awesome-free-llm-apis

516+ 免费大模型 API,来自 30 个提供商 — 一站式发现、对比、配置免费模型。

🌐 访问 freellm.net — 浏览模型 · 在线体验 · 配置生成器 · API 密钥

Provider Logos

🔄 数据每日从 freellm.net 自动更新 — 最后更新: 2026-10-21

🌐 English · 简体中文 · 繁體中文 · 日本語 · 한국어


为什么需要这个项目

找一个免费 LLM API,不应该翻十几个 GitHub README、注册五个不同平台、或者猜测哪些模型还有免费额度。

这个仓库是一个结构化、机器可读的免费 LLM API 目录 — 包含速率限制、上下文窗口、一键配置代码片段和直达 API 密钥链接。每日更新。

为什么选择这个仓库 + freellm.net:


三步上手

  1. 选一个提供商 — 看下方 Provider Directory。推荐从 Groq 开始(免信用卡,30 RPM 免费)。
  2. 获取 API Key — 点下方 Quick Reference 里任意一个 [Get Key →] 链接,注册(大多只需邮箱),复制 key。不到 1 分钟。
  3. 填入代码 — 复制 base URL + model ID,粘贴到下边的 Quick Start 示例。

配置具体工具?Claude Code · Cursor · Codex · OpenHuman · OpenCode · OpenClaw — 一键配置在 freellm.net/config/。

快速上手 — 30 秒接入免费 API

没用过 API? 最简单的方式:打开 console.groq.com/keys,用邮箱注册(无需信用卡),复制免费 key,粘贴到下面任意示例。不到一分钟就能跑起来。

以下所有提供商都暴露了 OpenAI 兼容接口。任何接受 baseURL + apiKey 的工具都能直接用 — 替换 base URL 和 key 即可。

Python (OpenAI SDK)

from openai import OpenAI

client = OpenAI(
    base_url="https://api.groq.com/openai/v1",  # 免费,无需信用卡
    api_key="GROQ_API_KEY",                     # 获取: console.groq.com/keys
)

response = client.chat.completions.create(
    model="llama-3.3-70b-versatile",            # 模型列表见下方 Best Models 表
    messages=[{"role": "user", "content": "你好!"}],
)
print(response.choices[0].message.content)
# Groq 免费额度: 30 RPM, 14,400 RPD — 个人使用绰绰有余

Codex CLI

export OPENAI_BASE_URL="https://api.groq.com/openai/v1"
export OPENAI_API_KEY="your-groq-key"          # 获取: console.groq.com/keys
codex --model "llama-3.3-70b-versatile"

Cursor

Settings → Models → Add Model
  Model name: llama-3.3-70b-versatile
  Base URL: https://api.groq.com/openai/v1
  API key: your-groq-key                       # 获取: console.groq.com/keys

Claude Code

# Claude Code 需要 Anthropic 兼容接口 — 使用 OpenRouter
export ANTHROPIC_BASE_URL="https://openrouter.ai/api"
export ANTHROPIC_AUTH_TOKEN="sk-or-v1-your-key"  # openrouter.ai/keys
export ANTHROPIC_API_KEY=""                       # 必须为空
# 注意: OpenRouter 的 Anthropic 模型需充值 $10(一次性)

其他工具?

大多数 AI 开发工具都接受自定义 API 端点 — 拿到免费 key 后:

更多即用配置在 freellm.net/config/。

所有提供商的 Base URL 和 API Key 链接 见下方 Quick Reference。


提供商目录 & 热门免费模型

Provider Free Models Credit Card? Max Context Modalities Get API Key
NVIDIA NIM 136 Phone verification 1M audio, embedding, image, pdf, reasoning, rerank, text, video, vision →
ModelScope 61 Registration 1M image, reasoning, text, video, vision →
Cloudflare Workers AI 41 No 262K code, image, reasoning, text, video →
OpenCode Zen 34 Registration 1M audio, reasoning, vision →
LLM7.io 24 No 1M audio, code, image, pdf, reasoning, text, video, vision →
Kilo Code 23 No 1M audio, code, image, reasoning, text, video →
Google Gemini 19 No 1M audio, image, pdf, reasoning, text, video, vision →
Ollama Cloud 17 Registration 1M code, image, reasoning, text, video, vision →
Mistral AI 15 No 256K code, image, pdf, reasoning, text →
OVHcloud AI Endpoints 15 Registration 262K code, image, reasoning, text, video →
Groq 12 No 262K image, reasoning, text, video →
Cohere 12 No 256K image, text →
Aion Labs 11 Registration 131K reasoning, text →
Hugging Face 9 No 131K code, image, text →
Z AI (Zhipu AI) 8 No 200K image, reasoning, text, video →
Cerebras 6 No 131K reasoning, text →
Cline 6 Registration 0 text, vision -
Agnes AI 5 Registration 256K image, reasoning, text, video, vision →
Alibaba Cloud Model Studio 5 Registration 1M code, image, text →
SiliconFlow 4 Registration 131K reasoning, text →
SambaNova 4 Registration 128K image, reasoning, text →
xAI 3 Registration 2M text →
Chutes.ai 2 Registration 131K reasoning, text →
Glhf.chat 2 Registration 131K text →
Grok (xAI) 2 Registration 131K text →
AI21 Labs 2 Registration 256K text →
DeepSeek 2 Registration 128K text →
Nscale 2 Registration 128K text →
Nebius 1 Registration 128K text →
Provider Free Models Credit Model Max Context Modalities Get API Key
OpenRouter 33 Free tier + $10 topup → 1K RPD 1M audio, code, decisions, embeddings, image, reasoning, rerank, speech, text, video →

快速参考 — Base URL 与 API Key

Provider Base URL Get API Key Credit Card?
NVIDIA NIM https://integrate.api.nvidia.com/v1 Get Key → Phone verification
ModelScope https://api-inference.modelscope.cn/v1 Get Key → Registration
Cloudflare Workers AI https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/run Get Key → No
OpenCode Zen https://opencode.ai/zen/v1 Get Key → Registration
OpenRouter https://openrouter.ai/api/v1 Get Key → Registration
LLM7.io https://api.llm7.io/v1 Get Key → No
Kilo Code https://api.kilo.ai/api/gateway Get Key → No
Google Gemini https://generativelanguage.googleapis.com/v1beta Get Key → No
Ollama Cloud https://ollama.com/api Get Key → Registration
Mistral AI https://api.mistral.ai/v1 Get Key → No
OVHcloud AI Endpoints https://oai.endpoints.kepler.ai.cloud.ovh.net/v1 Get Key → Registration
Groq https://api.groq.com/openai/v1 Get Key → No
Cohere https://api.cohere.com/v2 Get Key → No
Aion Labs https://api.aionlabs.ai/v1 Get Key → Registration
Hugging Face https://router.huggingface.co/v1 Get Key → No
Z AI (Zhipu AI) https://open.bigmodel.cn/api/paas/v4 Get Key → No
Cerebras https://api.cerebras.ai/v1 Get Key → No
Cline - - Registration
Agnes AI https://apihub.agnes-ai.com/v1 Get Key → Registration
Alibaba Cloud Model Studio https://dashscope-intl.aliyuncs.com/compatible-mode/v1 Get Key → Registration
SiliconFlow https://api.siliconflow.cn/v1 Get Key → Registration
SambaNova https://api.sambanova.ai/v1 Get Key → Registration
xAI https://api.x.ai/v1 Get Key → Registration
Chutes.ai https://api.chutes.ai/v1 Get Key → Registration
Glhf.chat https://glhf.chat/api/openai/v1 Get Key → Registration
Grok (xAI) https://api.x.ai/v1 Get Key → Registration
AI21 Labs https://api.ai21.com/studio/v1 Get Key → Registration
DeepSeek https://api.deepseek.com/v1 Get Key → Registration
Nscale https://inference.api.nscale.com/v1 Get Key → Registration
Nebius https://api.studio.nebius.com/v1 Get Key → Registration

各提供商最佳免费模型

Provider Best Free Model Model ID Max Context Rate Limit
NVIDIA NIM z-ai/glm-5.2 z-ai/glm-5.2 1M Up to 40 RPM
z-ai/glm-5.1 z-ai/glm-5.1 202K Up to 40 RPM
moonshotai/kimi-k2.6 moonshotai/kimi-k2.6 262K Up to 40 RPM
ModelScope MiniMax-M2.5-highspeed MiniMax/MiniMax-M2.5 204K See provider
Qwen/Qwen3.5-35B-A3B qwen-qwen3-5-35b-a3b 256K 2,000 RPD total; <=500 ..
Qwen/Qwen3.5-27B qwen-qwen3-5-27b 256K 2,000 RPD total; <=500 ..
Cloudflare Workers AI Mistral 7B @cf/mistral/mistral-7b-instruct-v0.1 32K See provider
Qwen 1.5 7B @cf/qwen/qwen1.5-7b-chat 32K See provider
@cf/meta/llama-3.3-70b-instruct-fp8-fast @cf/meta/llama-3.3-70b-instruct-fp8-fast 24K 10K neurons/day (shared)
OpenCode Zen big-pickle big-pickle 0
DeepSeek V4 Flash deepseek-v4-flash-free 1M
MiMo-V2.5 mimo-v2.5-free 1M
OpenRouter MiniMax: MiniMax M3.1 Flash (free) minimax/minimax-m3.1-flash:free 1M See provider
NVIDIA: Nemotron 3 Ultra (free) nvidia/nemotron-3-ultra-550b-a55b:free 1M See provider
NVIDIA: Nemotron 3.5 Super VL (free) nvidia/nemotron-3.5-super-vl:free 1M See provider
LLM7.io gpt-oss:20b gpt-oss-20b 128K 60 RPM, 250 req/hr (fre..
mistral-Nemo-Instruct-2407 mistral-Nemo-Instruct-2407 128K 60 RPM, 250 req/hr (fre..
minimax-m2.7 minimax-m2.7 180K 60 RPM, 250 req/hr (fre..
Kilo Code nvidia/nemotron-3-ultra-550b-a55b:free nvidia/nemotron-3-ultra-550b-a55b:free 1M 200 req/hr
stepfun/step-3.7-flash:free stepfun/step-3.7-flash 262K 200 req/hr
nvidia/nemotron-3-super-120b-a12b:free nvidia/nemotron-3-super-120b-a12b:free 262K 200 req/hr
Google Gemini Gemini 3.8 Flash gemini-3.8-flash 1M —
Gemini 3.7 Flash gemini-3.7-flash 1M —
Gemini 3.6 Flash gemini-3.6-flash 1M 15 RPM, 1,500 RPD
Ollama Cloud deepseek-v4-pro deepseek-v4-pro 1M Session/weekly limits (..
deepseek-v4-flash deepseek-v4-flash 1M Session/weekly limits (..
minimax-m3 minimax-m3 512K Session/weekly limits (..
Mistral AI Mistral 7B open-mistral-7b 32K See provider
Mixtral 8x7B open-mixtral-8x7b 32K See provider
Mistral Medium 3.5 (128B) mistral-medium-3-5-128b 256K ~1 RPS, 500K TPM
OVHcloud AI Endpoints Qwen3.5-397B-A17B qwen3.5-397b-a17b 262K 2 RPM (anonymous)
Meta-Llama-3_3-70B-Instruct meta-llama-3_3-70b-instruct 131K 2 RPM (anonymous)
Qwen3.8-27B qwen3.8-27b 262K 2 RPM (anonymous)
Groq Moonshot Kimi K2 moonshotai/kimi-k2-instruct 131K See provider
Moonshot Kimi K2 0905 moonshotai/kimi-k2-instruct-0905 131K See provider
groq/compound groq/compound 131K 30 RPM, 250 RPD
Cohere Command A+ (218B) command-a-218b 128K 20 RPM
Command A (111B) command-a-111b 256K 20 RPM
Command R+ command-r 128K 20 RPM
Aion Labs aion-labs/aion-2.0 aion-labs-aion-2-0 128K 15 RPM, 20K TPD
aion-labs/aion-rp-llama-3.1-8b aion-labs-aion-rp-llama-3-1-8b 32K 15 RPM, 20K TPD
aion-labs/aion-3.0 aion-labs-aion-3-0 128K 15 RPM, 20K TPD
Hugging Face Meta-Llama-3.1-8B-Instruct meta-llama-3-1-8b-instruct 128K Credit-metered
gemma-3-4b-it google/gemma-3-4b-it 131K Credit-metered
phi-4 phi-4 16K Credit-metered
Z AI (Zhipu AI) GLM-4.7-Flash glm-4.7-flash 200K 1 concurrent request
GLM-4.5-Flash (retirement announced) glm-4-5-flash-retirement-announced 128K 1 concurrent request
GLM-4.6V-Flash glm-4.6v-flash 128K 1 concurrent request
Cerebras Llama 3.1 70B llama3.1-70b 131K See provider
zai-glm-4.7 (deprecated Aug 2026) zai-glm-4-7-deprecated-aug-2026 131K 5 RPM, 30K TPM, 1M TPD
zai-glm-4.7 zai-glm-4.7 128K 10 RPM, 100 RPD, 1M TPD
Cline Solar Mini 4 cline-free/solar-mini4 0 See provider
cline-free/nemotron-3.5-super-vl cline-free/nemotron-3.5-super-vl 0 See provider
Minimax M3.1 Flash cline-free/minimax-m3.1-flash 0 See provider
Agnes AI agnes-1.5-flash agnes-1.5-flash 256K 30 RPM
agnes-2.0-flash agnes-2.0-flash 256K 30 RPM
agnes-image-2.0-flash agnes-image-2.0-flash 4K 30 RPM (1K)
Alibaba Cloud Model Studio Qwen3-Max qwen3-max 128K Tiered by region
Qwen3-Plus qwen3-plus 1M Tiered by region
Qwen3-VL-Plus qwen3-vl-plus 128K Tiered by region
SiliconFlow Qwen/Qwen3-8B Qwen/Qwen3-8B 128K 1,000 RPM, 50,000 TPM
Abbreviation abbreviation 131K See provider
deepseek-ai/DeepSeek-R1-Distill-Qwen-7B deepseek-ai-deepseek-r1-distill-qwen-7b 131K 30 RPM, 60K TPM
SambaNova DeepSeek-V3.1 deepseek-v3-1 128K 20 RPM, 20 RPD, 200K TPD
DeepSeek-V3.2 (Preview) deepseek-v3-2-preview 128K 20 RPM, 20 RPD, 200K TPD
MiniMax-M2.7 minimax-m2-7 128K 20 RPM, 20 RPD, 200K TPD
xAI grok-4.3 grok-4-3 1M Credit-based
grok-4.1-fast grok-4-1-fast 2M Credit-based
grok-3-mini grok-3-mini 131K Credit-based
Chutes.ai DeepSeek-R1 deepseek-ai/DeepSeek-R1 131K Community-powered, no h..
Llama 3.1 70B meta-llama/Meta-Llama-3.1-70B-Instruct 131K Community-powered, no h..
Glhf.chat Llama 3.1 70B meta-llama/Meta-Llama-3.1-70B-Instruct 131K Unlimited for free models
Mixtral 8x7B mistralai/Mixtral-8x7B-Instruct-v0.1 32K Unlimited for free models
Grok (xAI) Grok-2 grok-2 131K $25/month free credits,..
Grok-2 Mini grok-2-mini 131K $25/month free credits,..
AI21 Labs Jamba Large 1.7 jamba-large-1-7 256K 200 RPM, 10 RPS
Jamba Mini 2 jamba-mini-2 256K 200 RPM, 10 RPS
DeepSeek deepseek-chat (V3.2) deepseek-chat-v3-2 128K Dynamic
deepseek-reasoner (R1) deepseek-reasoner-r1 128K Dynamic
Nscale Llama-3.3-70B-Instruct llama-3-3-70b-instruct 128K Fair-use
DeepSeek-R1-Distill-Llama-70B deepseek-r1-distill-llama-70b 128K Fair-use
Nebius Qwen3-235B-A22B qwen3-235b-a22b 128K Tier-based

热门免费模型

Model Provider Context Weekly Usage
MiniMax: MiniMax M3.1 Flash (free) OpenRouter 1M 4967B tokens
NVIDIA: Nemotron 3 Ultra (free) OpenRouter 1M 4505B tokens
z-ai/glm-5.2 NVIDIA NIM 1M 2998B tokens
NVIDIA: Nemotron 3.5 Super VL (free) OpenRouter 1M 1167B tokens
Poolside: Laguna S 2.1 (free) OpenRouter 262K 992B tokens
NVIDIA: Nemotron 3.5 Lightning (free) OpenRouter 1M 931B tokens
Poolside: Laguna M.1 (free) OpenRouter 262K 768B tokens
Dots Studio: Dots3-Note Preview (free) OpenRouter 512K 703B tokens
NVIDIA: Nemotron 3 Super (free) OpenRouter 262K 680B tokens
Apodex: Apodex 1.1 Mini (free) OpenRouter 262K 284B tokens

参与贡献

欢迎贡献!

收录标准

模型列入本列表需满足: 1. 提供商明确提供免费层(不仅仅是试用额度) 2. API 公开可访问(无需候补、封闭内测、或逆向工程) 3. 试用额度:明确标注且最低 $1 额度


链接

许可证

MIT © open-free-llm-api


数据每日自动更新 · 最后更新: 2026-10-21