OpenRouter 免费模型

更新于 2026-11-08 05:00:02 (UTC+8) · 数据来自 OpenRouter API

1. 什么是 OpenRouter？

OpenRouter 是一个统一的 AI 模型 API 网关，让你通过一个 API Key 访问数百个不同的大语言模型，包括许多完全免费的模型。

2. 获取 API Key

  • 访问 openrouter.ai 注册账号
  • 进入 Settings → Keys，创建一个 API Key
  • 免费模型 不需要充值，注册即可使用

3. 在代码中调用

OpenRouter 兼容 OpenAI API 格式，只需修改 base_url：

import openai client = openai.OpenAI( base_url="https://openrouter.ai/api/v1", api_key="sk-***" ) response = client.chat.completions.create( model="qwen/qwen3-coder:free", messages=[{{"role": "user", "content": "你好"}}] ) print(response.choices[0].message.content)

4. cURL 调用

curl https://openrouter.ai/api/v1/chat/completions \ -H "Authorization: Bearer ***你的KEY" \ -H "Content-Type: application/json" \ -d '{{"model":"meta-llama/llama-3.3-70b-instruct:free","messages":[{{"role":"user","content":"Hello"}}]}}'

5. 如何选择模型？

  • 上下文长度：越大能处理的文本越长
  • 模态：💬 纯文本 / 🖼️ 支持图片输入 / 🎵 支持音频
  • 提供商：Google、Meta、Qwen 等大厂模型通常更稳定
  • 点击 Model ID 即可复制到剪贴板
💡 免费模型可能有速率限制（1-20 RPM），适合开发测试。生产环境建议使用付费模型。
16 免费模型
460 总模型数
Cohere 📏 256K

Cohere: North Mini Code (free)

cohere/north-mini-code:free

North Mini Code is Cohere's first agentic coding model and the debut of its North family. A sparse mixture-of-experts model with 30B total parameters ...

💬 text → text
Dots Studio 📏 512K

Dots Studio: Dots3-Note Preview (free)

dots-studio/dots-3-note-preview:free

Dots3-Note Preview is an open-weight mixture-of-experts model from Dots Studio, with 16B active parameters out of 280B total. It is the lightest model...

🖼️ text+image → text
Google 📏 262K

Google: Gemma 4 26B A4B (free)

google/gemma-4-26b-a4b-it:free

Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per...

🖼️🎬 text+image+video → text
Google 📏 262K

Google: Gemma 4 31B (free)

google/gemma-4-31b-it:free

Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context...

🖼️🎬 text+image+video → text
Google 📏 1.0M

Google: Lyria 3 Clip Preview

google/lyria-3-clip-preview

30 second duration clips are priced at $0.04 per clip. Lyria 3 is Google's family of music generation models, available through the Gemini API. With L...

🖼️🎵 text+image → text+audio
Google 📏 1.0M

Google: Lyria 3 Pro Preview

google/lyria-3-pro-preview

Full-length songs are priced at $0.08 per song. Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3,...

🖼️🎵 text+image → text+audio
Liquid 📏 65K

LiquidAI: LFM2.5-2.6B (free)

liquid/lfm-2.5-2.6b:free

LFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for agent workflows, data extraction, RAG, and long-context processing. Liquid a...

💬 text → text
Liquid 📏 262K

LiquidAI: LFM3-1.7B (free)

liquid/lfm-3-1.7b:free

A compact 1.7B-parameter text model with a 256K-token context, post-trained for agents, tool calling, and structured outputs. It reasons before it ans...

💬 text → text
NVIDIA 📏 256K

NVIDIA: Nemotron 3 Nano Omni (free)

nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free

NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems...

🖼️🎬 text+image+audio+video → text
NVIDIA 📏 1.0M

NVIDIA: Nemotron 3 Ultra (free)

nvidia/nemotron-3-ultra-550b-a55b:free

NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built o...

💬 text → text
NVIDIA 📏 1.0M

NVIDIA: Nemotron 3.5 Lightning (free)

nvidia/nemotron-3.5-lightning:free

NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throu...

💬 text → text
NVIDIA 📏 1.0M

NVIDIA: Nemotron 3.5 Super VL (free)

nvidia/nemotron-3.5-super-vl:free

NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, ...

🖼️🎬 text+image+video → text
OpenRouter 📏 200K

Free Models Router

openrouter/free

The simplest way to get free inference. openrouter/free is a router that selects free models at random from the models available on OpenRouter. The ro...

🖼️ text+image → text
Recursive 📏 262K

Recursive: Flint (free)

recursive/flint-v1.0:free

Flint is an open-weight mixture-of-experts model from Recursive, with about 2.5B active parameters out of 40B total, built by Recursive's autoresearch...

💬 text → text
Stealth 📏 1.0M

Crouton Alpha

stealth/crouton-alpha

Crouton Alpha is a lightweight model built for scalable coding, agentic, and multimodal workflows. It's ideal for executing agentic sub-tasks, tool us...

🖼️🎬 text+image+file+audio+video …
Xingchen Agi 📏 262K

XingChen: Xing4.0 29B A4B (free)

xingchen-agi/xing4.0-29b-a4b:free

Xing4.0-29B-A4B is an open-weight mixture-of-experts language model from China Telecom's AI team (TeleAI) and the successor to the TeleChat series. It...

💬 text → text