免费 LLM API 合集 Free-LLM-Collection：精选模型与速率限制一览

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

我会尽可能更新维护这个项目（目前只有我一个人）

入选原则是：长期可用 > 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

目前只接受提供了OpenAI格式的API

欢迎大家分享更多api

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

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

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

At present, only accepted OpenAI-formated API

Welcome to share more apis

Img Table

这个表格的数据是由LLM生成的，由Taple渲染

This data of the table was generated by LLM, Rendered by Taple

Markdown

硅基流动 / SiliconFlow

• API: https://api.siliconflow.cn/v1
• Rate Limits: 1000 RPM (each model)
• Rec. Models:
  • deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
  • Qwen/Qwen3-8B
  • Qwen/Qwen3.5-4B
  • 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)
• Ava. Models:
  • openrouter/free
  • nvidia/nemotron-3-super-120b-a12b:free
  • google/gemma-4-31b-it:free
  • google/gemma-4-26b-a4b-it:free
  • nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free
  • nvidia/nemotron-3-ultra-550b-a55b:free
  • cohere/north-mini-code:free
  • thinkingmachines/inkling:free
  • thinkingmachines/inkling-small:free
  • nvidia/nemotron-3.5-lightning:free
  • liquid/lfm-2.5-2.6b:free
  • nvidia/nemotron-3.5-super-vl:free
  • xingchen-agi/xing4.0-29b-a4b: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
• Ava. Models:
  • intern-latest

Google Gemini

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

• Rate Limits: 5 RPM / 20 RPD

• Models:

  • gemini-3-flash-preview

• Rate Limits: 5 RPM / 20 RPD

• Models:

  • gemini-3.5-flash
  • gemini-3.6-flash
  • gemini-3.7-flash

• Rate Limits: 15 RPM / 500 RPD

• Models:

  • gemini-3.1-flash-lite-preview
  • gemini-3.5-flash-lite

• Rate Limits: 15 RPM / 1500 RPD

• Models:

  • gemma-4-26b-a4b-it
  • gemma-4-31b-it

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
• Rec. Models:
  • command-a-plus-05-2026
  • tiny-aya-global tiny-aya-water

Bigmodel

• API: https://open.bigmodel.cn/api/paas/v4/
• Rate Limits: Unknown
  • GLM-4.7-Flash
  • GLM-4.6V-Flash

NVIDIA NIM

• API: https://integrate.api.nvidia.com/v1
• Rate Limits: 40 RPM
• Rec. Models:
  • nvidia/nemotron-3.5-super-vl-120b-a12b
  • stepfun-ai/step-5-preview
  • z-ai/glm-5.3-flash
  • meta/muse-glimmer-30b
  • deepseek-ai/deepseek-v4.1-flash

ModelScope

• API: https://api-inference.modelscope.cn/v1/
• Limits: 2000 RPD
• Rec. Models:
  • deepseek-ai/DeepSeek-V4-Flash-Vision-Exp
  • deepseek-ai/DeepSeek-V4.1-Flash
  • MiniMax/MiniMax-M2.7
  • inclusionAI/Ring-2.6-1T
  • deepseek-ai/DeepSeek-V4-Flash-0731
  • deepseek-ai/DeepSeek-V4-Pro-0813
  • ZhipuAI/GLM-5.3
  • stepfun-ai/Step-5-Preview

Kilo Gateway

• API: https://api.kilo.ai/api/gateway
• Rate Limits: 200RPH (Hour)
• Rec. Models:
  • openrouter/free
  • kili-auto/free
  • nvidia/nemotron-3.5-super-vl:free
  • poolside/laguna-s-2.1:free
  • nvidia/nemotron-3-ultra-550b-a55b:free
  • nvidia/nemotron-3-super-120b-a12b:free

HuggingFace

• API: https://router.huggingface.co/v1
• Rate Limits: 300 RPH (Hour)
• Rec. Models:
  • xingchen-agi/xing4.0-29b-a4b:free
  • Qwen/Qwen3.8-27B
  • Qwen/Qwen3.8-Flash-Next
  • deepseek-ai/DeepSeek-V4.1-Flash
  • nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4
  • inclusionAI/Ling-3.1-flash
  • zai-org/GLM-5.3-Flash
  • zai-org/GLM-5.3
  • moonshotai/Kimi-K3
  • meta-models/Muse-Glimmer-30B

Groq

• API: https://api.groq.com/openai/v1/
• Rate Limits: 30 RPM / 1000 RPD
• Ava. Models:
  • openai/gpt-oss-120b
  • openai/gpt-oss-20b
  • qwen/qwen3-32b

Celebras

• API: https://api.celebras.ai/v1

• Rate Limits: 30 RPM / 900 RPH / 1440 RPD

• Models:

  • gpt-oss-120b
  • qwen-3-235b-a22b-instruct-2507

• Rate Limits: 10 RPM / 100RPH / 100 RPD

• Models:

  • zai-glm-4.7

Mistral

• API: https://api.mistral.ai/v1
• Rate Limits: Unknown
• Rec. Models:
  • zai-glm-5-3
  • mistral-medium-3-5
  • mistral-small-2603
  • mistral-large-4

OpenCode Console

• API: https://opencode.ai/inference/openai/v1
• Rate Limit: Dynamic
• Ava. Models:
  • big-pickle
  • deepseek-v4.1-flash-free
  • space-bunny-free
  • beam-free
  • ll-alpha-free
  • longcat-2.5-preview-free
  • exo-free
  • mimo-v2.6-flash-free
  • mimo-v2.5-free
  • nemotron-3-ultra-free
  • nemotron-3.5-lightning-free
  • nemotron-3.5-super-vl-free
  • muse-spark-1.3-contributor-free

Token平台 / DXNT

• API: https://www.dxnt.com/v1

• Rate Limit: 20 RPM / 100 RPD

• Rec. Models:

  • dxnt.com/free

• Rate Limit: unknown

  • dxnt/sensenova-6.7-flash-lite

Agens AI

• API: https://apihub.agnes-ai.com/v1
• Rate Limits: 20 RPM
• Ava. Models:
  • agnes-3.0-flash
  • agnes-2.5-flash

Cloudflare Workers AI

• API: https://api.cloudflare.com/client/v4/accounts/{ACCOUNT_ID}/ai/v1
• Limits: 10k Neurons Per Day
• Rec. Models:
  • @cf/moonshotai/kimi-k2.7-code
  • @cf/zai-org/glm-5.2
  • @cf/moonshotai/kimi-k2.6
  • @cf/moonshotai/kimi-k2.5

SenseNova

• API: https://token.sensenova.cn/v1

• Rate Limits: 60000 Points Per 5 Hours / 600000 Points Per Week

• Models:

  • sensenova-6.8-flash-lite

• Rate Limits: ↑ + 可能来自上游的共用未知限制 Possibly Shared Unknown Limits From Upstream Service

• Models:

  • deepseek-v4-flash
  • glm-5.2

G4F

• API: https://g4f.space/v1
• Rate Limits: Unknown
• Rec. Models:
  • auto
  • ...

讯飞星火

• API: https://spark-api-open.xf-yun.com/v1
• Rate Limits: 2 QPS
• Ava. Models:
  • lite

Poolside

• API: https://inference.poolside.ai/v1
• Rate Limits: Unknown
• Ava. Models:
  • poolside/laguna-s-2.1
  • poolside/laguna-xs-2.1

ChatAnywhere

• API: https://api.chatanywhere.tech

• Rate Limits: 1000 Points Per Day + ...

• Rate Limits: 30 RPD

• Rec. Models:

  • deepseek-v4-flash
  • deepseek-v4-pro

• Rate Limits: 5 RPD

• Rec. Models:

  • gpt-5.4
  • gpt-5.4-mini
  • gpt-5.4-nano
  • gpt-5.5
  • gpt-5.6-luna
  • gpt-5.6-terra
  • gpt-5.6-sol

……

肖恩AI

• API: https://speed.toter.me
• Limits: 每日签到 / Daily Check-in
• Rec. Models:
  • gemini-3-flash
  • gemini-2.5-pro
  • gemini-3.1-pro
  • claude-sonnet-4-5
  • claude-opus-4-5

OrcaRouter

• API: https://api.orcarouter.ai/v1
• Limits: 动态调整 / Dynamic
• Ava. Models:
  • orcarouter/free
  • tencent/hy3-free
  • z-ai/glm-5.3-flash-free
  • deepseek/deepseek-v4-flash-free
  • tencent/hy4-preview-free

onomeo

• API: https://onomeo.com/v1
• Limits: 12 RPM + 30 Reqs Per 5 Hours
• Rec. Models:
  • auto
  • gpt-6-astra
  • gpt-6-sol
  • gpt-6-luna
  • gpt-5.6-terra
  • gemini-3.8-flash
  • gemini-3.7-flash
  • gemini-3.6-flash
  • gemini-3.5-flash-lite
  • claude-opus-5.5
  • grok-4.7
  • deepseek-ai/DeepSeek-V4-Pro-0813
  • deepseek-v4.1-flash
  • deepseek-v4-flash
  • Qwen/Qwen3.8-27B
  • Qwen/Qwen3.8-Flash-Next
  • glm-5.2
  • z-ai/glm-5.3-flash-free
  • nemotron-3-ultra-550b-a55b
  • nvidia/nemotron-3-super-120b-a12b
  • kimi-k3
  • meta/muse-glimmer-30b
  • mimo-v2.5:free
  • tencent/hy3-free
  • inclusionai/ling-3.0-flash-sante:free
  • inclusionai/ling-3.0-flash-fin:free
  • nex-agi/nex-n2.5-pro:free
  • Shanghai_AI_Laboratory/Intern-S2-Preview
  • stealth/space-bunny-alpha

Vercel AI Gateway

• API: https://ai-gateway.vercel.sh/v1
• Rate Limits: Unknown
• Ava. Models:
  • poolside/laguna-s-2.1-free
  • nvidia/nemotron-3.5-lightning-free

其它 / Other

来源 / Source

• 自行收集 / Self-collected

• 投稿 / Contributed by others

Star History

排行榜 / Leaderboards

• llm_benchmark
• Artifical Analysis
• LMArena