{
  "version": "1.0",
  "updated": "2026-08-31T02:00:40.788515+00:00",
  "sources": [
    "cheahjs/free-llm-api-resources",
    "tashfeenahmed/freellmapi",
    "mnfst/awesome-free-llm-apis",
    "nejib1/Free-LLM",
    "open-free-llm-api/awesome-freellm-apis"
  ],
  "providers": [
    {
      "name": "Agnes AI",
      "slug": "agnes-ai",
      "tier": "permanent_free",
      "website": "https://agnes-ai.com",
      "api_base": "https://apihub.agnes-ai.com/v1",
      "models_endpoint": "/models",
      "requires_key": true,
      "requires_card": false,
      "rate_limit": {
        "rpm": 30,
        "tpm": 500000
      },
      "models": [
        "agnes-image-2.1-flash",
        "agnes-image-2.0-flash",
        "agnes-video-v2.0"
      ],
      "free_models": [
        "agnes-image-2.1-flash",
        "agnes-image-2.0-flash",
        "agnes-video-v2.0"
      ],
      "features": [
        "image_generation",
        "video_generation",
        "image_editing"
      ],
      "region": "global",
      "notes": "Free image/video generation, images 1K: 30/20 RPM, 2K: 20/10 RPM, 3K: 2/1 RPM, 4K: 1/1 RPM; video 2/1 RPM; no credit card required",
      "source": "https://github.com/AgnesAI-Labs/AgnesAI-Models",
      "last_probed": "2026-08-30T10:59:35.940555+00:00",
      "status": "active",
      "context_window": 0,
      "max_output_tokens": 0,
      "function_calling": false,
      "health_score": 70,
      "models_count": 10
    },
    {
      "name": "Agnes AI",
      "slug": "agnes-ai-text",
      "tier": "trial_credit",
      "website": "https://agnes-ai.com",
      "api_base": "https://apihub.agnes-ai.com/v1",
      "models_endpoint": "/models",
      "requires_key": true,
      "requires_card": false,
      "rate_limit": {
        "rpm": 30,
        "actual_rpm": 20,
        "tpm": 500000
      },
      "models": [
        "agnes-2.5-flash",
        "agnes-2.5-pro",
        "agnes-2.0-flash",
        "agnes-1.5-flash"
      ],
      "free_models": [
        "agnes-2.5-flash",
        "agnes-2.0-flash",
        "agnes-1.5-flash"
      ],
      "features": [
        "chat",
        "vision",
        "function_calling",
        "reasoning",
        "tool_calling",
        "agent_workflows"
      ],
      "region": "global",
      "notes": "Free text inference: 30 RPM public / 20 actual RPM; 512K context; supports tool calling, code, reasoning, multi-turn, vision; no credit card; requires Dashboard login for credits",
      "source": "https://github.com/AgnesAI-Labs/AgnesAI-Models",
      "last_probed": "2026-08-30T10:59:36.245558+00:00",
      "status": "active",
      "context_window": 512000,
      "max_output_tokens": 8192,
      "function_calling": true,
      "health_score": 74,
      "models_count": 10
    },
    {
      "name": "Cerebras",
      "slug": "cerebras",
      "tier": "permanent_free",
      "website": "https://cloud.cerebras.ai",
      "api_base": "https://api.cerebras.ai/v1",
      "models_endpoint": "/models",
      "requires_key": true,
      "requires_card": false,
      "rate_limit": {
        "rpm": 30,
        "rpd": 14400,
        "tpd": 1000000
      },
      "models": [
        "llama3.1-8b",
        "llama3.3-70b"
      ],
      "free_models": [
        "llama3.1-8b",
        "llama3.3-70b"
      ],
      "features": [
        "chat"
      ],
      "region": "global",
      "notes": "Wafer-scale hardware, 2600+ tokens/s",
      "source": "https://github.com/cheahjs/free-llm-api-resources",
      "last_probed": "2026-08-30T10:59:35.631613+00:00",
      "status": "degraded",
      "context_window": 8192,
      "max_output_tokens": 8192,
      "function_calling": false,
      "health_score": 65,
      "models_count": 2
    },
    {
      "name": "Cloudflare Workers AI",
      "slug": "cloudflare-workers-ai",
      "tier": "permanent_free",
      "website": "https://developers.cloudflare.com/workers-ai",
      "api_base": "https://api.cloudflare.com/client/v4/accounts/{account_id}/ai",
      "models_endpoint": "/models/search",
      "requires_key": true,
      "requires_card": false,
      "rate_limit": {
        "daily_neurons": 10000
      },
      "models": [
        "@cf/meta/llama-3.1-8b-instruct",
        "@cf/meta/llama-3.3-70b-instruct",
        "@cf/mistral/mistral-7b-instruct-v0.1",
        "@cf/google/gemma-7b-it"
      ],
      "free_models": [
        "@cf/meta/llama-3.1-8b-instruct",
        "@cf/meta/llama-3.3-70b-instruct",
        "@cf/mistral/mistral-7b-instruct-v0.1",
        "@cf/google/gemma-7b-it"
      ],
      "features": [
        "chat",
        "embeddings",
        "vision"
      ],
      "region": "global",
      "notes": "Edge deployment, 10K neurons/day free tier",
      "source": "https://github.com/cheahjs/free-llm-api-resources",
      "last_probed": "2026-08-30T10:59:35.702773+00:00",
      "status": "down",
      "context_window": 8192,
      "max_output_tokens": 4096,
      "function_calling": false,
      "health_score": 70,
      "models_count": 4
    },
    {
      "name": "Cohere",
      "slug": "cohere",
      "tier": "permanent_free",
      "website": "https://dashboard.cohere.com",
      "api_base": "https://api.cohere.ai/v1",
      "models_endpoint": "/models",
      "requires_key": true,
      "requires_card": false,
      "rate_limit": {
        "rpm": 20,
        "monthly_requests": 1000
      },
      "models": [
        "command-a",
        "command-r-plus",
        "command-r",
        "command-light"
      ],
      "free_models": [
        "command-r",
        "command-light"
      ],
      "features": [
        "chat",
        "embeddings",
        "rerank"
      ],
      "region": "global",
      "notes": "Strong RAG/Embedding, 1000 req/month free",
      "source": "https://github.com/cheahjs/free-llm-api-resources",
      "last_probed": "2026-08-30T10:59:35.654171+00:00",
      "status": "active",
      "context_window": 4096,
      "max_output_tokens": 4096,
      "function_calling": false,
      "health_score": 70,
      "models_count": 20
    },
    {
      "name": "DeepSeek",
      "slug": "deepseek",
      "tier": "trial_credit",
      "website": "https://platform.deepseek.com",
      "api_base": "https://api.deepseek.com/v1",
      "models_endpoint": "/models",
      "requires_key": true,
      "requires_card": true,
      "rate_limit": {},
      "models": [
        "deepseek-chat",
        "deepseek-reasoner"
      ],
      "free_models": [
        "deepseek-chat"
      ],
      "features": [
        "chat",
        "reasoning",
        "function_calling"
      ],
      "region": "cn",
      "notes": "Limited free tier, strong coding ability",
      "source": "https://github.com/nejib1/Free-LLM",
      "last_probed": "2026-08-30T10:59:36.168017+00:00",
      "status": "active",
      "context_window": 64000,
      "max_output_tokens": 8192,
      "function_calling": true,
      "health_score": 70
    },
    {
      "name": "Google AI Studio",
      "slug": "google-ai-studio",
      "tier": "permanent_free",
      "website": "https://aistudio.google.com",
      "api_base": "https://generativelanguage.googleapis.com/v1beta",
      "models_endpoint": "/models",
      "requires_key": true,
      "requires_card": false,
      "rate_limit": {
        "rpm": 15,
        "rpd": 1500,
        "tpm": 250000
      },
      "models": [
        "gemini-1.5-flash",
        "gemini-1.5-pro",
        "gemini-2.0-flash-exp"
      ],
      "free_models": [
        "gemini-1.5-flash",
        "gemini-2.0-flash-exp"
      ],
      "features": [
        "chat",
        "vision",
        "function_calling",
        "embeddings"
      ],
      "region": "global",
      "notes": "Requires Google account, good Chinese support, strong multimodal",
      "source": "https://github.com/cheahjs/free-llm-api-resources",
      "last_probed": "2026-08-30T10:59:35.707781+00:00",
      "status": "degraded",
      "context_window": 2000000,
      "max_output_tokens": 8192,
      "function_calling": true,
      "health_score": 52,
      "models_count": 50
    },
    {
      "name": "Groq",
      "slug": "groq",
      "tier": "permanent_free",
      "website": "https://console.groq.com",
      "api_base": "https://api.groq.com/openai/v1",
      "models_endpoint": "/models",
      "requires_key": true,
      "requires_card": false,
      "rate_limit": {
        "rpm": 30,
        "rpd": 14400,
        "tpm": 6000
      },
      "models": [
        "llama-3.3-70b-versatile",
        "llama-3.1-8b-instant",
        "mixtral-8x7b-32768",
        "gemma2-9b-it"
      ],
      "free_models": [
        "llama-3.3-70b-versatile",
        "llama-3.1-8b-instant",
        "mixtral-8x7b-32768",
        "gemma2-9b-it"
      ],
      "features": [
        "chat",
        "function_calling"
      ],
      "region": "global",
      "notes": "LPU inference at extreme speed, no credit card required",
      "source": "https://github.com/cheahjs/free-llm-api-resources",
      "last_probed": "2026-08-30T10:59:35.791626+00:00",
      "status": "active",
      "context_window": 8192,
      "max_output_tokens": 8192,
      "function_calling": true,
      "health_score": 68,
      "models_count": 14
    },
    {
      "name": "HuggingFace Inference",
      "slug": "huggingface",
      "tier": "permanent_free",
      "website": "https://huggingface.co/inference-api",
      "api_base": "https://router.huggingface.co/v1",
      "models_endpoint": "/models",
      "requires_key": true,
      "requires_card": false,
      "rate_limit": {
        "monthly_credits": 0.1
      },
      "models": [
        "meta-llama/Meta-Llama-3.1-70B-Instruct",
        "mistralai/Mistral-7B-Instruct-v0.3",
        "google/gemma-2-9b-it",
        "Qwen/Qwen2.5-72B-Instruct"
      ],
      "free_models": [
        "meta-llama/Meta-Llama-3.1-70B-Instruct",
        "mistralai/Mistral-7B-Instruct-v0.3",
        "google/gemma-2-9b-it",
        "Qwen/Qwen2.5-72B-Instruct"
      ],
      "features": [
        "chat",
        "embeddings",
        "vision",
        "audio"
      ],
      "region": "global",
      "notes": "$0.10/month credits, most aggregated models",
      "source": "https://github.com/cheahjs/free-llm-api-resources",
      "last_probed": "2026-08-30T10:59:35.761929+00:00",
      "status": "active",
      "context_window": 4096,
      "max_output_tokens": 4096,
      "function_calling": false,
      "health_score": 65,
      "models_count": 136
    },
    {
      "name": "Kilo Code",
      "slug": "kilo-code",
      "tier": "permanent_free",
      "website": "https://kilo.ai",
      "api_base": "https://api.kilo.ai/api/gateway/v1",
      "models_endpoint": "/models",
      "requires_key": false,
      "requires_card": false,
      "rate_limit": {
        "rph": 200
      },
      "models": [
        "kilo-auto/free",
        "stepfun/step-1-flash",
        "deepseek/deepseek-chat"
      ],
      "free_models": [
        "kilo-auto/free",
        "stepfun/step-1-flash",
        "deepseek/deepseek-chat"
      ],
      "features": [
        "chat",
        "function_calling"
      ],
      "region": "global",
      "notes": "No key needed to list models, 200 req/hr per IP",
      "source": "https://github.com/cheahjs/free-llm-api-resources",
      "last_probed": "2026-08-30T10:59:36.454610+00:00",
      "status": "active",
      "models_count": 366,
      "context_window": 32768,
      "max_output_tokens": 4096,
      "function_calling": true,
      "health_score": 68
    },
    {
      "name": "LLM7.io",
      "slug": "llm7",
      "tier": "permanent_free",
      "website": "https://llm7.io",
      "api_base": "https://api.llm7.io/v1",
      "models_endpoint": "/models",
      "requires_key": true,
      "requires_card": false,
      "rate_limit": {
        "rpm": 30
      },
      "models": [
        "claude-3.5-sonnet",
        "gpt-5",
        "gemini-2.0",
        "kling",
        "seedance"
      ],
      "free_models": [
        "openai",
        "gpt-4o-mini",
        "deepseek-chat"
      ],
      "features": [
        "chat",
        "vision",
        "video_generation"
      ],
      "region": "global",
      "notes": "Includes closed-source top models, 30 RPM (120 RPM with token). Base models free, closed-source requires token",
      "source": "https://github.com/nejib1/Free-LLM",
      "last_probed": "2026-08-30T10:59:36.220503+00:00",
      "status": "active",
      "models_count": 44,
      "context_window": 128000,
      "max_output_tokens": 4096,
      "function_calling": true,
      "health_score": 70
    },
    {
      "name": "Mistral La Plateforme",
      "slug": "mistral",
      "tier": "permanent_free",
      "website": "https://console.mistral.ai",
      "api_base": "https://api.mistral.ai/v1",
      "models_endpoint": "/models",
      "requires_key": true,
      "requires_card": false,
      "rate_limit": {
        "rps": 1,
        "tpm": 500000
      },
      "models": [
        "mistral-large-latest",
        "mistral-small-latest",
        "open-mistral-7b",
        "open-mixtral-8x7b"
      ],
      "free_models": [
        "open-mistral-7b",
        "open-mixtral-8x7b"
      ],
      "features": [
        "chat",
        "embeddings",
        "function_calling"
      ],
      "region": "eu",
      "notes": "EU privacy standards, ~1B tokens/month free",
      "source": "https://github.com/cheahjs/free-llm-api-resources",
      "last_probed": "2026-08-30T10:59:36.073983+00:00",
      "status": "active",
      "context_window": 32768,
      "max_output_tokens": 4096,
      "function_calling": true,
      "health_score": 70,
      "models_count": 54
    },
    {
      "name": "NVIDIA NIM",
      "slug": "nvidia-nim",
      "tier": "permanent_free",
      "website": "https://build.nvidia.com",
      "api_base": "https://integrate.api.nvidia.com/v1",
      "models_endpoint": "/models",
      "requires_key": true,
      "requires_card": false,
      "rate_limit": {
        "rpm": 40
      },
      "models": [
        "nvidia/nemotron-3-ultra-550b-a55b",
        "meta/llama-3.1-405b-instruct",
        "microsoft/phi-3.5-mini-instruct",
        "google/gemma-2-9b-it"
      ],
      "free_models": [
        "nvidia/nemotron-3-ultra-550b-a55b",
        "meta/llama-3.1-405b-instruct",
        "microsoft/phi-3.5-mini-instruct",
        "google/gemma-2-9b-it"
      ],
      "features": [
        "chat",
        "vision",
        "function_calling"
      ],
      "region": "global",
      "notes": "Requires phone verification, 102+ models, GPU cluster inference",
      "source": "https://github.com/cheahjs/free-llm-api-resources",
      "last_probed": "2026-08-30T10:59:36.125587+00:00",
      "status": "active",
      "models_count": 83,
      "context_window": 1000000,
      "max_output_tokens": 4096,
      "function_calling": true,
      "health_score": 70
    },
    {
      "name": "Ollama Cloud",
      "slug": "ollama-cloud",
      "tier": "permanent_free",
      "website": "https://ollama.com",
      "api_base": "https://ollama.com/v1",
      "models_endpoint": "/models",
      "chat_endpoint": "/chat/completions",
      "requires_key": true,
      "requires_card": false,
      "rate_limit": {
        "session_reset_hours": 5,
        "weekly_reset_days": 7,
        "concurrency": 1,
        "relative_usage_scaling": {
          "pro": "50x",
          "max": "250x"
        }
      },
      "models": [
        "deepseek-v4-flash:0731",
        "gpt-oss:120b",
        "deepseek-v4-pro:preview",
        "deepseek-v4-pro:0813",
        "minimax-m2.7",
        "minimax-m3",
        "nemotron-3-ultra",
        "glm-5.2",
        "kimi-k2.6",
        "nemotron-3-nano:30b",
        "gpt-oss:20b",
        "kimi-k2.7-code",
        "mistral-large-3:675b",
        "gemma4:31b",
        "nemotron-3-super",
        "qwen3.5:397b",
        "glm-5.1",
        "glm-5.3-flash",
        "kimi-k3",
        "deepseek-v4-flash:preview"
      ],
      "free_models": [
        "deepseek-v4-flash:0731",
        "gpt-oss:120b",
        "deepseek-v4-pro:preview",
        "deepseek-v4-pro:0813",
        "minimax-m2.7",
        "minimax-m3",
        "nemotron-3-ultra",
        "glm-5.2",
        "kimi-k2.6",
        "nemotron-3-nano:30b",
        "gpt-oss:20b",
        "kimi-k2.7-code",
        "mistral-large-3:675b",
        "gemma4:31b",
        "nemotron-3-super",
        "qwen3.5:397b",
        "glm-5.1",
        "glm-5.3-flash",
        "kimi-k3",
        "deepseek-v4-flash:preview"
      ],
      "features": [
        "chat",
        "function_calling",
        "multimodal",
        "vision",
        "streaming"
      ],
      "region": "global",
      "notes": "Free tier provides access to Ollama's cloud-hosted models with usage limits: 1 concurrent model, session limits reset every 5 hours, weekly limits reset every 7 days. Exactly what it says on the pricing page: https://ollama.com/pricing.",
      "source": "https://ollama.com/pricing",
      "last_probed": "2026-08-30T10:59:36.195391+00:00",
      "status": "active",
      "context_window": 128000,
      "max_output_tokens": 4096,
      "function_calling": true,
      "health_score": 70,
      "models_count": 19
    },
    {
      "name": "OpenCode Zen",
      "slug": "opencode-zen",
      "tier": "permanent_free",
      "website": "https://opencode.ai/zen",
      "api_base": "https://opencode.ai/zen/v1",
      "models_endpoint": "/models",
      "requires_key": true,
      "requires_card": false,
      "rate_limit": {
        "rpd": 100
      },
      "models": [
        "deepseek-v4-flash-free",
        "mimo-v2.5-free",
        "north-mini-code-free",
        "nemotron-3-ultra-free",
        "nemotron-3.5-lightning-free",
        "nemotron-3-super-free",
        "minimax-m2.5-free",
        "hy3-free",
        "x-preview-f-free",
        "big-pickle",
        "muse-spark-1.2-contributor-free"
      ],
      "free_models": [
        "deepseek-v4-flash-free",
        "mimo-v2.5-free",
        "north-mini-code-free",
        "nemotron-3-ultra-free",
        "nemotron-3.5-lightning-free",
        "nemotron-3-super-free",
        "minimax-m2.5-free",
        "hy3-free",
        "x-preview-f-free",
        "big-pickle",
        "muse-spark-1.2-contributor-free"
      ],
      "features": [
        "chat",
        "function_calling"
      ],
      "region": "global",
      "notes": "OpenCode Zen free tier: 100 req/day, no credit card, OpenAI-compatible. Free models limited time, data collected for improvement. Auth: `opencode auth login --provider zen`. Endpoint: https://opencode.ai/zen/v1/chat/completions",
      "source": "https://opencode.ai/docs/zen/",
      "last_probed": "2026-08-30T10:59:36.229497+00:00",
      "status": "active",
      "context_window": 128000,
      "max_output_tokens": 4096,
      "function_calling": false,
      "health_score": 75,
      "models_count": 63
    },
    {
      "name": "OpenRouter",
      "slug": "openrouter",
      "tier": "permanent_free",
      "website": "https://openrouter.ai",
      "api_base": "https://openrouter.ai/api/v1",
      "models_endpoint": "/models",
      "requires_key": true,
      "requires_card": false,
      "rate_limit": {
        "rpm": 20,
        "rpd": 50
      },
      "models": [
        "inclusionai/ling-3.0-flash:free",
        "poolside/laguna-s-2.1:free",
        "cohere/north-mini-code:free",
        "nvidia/nemotron-3-ultra-550b-a55b:free",
        "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free"
      ],
      "free_models": [
        "inclusionai/ling-3.0-flash:free",
        "poolside/laguna-s-2.1:free",
        "cohere/north-mini-code:free",
        "nvidia/nemotron-3-ultra-550b-a55b:free",
        "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free"
      ],
      "features": [
        "chat",
        "vision",
        "function_calling",
        "reasoning"
      ],
      "region": "global",
      "notes": "Aggregation platform, 14 free models, 1M context (Nemotron Ultra)",
      "source": "https://github.com/cheahjs/free-llm-api-resources",
      "last_probed": "2026-08-30T10:59:36.243240+00:00",
      "status": "active",
      "models_count": 396,
      "context_window": 1000000,
      "max_output_tokens": 4096,
      "function_calling": true,
      "health_score": 72
    },
    {
      "name": "OVHcloud AI Endpoints",
      "slug": "ovhcloud",
      "tier": "permanent_free",
      "website": "https://endpoints.ai.cloud.ovh.net",
      "api_base": "https://endpoints.ai.cloud.ovh.net/v1",
      "models_endpoint": "/models",
      "requires_key": true,
      "requires_card": false,
      "rate_limit": {
        "rpm": 2
      },
      "models": [
        "mistral-7b-instruct",
        "llama-3.1-8b-instruct",
        "llama-3.3-70b-instruct",
        "mixtral-8x7b-instruct"
      ],
      "free_models": [
        "mistral-7b-instruct",
        "llama-3.1-8b-instruct",
        "llama-3.3-70b-instruct",
        "mixtral-8x7b-instruct"
      ],
      "features": [
        "chat"
      ],
      "region": "eu",
      "notes": "EU GDPR compliant, anonymous 2 RPM",
      "source": "https://github.com/nejib1/Free-LLM",
      "last_probed": "2026-08-30T10:59:36.832164+00:00",
      "status": "degraded",
      "context_window": 32768,
      "max_output_tokens": 4096,
      "function_calling": false,
      "health_score": 46
    },
    {
      "name": "Pollinations.ai",
      "slug": "pollinations",
      "tier": "permanent_free",
      "website": "https://pollinations.ai",
      "api_base": "https://text.pollinations.ai",
      "models_endpoint": "/models",
      "requires_key": true,
      "requires_card": false,
      "rate_limit": {},
      "models": [
        "openai",
        "gpt-4o",
        "claude",
        "gemini"
      ],
      "free_models": [
        "openai"
      ],
      "features": [
        "chat",
        "image_generation"
      ],
      "region": "global",
      "notes": "Completely free, no registration required, supports text-to-image",
      "source": "https://github.com/nejib1/Free-LLM",
      "last_probed": "2026-08-30T10:59:36.633194+00:00",
      "status": "active",
      "context_window": 4096,
      "max_output_tokens": 4096,
      "function_calling": false,
      "health_score": 55,
      "models_count": 1
    },
    {
      "name": "Z.AI (Zhipu AI)",
      "slug": "z-ai",
      "tier": "permanent_free",
      "website": "https://z.ai/",
      "api_base": "https://open.bigmodel.cn/api/paas/v4/",
      "models_endpoint": "/models",
      "requires_key": true,
      "requires_card": false,
      "rate_limit": {
        "concurrent": 1,
        "notes": "Free tier: 1 concurrent request, session-based limits"
      },
      "models": [
        "glm-4.5-flash",
        "glm-4.6-flash",
        "glm-4.7-flash"
      ],
      "free_models": [
        "glm-4.5-flash",
        "glm-4.6-flash",
        "glm-4.7-flash"
      ],
      "features": [
        "chat",
        "function_calling",
        "vision",
        "streaming"
      ],
      "region": "global",
      "notes": "Permanent free models, no credit card required. Phone verification required. 1 concurrent request, 200K context window.",
      "source": "https://z.ai/",
      "last_probed": "2026-08-30T10:59:37.202826+00:00",
      "status": "active",
      "context_window": 200000,
      "max_output_tokens": 8192,
      "function_calling": true,
      "health_score": 75,
      "models_count": 3
    }
  ]
}