OpenRouter — Free LLM API

33 free models available — credit card may be required. Get API key →

Single API key for 300+ models from every major lab.

OpenRouter is a unified API gateway that routes requests to models from OpenAI, Anthropic, Google, Meta, Mistral, and dozens of other providers. With a single API key and one base URL, developers can switch between models without changing code. The free tier (marked :free) offers 200 requests/day — or 1,000/day with a $10 lifetime top-up.

  • 35+ permanently free models
  • OpenAI-compatible endpoint
  • 200 RPD free, 1,000 RPD with $10 lifetime credit
  • One key for 300+ models

API Compatibility: OpenAI SDK-compatible (Chat Completions)

All Free OpenRouter Models — Context Windows & Rate Limits

Model Context Max Output Modality Rate Limit Status
Owl Alpha 1.0M 262K text See provider page Details
NVIDIA: Nemotron 3 Nano Omni (free) 256K 66K textimageaudio See provider page Details
Poolside: Laguna XS.2 (free) 131K 8K text See provider page Details
Poolside: Laguna M.1 (free) 131K 8K text See provider page Details
inclusionAI: Ling-2.6-1T (free) 262K 33K text See provider page Details
Tencent: Hy3 preview (free) 262K 262K text See provider page Details
Baidu: Qianfan-OCR-Fast (free) 66K 29K textimage See provider page Details
Google: Gemma 4 26B A4B (free) 262K 33K textimage See provider page Details
Google: Gemma 4 31B (free) 262K 33K textimage See provider page Details
Google: Lyria 3 Pro Preview 1.0M 66K textimage See provider page Details
Google: Lyria 3 Clip Preview 1.0M 66K textimage See provider page Details
NVIDIA: Nemotron 3 Super (free) 262K 262K text See provider page Details
MiniMax: MiniMax M2.5 (free) 197K 8K text See provider page Details
Free Models Router 200K 8K textimage See provider page Details
LiquidAI: LFM2.5-1.2B-Thinking (free) 33K 8K textreasoning See provider page Details
LiquidAI: LFM2.5-1.2B-Instruct (free) 33K 8K text See provider page Details
NVIDIA: Nemotron 3 Nano 30B A3B (free) 256K 8K text See provider page Details
NVIDIA: Nemotron Nano 12B 2 VL (free) 128K 128K textimage See provider page Details
Qwen: Qwen3 Next 80B A3B Instruct (free) 262K 8K text See provider page Details
NVIDIA: Nemotron Nano 9B V2 (free) 128K 8K text See provider page Details
OpenAI: gpt-oss-120b (free) 131K 131K text See provider page Details
OpenAI: gpt-oss-20b (free) 131K 8K text See provider page Details
Z.ai: GLM 4.5 Air (free) 131K 96K text See provider page Details
Qwen: Qwen3 Coder 480B A35B (free) 262K 262K textcode See provider page Details
Venice: Uncensored (free) 33K 8K text See provider page Details
Google: Gemma 3n 2B (free) 8K 2K text See provider page Details
Google: Gemma 3n 4B (free) 8K 2K text See provider page Details
Google: Gemma 3 4B (free) 33K 8K textimage See provider page Details
Google: Gemma 3 12B (free) 33K 8K textimage See provider page Details
Google: Gemma 3 27B (free) 131K 8K textimage See provider page Details
Meta: Llama 3.3 70B Instruct (free) 66K 8K text See provider page Details
Meta: Llama 3.2 3B Instruct (free) 131K 8K text See provider page Details
Nous: Hermes 3 405B Instruct (free) 131K 8K text See provider page Details

Frequently Asked Questions about OpenRouter Free API

Is OpenRouter free to use?

OpenRouter offers a permanently free tier with 33 available models. Account creation is required, and a credit card may be needed to activate the free tier.

What models does OpenRouter offer for free?

OpenRouter provides 33 free models covering chat, vision, reasoning, coding use cases. Supported modalities include text, image, audio, reasoning, code. Browse the full list above with context windows and rate limits.

How do I use OpenRouter with Claude Code or Cursor?

Click "Details" on any model above to get one-click configuration snippets for Claude Code (cc), Cursor, Codex, and more. All OpenRouter models listed here use an OpenAI-compatible endpoint, so any tool that accepts a custom baseURL will work.