Skip to main content
GitHub Models provides free access to state-of-the-art language models, with rate limits dependent on your GitHub Copilot subscription tier.

​
Overview

GitHub Models offers access to the latest AI models from leading providers including OpenAI, Anthropic, Meta, Mistral, and more.
Extremely restrictive input/output token limits - Models have significantly lower token limits compared to direct provider access.

​
Rate Limits

Rate limits are dependent on your GitHub Copilot subscription tier:
  • Free tier: Limited requests
  • Pro tier: Increased limits
  • Pro+ tier: Higher limits
  • Business tier: Enterprise limits
  • Enterprise tier: Maximum limits
View detailed rate limits

​
Available Models

​
OpenAI Models

  • OpenAI GPT-4.1
  • OpenAI GPT-4.1-mini
  • OpenAI GPT-4.1-nano
  • OpenAI GPT-4o
  • OpenAI GPT-4o mini
  • OpenAI gpt-5
  • OpenAI gpt-5-chat (preview)
  • OpenAI gpt-5-mini
  • OpenAI gpt-5-nano
  • OpenAI o1
  • OpenAI o1-mini
  • OpenAI o1-preview
  • OpenAI o3
  • OpenAI o3-mini
  • OpenAI o4-mini

​
Meta Llama Models

  • Llama 4 Maverick 17B 128E Instruct FP8
  • Llama 4 Scout 17B 16E Instruct
  • Llama-3.2-11B-Vision-Instruct
  • Llama-3.2-90B-Vision-Instruct
  • Llama-3.3-70B-Instruct
  • Meta-Llama-3.1-405B-Instruct
  • Meta-Llama-3.1-8B-Instruct

​
Mistral Models

  • Codestral 25.01
  • Ministral 3B
  • Mistral Medium 3 (25.05)
  • Mistral Small 3.1

​
DeepSeek Models

  • DeepSeek-R1
  • DeepSeek-R1-0528
  • DeepSeek-V3-0324

​
xAI Models

  • Grok 3
  • Grok 3 Mini

​
Other Models

  • AI21 Jamba 1.5 Large
  • Cohere Command A
  • Cohere Command R 08-2024
  • Cohere Command R+ 08-2024
  • MAI-DS-R1
  • Phi-4
  • Phi-4-mini-instruct
  • Phi-4-mini-reasoning
  • Phi-4-multimodal-instruct
  • Phi-4-reasoning

​
Embedding Models

  • OpenAI Text Embedding 3 (large)
  • OpenAI Text Embedding 3 (small)

​
API Usage

import openai

client = openai.OpenAI(
    base_url="https://models.inference.ai.azure.com",
    api_key="YOUR_GITHUB_TOKEN"
)

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[
        {"role": "user", "content": "Hello, how are you?"}
    ]
)

print(response.choices[0].message.content)

​
Getting Started

1

GitHub Account

Sign in to your GitHub account
2

Visit GitHub Models

Go to github.com/marketplace/models
3

Generate Token

Create a personal access token with appropriate permissions
4

Start Building

Use the Azure OpenAI-compatible endpoint

​
Key Features

Latest Models

Access to cutting-edge models from multiple providers

GitHub Integration

Seamless integration with GitHub workflows

Multiple Providers

OpenAI, Meta, Mistral, Anthropic, and more

Flexible Tiers

Scale with GitHub Copilot subscription

​
Limitations

  • Extremely restrictive token limits per request
  • Rate limits vary by subscription tier
  • Primarily designed for prototyping, not production
  • Free tier has very limited access

​
Use Cases

  • Prototyping: Test different models quickly
  • Model Comparison: Evaluate multiple providers
  • GitHub Integration: Build AI-powered GitHub actions
  • Development: Develop with latest models

​
Subscription Benefits

TierAccess Level
FreeVery limited requests
Copilot ProEnhanced limits
Copilot Pro+Higher limits
Copilot BusinessEnterprise limits
Copilot EnterpriseMaximum limits

​
Additional Resources

GitHub Models

Browse available models

Documentation

Official documentation

Rate Limits

Detailed rate limit information

Copilot Pricing

Subscription options

Build docs developers (and LLMs) love

Get started for freeTalk to us