Free LLM Collection

这是一个关于免费的大模型api的合集，并精选了一部分模型

This is a collection of free LLM apis, and selected some models

我会尽可能更新维护这个项目（目前只有我一个人）

I will keep maintaining and updating this project to the best of my ability

入选原则是：限制请求速率而不是token > 尽可能多的来源 > 尽可能新且好的模型 > 足够用的请求速率

The selection criteria are: limit request rate over token count > more sources > newer and better models > sufficient rate limits

主要是有一定热度的文本模型

Primarily text models that have gained some popularity

目前只接受提供了OpenAI格式的API

At present, only accepted OpenAI-formated API

欢迎大家分享更多api

Welcome to share more apis

Img Table

这个表格是由Gemini 3 Flash生成的，由Taple渲染

This table was generated by Gemini 3 Flash, Rendered by Taple

Markdown

ChatAnywhere

• API: https://api.chatanywhere.tech
• Rate Limits: Not Limited
• Tip: -
• Models:
  • gpt-4o-mini

硅基流动 / SiliconFlow

• API: https://api.siliconflow.cn/v1
• Rate Limits: 1000 RPM (each model)
• Tip: -
• Models:
  • deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
  • Qwen/Qwen3-8B
  • THUDM/glm-4-9b-chat
  • THUDM/GLM-4-9B-0414
  • THUDM/GLM-Z1-9B-0414
  • THUDM/GLM-4.1V-9B-Thinking

OpenRouter

• API: https://openrouter.ai/api/v1
• Rate Limits: 20 RPM / 200 RPD (each model)
• Tip: -
• Models:
  • deepseek/deepseek-r1-0528:free
  • moonshotai/kimi-k2:free
  • z-ai/glm-4.5-air:free
  • qwen/qwen3-coder:free
  • openai/gpt-oss-120b:free
  • openai/gpt-oss-20b:free
  • arcee-ai/trinity-mini:free
  • nvidia/nemotron-3-nano-30b-a3b:free
  • nvidia/nemotron-nano-12b-v2-vl:free
  • nvidia/nemotron-nano-9b-v2:free
  • arcee-ai/trinity-large-preview:free
  • liquid/lfm-2.5-1.2b-thinking:free
  • liquid/lfm-2.5-1.2b-instruct:free
  • allenai/molmo-2-8b:free

书生 / Intern AI

• API: https://chat.intern-ai.org.cn/api/v1
• Rate Limits: 10 RPM
• Tip: 密钥有效期6个月 / The key is valid for 6 months
• Models:
  • intern-latest
  • intern-s1-mini
  • internvl3-78b

共享算力 / suanli.com

• API: https://api.suanli.cn/v1
• Rate Limits: Unknown
• Tip: 算力由他人设备共享提供 / Shared computing by other people's devices
• Models:
  • free:QwQ-32B

Google Gemini

• API: https://generativelanguage.googleapis.com/v1beta/openai

• Rate Limits: 30 RPM / 1440 RPD

• Tip: GFW

• Models:

  • gemma-3-27b
  • gemma-3-12b
  • gemma-3-4b

• Rate Limits: 5 RPM / 20 RPD

• Models:

  • gemini-2.5-flash
  • gemini-3-flash

• Rate Limits: 10 RPM / 20 RPD

• Models:

  • gemini-2.5-flash-lite

Cohere

• API: https://api.cohere.ai/compatibility/v1
• Rate Limits: 20 RPM
• Tip:
  • 绑定支付方式可以使用速率限制更宽松的 Production Key / Binding payment methods can use rate limiting and relaxed Production Key
  • GFW
• Models:
  • command-a-03-2025
  • command-a-vision-07-2025

Bigmodel

• API: https://open.bigmodel.cn/api/paas/v4/
• Rate Limits: 只有并发数限制（均为30） / Only the number of concurrent transactions is limited (both 30).
• Tip: -
• Models:
  • GLM-4-Flash-250414
  • GLM-Z1-Flash
  • GLM-4.5-Flash
  • GLM-4.1V-Thinking-Flash
  • GLM-4.6V-Flash

Github Models

• API: https://models.github.ai/inference
• Rate Limits: 15 RPM / 150 RPD
• Tip:
  • 如果使用 Azure API，可以使用更多模型 / If used Azure API, more models available
• Models:
  • openai/gpt-4.1-mini
  • openai/gpt-4.1
  • openai/gpt-4o

哈基米半公益站

• API: https://api.gemai.cc/v1
• Rate Limits: Unknown
• Tip:
  • 赠送¥100额度 / Gift ¥100 Credit
• Models:
  • gpt-5.1
  • gpt-5.1-high
  • [官逆]gemini-2.5-pro
  • [满血A]gemini-3-pro-preview
  • [满血A]gemini-3-pro-preview-thinking
  • [满血B]gemini-2.5-flash
  • [满血C]gemini-2.5-flash-thinking
  • [满血C]gemini-2.5-pro-thinking
  • [特价C]128k-claude-sonnet-4-5-20250929
  • deepseek-v3.2-exp
  • deepseek-v3.2-exp-thinking
  • grok-4
  • grok-4.1

熊猫API

• API: https://api520.pro/v1
• Rate Limits: Unknown
• Tip:
  • 赠送¥100额度 / Gift ¥100 Credit
• Models:
  • 熊猫-按量-特供顶级-官方正向满血-claude-haiku-4.5
  • 熊猫-按量-特供顶级-官方正向满血-claude-opus-4
  • 熊猫-按量-特供顶级-官方正向满血-claude-opus-4.1
  • 熊猫-按量-特供顶级-官方正向满血-claude-opus-4.1-thinking
  • 熊猫-按量-特供顶级-官方正向满血-claude-opus-4.5
  • 熊猫-按量-特供顶级-官方正向满血-claude-opus-4.5-thinking
  • 熊猫-按量-特供顶级-官方正向满血-claude-sonnet-4.5
  • 熊猫-按量-特供顶级-官方正向满血-claude-sonnet-4.5-thinking
  • 熊猫-A-4-deepseek-v3.2-满血
  • 熊猫-A-5-deepseek-v3.1-terminus-thinking-满血
  • 熊猫-A-5-deepseek-v3.2-thinking-满血
  • 熊猫-A-1-gemini-2.5-flash-lite-0925
  • 熊猫-A-2-gemini-2.5-flash-0925
  • 熊猫特供-按量-SS-gemini-2.5-pro
  • 熊猫特供-按量-SS-gemini-2.5-pro-thinking
  • 熊猫特供-按量-SSS-gemini-3-pro-preview
  • 熊猫-A-5-kimi-k2-thinking-满血
  • 熊猫-A-3-速度极快-gpt-oss-120b
  • 熊猫-A-5-Grok-4-fast-200w上下文已知最大
  • 熊猫-A-5-grok-4.1
  • 熊猫-A-4-豆包-doubao-seed-1.6
  • 熊猫-A-5-豆包-doubao-seed-1.6-thinking
  • 熊猫-A-5-智谱glm-4.6-满血
  • 熊猫-A-3-qwen3-max-满血
  • 熊猫-A-4-minimax-m2

其它 / Other

来源 / Source

• 自行收集 / Self-collected

• 投稿（B站等） / Contributed by others

Star History

排行榜 / Leaderboards

• llm_benchmark：个人评测榜单，可信度高，而且收录更全 / A personal review list, it is highly credible, and it is more comprehensive
• Artifical Analysis
• LMArena