
          "context": "1M",
          "added": "2026-11-04",
          "caps": [
            "vision"
          ],
          "released": "2025-06"
        },
        {
          "name": "Gemini 2.5 Flash",
          "context": "1M",
          "added": "2026-11-04",
          "caps": [
            "vision"
          ],
          "released": "2025-06"
        }
      ],
      "api": {
        "base_url": "https://generativelanguage.googleapis.com/v1beta/openai/",
        "openai_compatible": true
      },
      "tier": {
        "volume": 4.0
      }
    },
    {
      "name": "Groq",
      "url": "https://console.groq.com/",
      "docs": "https://console.groq.com/docs/rate-limits",
      "limits_short": "1k req/day · 8k tok/min",
      "limits_detail": "Free plan: 30 req/min, 1,000 req/day, 8k tokens/min, 200k tokens/day (per organization). Cached tokens don't count. Fastest free inference available.",
      "free_until": {
        "type": "ongoing",
        "detail": "No announced end date."
      },
      "caveats": [
        {
          "flag": "low_tpm",
          "text": "Tokens-per-minute cap is tight - fine for chat, throttles bulk work."
        }
      ],
      "models": [
        {
          "name": "gpt-oss-120b",
          "context": "131k",
          "added": "2026-11-04",
          "caps": [
            "reasoning"
          ],
          "released": "2025-08"
        },
        {
          "name": "gpt-oss-20b",
          "context": "131k",
          "added": "2026-11-04",
          "caps": [
            "reasoning"
          ],
          "released": "2025-08"
        },
        {
          "name": "qwen3.8-27b",
          "context": "131k",
          "added": "2026-11-04",
          "caps": [
            "vision"
          ],
          "released": "2026-08"
        },
        {
          "name": "whisper-large-v3 (audio)",
          "context": null,
          "added": "2026-11-04",
          "caps": [
            "audio"
          ],
          "released": "2023-11"
        }
      ],
      "api": {
        "base_url": "https://api.groq.com/openai/v1",
        "openai_compatible": true
      },
      "tier": {
        "volume": 3.5
      }
    },
    {
      "name": "OpenRouter (:free)",
      "url": "https://openrouter.ai/models?max_price=0",
      "docs": "https://openrouter.ai/docs/api_reference/limits",
      "limits_short": "20 rpm · 50 req/day",
      "limits_detail": "16 models with ':free' IDs right now (live count via openrouter.ai/api/v1/models, filter price 0). 20 req/min, 50 req/day - rises to 1,000 req/day once you have ever bought $10 of credits (no need to spend them).",
      "free_until": {
        "type": "ongoing",
        "detail": "No announced end date; individual free models appear and disappear."
      },
      "caveats": [
        {
          "flag": "failed_count",
          "text": "Failed requests count against your daily cap."
        },
        {
          "flag": "training",
          "text": "Some free-model providers may train on your prompts."
        }
      ],
      "models": [
        {
          "name": "nvidia/nemotron-3.5-super-vl:free",
          "context": "1M",
          "added": "2026-11-04",
          "caps": [
            "vision"
          ],
          "released": "2026-10",
          "url": "https://openrouter.ai/nvidia/nemotron-3.5-super-vl"
        },
        {
          "name": "nvidia/nemotron-3.5-lightning:free",
          "context": "1M",
          "added": "2026-11-04",
          "caps": [],
          "released": "2026-08",
          "url": "https://openrouter.ai/nvidia/nemotron-3.5-lightning"
        },
        {
          "name": "nvidia/nemotron-3-ultra-550b-a55b:free",
          "context": "1M",
          "added": "2026-11-04",
          "caps": [],
          "released": "2026-06",
          "url": "https://openrouter.ai/nvidia/nemotron-3-ultra-550b-a55b"
        },
        {
          "name": "dots-studio/dots-3-note-preview:free",
          "context": "500k",
          "added": "2026-11-04",
          "caps": [
            "vision"
          ],
          "released": "2026-08",
          "url": "https://openrouter.ai/dots-studio/dots-3-note-preview"
        },
        {
          "name": "google/gemma-4-31b-it:free",
          "context": "256k",
          "added": "2026-11-04",
          "caps": [
            "vision"
          ],
          "released": "2026-04",
          "url": "https://openrouter.ai/google/gemma-4-31b-it"
        },
        {
          "name": "google/gemma-4-26b-a4b-it:free",
          "context": "256k",
          "added": "2026-11-04",
          "caps": [
            "vision"
          ],
          "released": "2026-04",
          "url": "https://openrouter.ai/google/gemma-4-26b-a4b-it"
        },
        {
          "name": "xingchen-agi/xing4.0-29b-a4b:free",
          "context": "256k",
          "added": "2026-11-04",
          "caps": [],
          "released": "2026-10",
          "url": "https://openrouter.ai/xingchen-agi/xing4.0-29b-a4b"
        },
        {
          "name": "recursive/flint-v1.0:free",
          "context": "256k",
          "added": "2026-11-04",
          "caps": [],
          "released": "2026-10",
          "url": "https://openrouter.ai/recursive/flint-v1.0"
        },
        {
          "name": "cohere/north-mini-code:free",
          "context": "250k",
          "added": "2026-11-04",
          "caps": [
            "code"
          ],
          "released": "2026-06",
          "url": "https://openrouter.ai/cohere/north-mini-code"
        },
        {
          "name": "liquid/lfm-2.5-2.6b:free",
          "context": "64k",
          "added": "2026-11-04",
          "caps": [],
          "released": "2026-08",
          "url": "https://openrouter.ai/liquid/lfm-2.5-2.6b"
        },
        {
          "name": "openrouter/free (auto-router)",
          "context": "195k",
          "added": "2026-11-04",
          "caps": [
            "vision"
          ],
          "released": "2026-02",
          "url": "https://openrouter.ai/openrouter/free"
        },
        {
          "name": "stealth/crouton-alpha",
          "context": "1.04858M",
          "added": "2026-11-04",
          "caps": [
            "omni"
          ],
          "released": "2026-11",
          "url": "https://openrouter.ai/stealth/crouton-alpha"
        },
        {
          "name": "nvidia/nemotron-3.5-content-safety:free",
          "context": "125k",
          "added": "2026-11-04",
          "caps": [
            "vision"
          ],
          "released": "2026-06",
          "url": "https://openrouter.ai/nvidia/nemotron-3.5-content-safety"
        },
        {
          "name": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free",
          "context": "250k",
          "added": "2026-11-04",
          "caps": [
            "omni",
            "reasoning"
          ],
          "released": "2026-04",
          "url": "https://openrouter.ai/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning"
        },
        {
          "name": "google/lyria-3-pro-preview",
          "context": "1.04858M",
          "added": "2026-11-04",
          "caps": [
            "vision"
          ],
          "released": "2026-03",
          "url": "https://openrouter.ai/google/lyria-3-pro-preview"
        },
        {
          "name": "google/lyria-3-clip-preview",
          "context": "1.04858M",
          "added": "2026-11-04",
          "caps": [
            "vision"
          ],
          "released": "2026-03",
          "url": "https://openrouter.ai/google/lyria-3-clip-preview"
        }
      ],
      "api": {
        "base_url": "https://openrouter.ai/api/v1",
        "openai_compatible": true
      },
      "tier": {
        "volume": 2.0
      }
    },
    {
      "name": "Cloudflare Workers AI",
      "url": "https://developers.cloudflare.com/workers-ai/",
      "docs": "https://developers.cloudflare.com/workers-ai/platform/pricing/",
      "limits_short": "10k neurons/day",
      "limits_detail": "10,000 neurons per day on the Workers Free plan (resets 00:00 UTC); overage $0.011 per 1,000 neurons. Frontier models (Kimi K2.6, GLM 5.x, recent DeepSeek V4 Flash) require a paid plan; the models below are the open-weight catalog.",
      "free_until": {
        "type": "ongoing",
        "detail": "Permanent part of the Workers Free plan."
      },
      "caveats": [],
      "models": [
        {
          "name": "llama-3.3-70b-instruct-fp8-fast",
          "context": null,
          "added": "2026-11-04",
          "caps": [],
          "url": "https://developers.cloudflare.com/workers-ai/models/llama-3.3-70b-instruct-fp8-fast",
          "released": "2024-12"
        },
        {
          "name": "llama-4-scout-17b-16e-instruct",
          "context": null,
          "added": "2026-11-04",
          "caps": [
            "vision"
          ],
          "url": "https://developers.cloudflare.com/workers-ai/models/llama-4-scout-17b-16e-instruct",
          "released": "2025-04"
        },
        {
          "name": "qwen3-30b-a3b-fp8",
          "context": null,
          "added": "2026-11-04",
          "caps": [],
          "url": "https://developers.cloudflare.com/workers-ai/models/qwen3-30b-a3b-fp8",
          "released": "2025-04"
        },
        {
          "name": "qwen3.8-27b",
          "context": null,
          "added": "2026-11-04",
          "caps": [
            "vision"
          ],
          "url": "https://developers.cloudflare.com/workers-ai/models/qwen3.8-27b",
          "released": "2026-08"
        },
        {
          "name": "qwen2.5-coder-32b-instruct",
          "context": null,
          "added": "2026-11-04",
          "caps": [
            "code"
          ],
          "url": "https://developers.cloudflare.com/workers-ai/models/qwen2.5-coder-32b-instruct",
          "released": "2024-11"
        },
        {
          "name": "gpt-oss-120b",
          "context": null,
          "added": "2026-11-04",
          "caps": [
            "reasoning"
          ],
          "released": "2025-08",
          "url": "https://developers.cloudflare.com/workers-ai/models/gpt-oss-120b"
        },
        {
          "name": "gpt-oss-20b",
          "context": null,
          "added": "2026-11-04",
          "caps": [
            "reasoning"
          ],
          "released": "2025-08",
          "url": "https://developers.cloudflare.com/workers-ai/models/gpt-oss-20b"
        },
        {
          "name": "gemma-4-26b-a4b-it",
          "context": null,
          "added": "2026-11-04",
          "caps": [
            "vision"
          ],
          "url": "https://developers.cloudflare.com/workers-ai/models/gemma-4-26b-a4b-it",
          "released": "2026-04"
        },
        {
          "name": "mistral-small-3.1-24b-instruct",
          "context": "128k",
          "added": "2026-11-04",
          "caps": [
            "vision"
          ],
          "url": "https://developers.cloudflare.com/workers-ai/models/mistral-small-3.1-24b-instruct",
          "released": "2025-03"
        },
        {
          "name": "deepseek-r1-distill-qwen-32b",
          "context": null,
          "added": "2026-11-04",
          "caps": [
            "reasoning"
          ],
          "released": "2025-01",
          "url": "https://developers.cloudflare.com/workers-ai/models/deepseek-r1-distill-qwen-32b"
        },
        {
          "name": "glm-4.7-flash",
          "context": "131k",
          "added": "2026-11-04",
          "caps": [],
          "url": "https://developers.cloudflare.com/workers-ai/models/glm-4.7-flash",
          "released": "2026-01"
        }
      ],
      "api": {
        "base_url": "https://api.cloudflare.com/client/v4/accounts/{account}/ai/run/",
        "openai_compatible": false
      },
      "tier": {
        "volume": 2.5
      }
    },
    {
      "name": "NVIDIA NIM",
      "url": "https://build.nvidia.com/",
      "docs": "https://build.nvidia.com/",
      "limits_short": "unpublished",
      "limits_detail": "Free inference on build.nvidia.com with no published quota - intended for evaluation, 'limits can change' at any time.",
      "free_until": {
        "type": "ongoing",
        "detail": "Ongoing, but explicitly evaluation-only."
      },
      "caveats": [
        {
          "flag": "eval",
          "text": "Evaluation only - not meant as a production dependency."
        }
      ],
      "models": [
        {
          "name": "nemotron-3-ultra-550b-a55b",
          "context": null,
          "added": "2026-11-04",
          "caps": [],
          "released": "2026-06"
        },
        {
          "name": "nemotron-3.5-super-vl-120b-a12b",
          "context": null,
          "added": "2026-11-04",
          "caps": [
            "vision"
          ],
          "released": "2026-10"
        },
        {
          "name": "nemotron-3.5-lightning-30b-a3b",
          "context": null,
          "added": "2026-11-04",
          "caps": [],
          "released": "2026-08"
        },
        {
          "name": "deepseek-v4.1-flash",
          "context": null,
          "added": "2026-11-04",
          "caps": [
            "vision"
          ],
          "released": "2026-09"
        }
      ],
      "api": {
        "base_url": "https://integrate.api.nvidia.com/v1",
        "openai_compatible": true
      },
      "tier": {
        "volume": 2.0
      }
    },
    {
      "name": "Mistral La Plateforme",
      "url": "https://console.mistral.ai/",
      "docs": "https://docs.mistral.ai/models",
      "limits_short": "per-model (see docs)",
      "limits_detail": "Free tier on registration with per-model rate limits; Codestral has a dedicated free endpoint for coding. Exact limits vary per model - check the docs.",
      "free_until": {
        "type": "ongoing",
        "detail": "No announced end date."
      },
      "caveats": [],
      "models": [
        {
          "name": "mistral-large-4",
          "context": null,
          "added": "2026-11-04",
          "caps": [
            "vision"
          ],
          "released": "2026-10"
        },
        {
          "name": "mistral-small-4",
          "context": null,
          "added": "2026-11-04",
          "caps": [
            "reasoning"
          ],
          "released": "2026-03"
        },
        {
          "name": "ministral-3-14b",
          "context": null,
          "added": "2026-11-04",
          "caps": [],
          "released": "2025-12"
        },
        {
          "name": "codestral (v25.08)",
          "context": null,
          "added": "2026-11-04",
          "caps": [
            "code"
          ],
          "released": "2025-08"
        },
        {
          "name": "glm-5.3-flash (3rd-party)",
          "context": "1M",
          "added": "2026-11-04",
          "caps": [
            "vision"
          ],
          "released": "2026-08"
        }
      ],
      "api": {
        "base_url": "https://api.mistral.ai/v1",
        "openai_compatible": true
      },
      "tier": {
        "volume": 2.5
      }
    },
    {
      "name": "Vercel AI Gateway",
      "url": "https://vercel.com/ai-gateway",
      "docs": "https://ai-gateway.vercel.sh/v1/models",
      "limits_short": "$5 credit / month",
      "limits_detail": "$5 of gateway credit per month, refreshing monthly. Several models are zero-priced (cost nothing, credit untouched); the rest draw down the credit. Live list: GET ai-gateway.vercel.sh/v1/models, filter price 0 (also free: several transcription models).",
      "free_until": {
        "type": "ongoing",
        "detail": "Ongoing - the $5 credit refreshes every month."
      },
      "caveats": [],
      "models": [
        {
          "name": "nvidia/nemotron-3.5-lightning-free",
          "context": "1M",
          "added": "2026-11-04",
          "caps": [],
          "released": "2026-10"
        },
        {
          "name": "reflection/beam-free",
          "context": "1.04858M",
          "added": "2026-11-04",
          "caps": [],
          "released": "2026-10"
        },
        {
          "name": "stealth/glyph-cluster",
          "context": "250k",
          "added": "2026-11-04",
          "caps": [],
          "released": "2026-10"
        },
        {
          "name": "reflection/beam",
          "context": "1.04858M",
          "added": "2026-11-04",
          "caps": [],
          "released": "2026-10"
        }
      ],
      "api": {
        "base_url": "https://ai-gateway.vercel.sh/v1",
        "openai_compatible": true
      },
      "tier": {
        "volume": 3.0
      }
    },
    {
      "name": "Cerebras",
      "url": "https://cloud.cerebras.ai/",
      "docs": "https://inference-docs.cerebras.ai/models",
      "limits_short": "$5 trial credits",
      "limits_detail": "$5 of credits - requires adding a verified payment method, expires 30 days after signup. Shared inference free tier halves context windows (65k vs 131k paid). Extremely fast inference while it lasts.",
      "free_until": {
        "type": "relative",
        "detail": "Credits expire 30 days after signup."
      },
      "caveats": [
        {
          "flag": "card",
          "text": "Verified payment method required."
        },
        {
          "flag": "trial",
          "text": "Trial credits, not a permanent free tier."
        }
      ],
      "models": [
        {
          "name": "gpt-oss-120b",
          "context": "65k",
          "added": "2026-11-04",
          "caps": [
            "reasoning"
          ],
          "released": "2025-08"
        },
        {
          "name": "qwen-3.8-27b",
          "context": "64k",
          "added": "2026-11-04",
          "caps": [
            "vision"
          ],
          "released": "2026-08"
        }
      ],
      "api": {
        "base_url": "https://api.cerebras.ai/v1",
        "openai_compatible": true
      },
      "tier": {
        "volume": 1.5
      }
    },
    {
      "name": "Cohere",
      "url": "https://dashboard.cohere.com/",
      "docs": "https://docs.cohere.com/docs/models",
      "limits_short": "1k calls / month",
      "limits_detail": "Trial keys: 1,000 API calls per month, evaluation only, not for production.",
      "free_until": {
        "type": "ongoing",
        "detail": "Trial program, ongoing but capped."
      },
      "caveats": [
        {
          "flag": "eval",
          "text": "Evaluation only - not for production."
        }
      ],
      "models": [
        {
          "name": "command-a-03-2025",
          "context": "256k",
          "added": "2026-11-04",
          "caps": [],
          "released": "2025-03"
        },
        {
          "name": "command-a-plus-05-2026",
          "context": "128k",
          "added": "2026-11-04",
          "caps": [
            "vision"
          ],
          "released": "2026-05"
        },
        {
          "name": "command-a-reasoning-08-2025",
          "context": "256k",
          "added": "2026-11-04",
          "caps": [
            "reasoning"
          ],
          "released": "2025-08"
        },
        {
          "name": "command-r7b-12-2024",
          "context": "128k",
          "added": "2026-11-04",
          "caps": [],
          "released": "2024-12"
        },
        {
          "name": "north-mini-code-1.0",
          "context": "256k",
          "added": "2026-11-04",
          "caps": [
            "code"
          ],
          "released": "2026-06"
        }
      ],
      "api": {
        "base_url": "https://api.cohere.com/v2",
        "openai_compatible": false
      },
      "tier": {
        "volume": 1.5
      }
    }
  ],
  "changelog": [
    {
      "date": "2026-11-04",
      "text": "auto-update via provider APIs: 6 models added, 1 removed.",
      "source": null
    },
    {
      "date": "2026-11-04",
      "text": "Model lists replaced with concrete live data: OpenRouter models API (16 ':free'), Vercel gateway API (3 zero-price), NVIDIA / Cerebras / Cohere / Mistral / Cloudflare official docs.",
      "source": null
    },
    {
      "date": "2026-11-04",
      "text": "First snapshot: 9 providers tracked, all entries verified today.",
      "source": null
    },
    {
      "date": "2026-10-01",
      "text": "Hugging Face Inference Providers no longer offer free monthly credits - free accounts get nothing, PRO gets $2/month.",
      "source": {
        "label": "flatkey.ai",
        "url": "https://flatkey.ai/blog/free-llm-apis-2026"
      }
    },
    {
      "date": "2026-07-30",
      "text": "GitHub Models retired: playground, model catalog, inference API and BYOK shut down entirely.",
      "source": {
        "label": "github.blog",
        "url": "https://github.blog/changelog/2026-07-30-github-models-is-now-retired"
      }
    },
    {
      "date": "2026",
      "text": "Cerebras free access became trial-only: $5 credits, verified card required, 30-day expiry (date approximate).",
      "source": {
        "label": "flatkey.ai",
        "url": "https://flatkey.ai/blog/free-llm-apis-2026"
      }
    }
  ],
  "flag_legend": {
    "training": "Inputs may be used for training",
    "card": "Payment card required",
    "eval": "Evaluation / trial only",
    "low_tpm": "Low tokens-per-minute cap",
    "failed_count": "Failed requests count against limits",
    "trial": "Time-limited credits"
  }
}