GPT4Free

Community-Driven & Open SourceFree GPT Playground For LLMs & AgentsExperiment with AI Models without having to go through the hassle of APIs, logins, or restrictions.Start ChattingExplore Models300+Models10+Providers100%Free to StartOpenAICompatible APIWhy GPT4Free?Everything you need to work with LLMs, without the friction.Multi-Provider AccessOne interface for OpenAI, Anthropic, Google, Meta, xAI, DeepSeek, and more. Switch models with a click.No RestrictionsNo geo-blocks, no waitlists, no API key hassles. Just open the playground and start chatting.OpenAI-Compatible APIDrop-in replacement at api.gpt4free.io. Use with any OpenAI SDK — Python, JavaScript, curl.Built by the CommunityAn open, community-driven project. Multi-provider support, local GUI, and flexible integrations.Featured ModelsPopular models available on the platformView all How It Works1Open the PlaygroundNavigate to the chat — no account required for free models.2Pick Any ModelChoose from hundreds of models across every major AI provider.3Start ChattingGet instant responses. Upgrade to credits for premium models.Ready to try the free AI playground?No credit card. No sign-up required.Launch Playground --- Available ModelsAll models available through the GPT4Free platform. New models are added regularly as providers update their offerings.Customtrinity large preview:freearcee-ai/trinity-large-preview:freetrinity mini:freearcee-ai/trinity-mini:freedolphin mistral 24b venice edition:freecognitivecomputations/dolphin-mistral-24b-venice-edition:freegemma 3 12b it:freegoogle/gemma-3-12b-it:freegemma 3 27b it:freegoogle/gemma-3-27b-it:freegemma 3 4b it:freegoogle/gemma-3-4b-it:freegemma 3n e2b it:freegoogle/gemma-3n-e2b-it:freegemma 3n e4b it:freegoogle/gemma-3n-e4b-it:freelfm 2.5 1.2b instruct:freeliquid/lfm-2.5-1.2b-instruct:freelfm 2.5 1.2b thinking:freeliquid/lfm-2.5-1.2b-thinking:freellama 3.2 3b instruct:freemeta-llama/llama-3.2-3b-instruct:freellama 3.3 70b instruct:freemeta-llama/llama-3.3-70b-instruct:freemistral small 3.1 24b instruct:freemistralai/mistral-small-3.1-24b-instruct:freehermes 3 llama 3.1 405b:freenousresearch/hermes-3-llama-3.1-405b:freenemotron 3 nano 30b a3b:freenvidia/nemotron-3-nano-30b-a3b:freenemotron 3 super 120b a12b:freenvidia/nemotron-3-super-120b-a12b:freenemotron nano 12b v2 vl:freenvidia/nemotron-nano-12b-v2-vl:freenemotron nano 9b v2:freenvidia/nemotron-nano-9b-v2:freegpt oss 120b:freeopenai/gpt-oss-120b:freegpt oss 20b:freeopenai/gpt-oss-20b:freefreeopenrouter/freehealer alphaopenrouter/healer-alphahunter alphaopenrouter/hunter-alphaqwen3 4b:freeqwen/qwen3-4b:freeqwen3 coder:freeqwen/qwen3-coder:freeqwen3 next 80b a3b instruct:freeqwen/qwen3-next-80b-a3b-instruct:freestep 3.5 flash:freestepfun/step-3.5-flash:freeglm 4.5 air:freez-ai/glm-4.5-air:freeStart using any modelGet Started --- API DocumentationComplete reference for the GPT4Free API. OpenAI-compatible — use as a drop-in replacement for any provider.Quick StartMake your first API call in seconds. Just replace the API key with your own.curl https://api.gpt4free.io/v1/chat/completions \ -H "Authorization: Bearer YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "gpt-4.1", "messages": [ {"role": "user", "content": "Hello!"} ] }'Base URLhttps://api.gpt4free.io/v1All endpoints follow the OpenAI API specification. Replace api.openai.com/v1 with our base URL in any OpenAI-compatible SDK or HTTP client.AuthenticationAuthenticate by passing your API key in the Authorization header with every request:Authorization: Bearer sk-your-api-keyGet your API key from the dashboard after creating an account.Keep your key secret. Do not expose it in client-side code or public repositories.Free-tier endpoints (such as listing models) may not require authentication.EndpointsPOST/v1/chat/completionsCreate a chat completion. Supports multi-turn conversations, function/tool calling, and real-time streaming via Server-Sent Events.Request Body{ "model": "gpt-4.1", "messages": [ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "Explain quantum computing." } ], "temperature": 0.7, "max_tokens": 1024, "stream": false, "top_p": 1.0, "frequency_penalty": 0.0, "presence_penalty": 0.0, "stop": null, "tools": [], "tool_choice": "auto" }Response{ "id": "chatcmpl-abc123", "object": "chat.completion", "created": 1709827200, "model": "gpt-4.1", "choices": [ { "index": 0, "message": { "role": "assistant", "content": "Quantum computing uses qubits..." }, "finish_reason": "stop" } ], "usage": { "prompt_tokens": 24, "completion_tokens": 128, "total_tokens": 152 } }Set "stream": true to receive the response as Server-Sent Events. See the Streaming section below for format details.GET/v1/modelsList all models currently available through the API. Use the model id value when making completion or embedding requests.Response{ "object": "list", "data": [ { "id": "gpt-4.1", "object": "model", "owned_by": "openai" }, { "id": "claude-sonnet-4-20250514", "object": "model", "owned_by": "anthropic" }, { "id": "gemini-2.5-pro", "object": "model", "owned_by": "google" } ] }No request body required. Authentication is optional for this endpoint.POST/v1/embeddingsGenerate vector embeddings for a given input. Useful for semantic search, clustering, and retrieval-augmented generation (RAG).Request Body{ "model": "text-embedding-3-small", "input": "The quick brown fox jumps over the lazy dog." } // You can also pass an array of strings: { "model": "text-embedding-3-small", "input": [ "First sentence.", "Second sentence." ] }Response{ "object": "list", "data": [ { "object": "embedding", "embedding": [0.0023, -0.0091, 0.0152, ...], "index": 0 } ], "model": "text-embedding-3-small", "usage": { "prompt_tokens": 9, "total_tokens": 9 } }POST/v1/images/generationsGenerate images from a text prompt. Returns one or more image URLs.Request Body{ "model": "dall-e-3", "prompt": "A futuristic city skyline at sunset, digital art", "n": 1, "size": "1024x1024" }Response{ "created": 1709827200, "data": [ { "url": "https://..." } ] }Supported sizes vary by model. Common values: 256x256, 512x512, 1024x1024, 1792x1024.POST/v1/audio/transcriptionsTranscribe audio files to text. Send the audio file as multipart form data.Request Body// Multipart form data: // - model: "whisper-1" // - file: