GitHub Models - Free Prototyping Tier
Source: https://github.com/marketplace/models
Description
Create account to comment on specific lines or Sign in
+ 1 GitHub Models gives every GitHub user free, rate-limited access to 40+ AI models from OpenAI, Meta, DeepSeek, Mistral, Microsoft, Cohere, xAI, and AI21 Labs. No credit card, no Azure account, no separate API key signup — just your GitHub login. The free tier is designed for prototyping and experimentation, with strict per-model rate limits (e.g., 50 requests/day for GPT-4o). When you are ready for production, you can opt into pay-as-you-go billing or bring your own API key (BYOK).
No comments on this line yet.
+ 2
No comments on this line yet.
+
3
No comments on this line yet.
+ 4
No comments on this line yet.
+ 6
No comments on this line yet.
+ 7 1. Go to github.com/marketplace/models
No comments on this line yet.
+ 8 2. Sign in with any GitHub account (free accounts work)
No comments on this line yet.
+ 9 3. Playground — click any model to open an interactive chat playground. Works immediately, no setup required
No comments on this line yet.
+ 10 4. API access — go to Settings → Developer settings → Personal access tokens → Fine-grained tokens
No comments on this line yet.
+
11
5. Generate a new token with the models:read scope (this scope is required since May 2025)
No comments on this line yet.
+
12
6. Use the token with the API endpoint: https://models.github.ai/inference/chat/completions
No comments on this line yet.
+
13
7. Set the Authorization: Bearer <YOUR_TOKEN> header in your requests
No comments on this line yet.
+ 14
No comments on this line yet.
+ 15 Important:
No comments on this line yet.
+ 16 • No credit card or payment method required for the free tier
No comments on this line yet.
+ 17 • One GitHub account = one set of free rate limits
No comments on this line yet.
+ 18 • The playground works in-browser with zero configuration
No comments on this line yet.
+
19
• In GitHub Actions workflows, add models: read to the permissions block and use the built-in GITHUB_TOKEN
No comments on this line yet.
+ 20
No comments on this line yet.
+
21
No comments on this line yet.
+ 22
No comments on this line yet.
+ 24
No comments on this line yet.
+ 25 GitHub Models provides access to 40+ models across multiple providers. The catalog is continuously updated. Key models include:
No comments on this line yet.
+ 26
No comments on this line yet.
+ 28 ModelType
No comments on this line yet.
+ 29 GPT-5.2Latest flagship
No comments on this line yet.
+ 30 GPT-5.2-CodexLatest code-specialized
No comments on this line yet.
+ 31 GPT-5 / GPT-5.1Flagship models
No comments on this line yet.
+ 32 GPT-5 miniCompact flagship
No comments on this line yet.
+ 33 GPT-4.1 / 4.1 mini / 4.1 nanoProduction models (1M token context)
No comments on this line yet.
+ 34 GPT-4o / 4o miniMultimodal models
No comments on this line yet.
+ 35 o4-miniReasoning (improved o3-mini)
No comments on this line yet.
+ 36 o3 / o3-miniReasoning models
No comments on this line yet.
+ 37 o1Advanced reasoning
No comments on this line yet.
+ 38 Text Embedding 3 (large/small)Embedding models
No comments on this line yet.
+ 39
No comments on this line yet.
+ 41 ModelType
No comments on this line yet.
+ 42 Llama 4 Maverick 17B 128ELatest MoE model
No comments on this line yet.
+ 43 Llama 4 Scout 17B 16EMulti-doc summarization
No comments on this line yet.
+ 44 Llama 3.3 70B InstructGeneral purpose
No comments on this line yet.
+ 45 Llama 3.2 11B/90B VisionMultimodal
No comments on this line yet.
+ 46 Llama 3.1 405B / 8BLarge and small variants
No comments on this line yet.
+ 47
No comments on this line yet.
+ 49 ModelType
No comments on this line yet.
+ 50 DeepSeek-R1 / R1-0528Reasoning model
No comments on this line yet.
+ 51 DeepSeek-V3-0324General purpose
No comments on this line yet.
+ 52 MAI-DS-R1Microsoft-tuned DeepSeek-R1
No comments on this line yet.
+ 53
No comments on this line yet.
+ 55 ModelType
No comments on this line yet.
+ 56 Mistral Medium 3Mid-size model
No comments on this line yet.
+ 57 Mistral Small 3.1Multimodal, 128K context
No comments on this line yet.
+ 58 Ministral 3BUltra-compact
No comments on this line yet.
+ 59 Codestral 25.01Code-specialized
No comments on this line yet.
+ 60
No comments on this line yet.
+ 62 ModelType
No comments on this line yet.
+ 63 Phi-4 14BLow-latency SLM
No comments on this line yet.
+ 64 Phi-3.5 / Phi-4 mini3.8B parameter SLM
No comments on this line yet.
+ 65
No comments on this line yet.
+ 67 ModelType
No comments on this line yet.
+ 68 Claude Opus 4.5Most capable
No comments on this line yet.
+ 69 Claude Sonnet 4.5Balanced performance
No comments on this line yet.
+ 70 Claude Haiku 4.5Fast, lightweight
No comments on this line yet.
+ 71
No comments on this line yet.
+ 73 ModelProvider
No comments on this line yet.
+ 74 Grok 3 / Grok 3 MinixAI
No comments on this line yet.
+ 75 Cohere Command A (398B MoE)Cohere
No comments on this line yet.
+ 76 Cohere Command R / R+Cohere
No comments on this line yet.
+ 77 AI21 Jamba 1.5 LargeAI21 Labs
No comments on this line yet.
+ 78
No comments on this line yet.
+
79
Browse the full, up-to-date catalog at github.com/marketplace/models or use the REST API: GET /catalog/models.
No comments on this line yet.
+ 80
No comments on this line yet.
+
81
No comments on this line yet.
+ 82
No comments on this line yet.
+ 84
No comments on this line yet.
+ 85 Each model is classified into a rate limit tier (Low, High, or Embedding). You can find a model's tier on its marketplace page.
No comments on this line yet.
+ 86
No comments on this line yet.
+ 87 TierRequests/minRequests/dayTokens/request (input)Tokens/request (output)Concurrent requests
No comments on this line yet.
+ 88 High (e.g., GPT-4o, GPT-5, o3)10508,0004,0002
No comments on this line yet.
+ 89 Low (e.g., Phi-4, Llama 3.1 8B, Ministral 3B)151508,0004,0005
No comments on this line yet.
+ 90 Embedding (e.g., Text Embedding 3)1515064,000—5
No comments on this line yet.
+ 91
No comments on this line yet.
+ 92 Key details:
No comments on this line yet.
+ 93 • Limits apply per GitHub account, not per token or project
No comments on this line yet.
+ 94 • Limits may vary based on your GitHub Copilot plan (Free, Pro, Pro+, Business, Enterprise)
No comments on this line yet.
+ 95 • Limits are subject to change without notice
No comments on this line yet.
+ 96 • When you hit the limit, requests return HTTP 429 until the window resets
No comments on this line yet.
+ 97 • Token limits are per request, not per day — you cannot batch beyond the per-request cap
No comments on this line yet.
+ 98
No comments on this line yet.
+
99
No comments on this line yet.
+ 100
No comments on this line yet.
+ 102
No comments on this line yet.
+ 103 GitHub Models rate limits are connected to your GitHub Copilot plan. While all GitHub accounts get free access, your plan may affect the exact limits:
No comments on this line yet.
+ 104
No comments on this line yet.
+ 105 Copilot PlanPriceNotes
No comments on this line yet.
+ 106 Free$0/monthBase rate limits for GitHub Models
No comments on this line yet.
+ 107 Pro$10/monthHigher limits, 300 premium requests/month for Copilot features
No comments on this line yet.
+ 108 Pro+$39/monthHighest individual limits, 1,500 premium requests/month
No comments on this line yet.
+ 109 Business$19/user/monthOrganization-level, 300 premium requests/month
No comments on this line yet.
+ 110 Enterprise$39/user/monthFull enterprise features, 1,000 premium requests/month
No comments on this line yet.
+ 111
No comments on this line yet.
+ 112 Note: Copilot premium requests and GitHub Models rate limits are related but separate concepts. The Copilot premium request allowance covers Copilot Chat and coding agent usage, while GitHub Models rate limits govern direct API/playground inference.
No comments on this line yet.
+ 113
No comments on this line yet.
+
114
No comments on this line yet.
+ 115
No comments on this line yet.
+ 117
No comments on this line yet.
+ 118 When you outgrow the free tier, there are two paths:
No comments on this line yet.
+ 119
No comments on this line yet.
+ 121 • Opt in through your GitHub account settings
No comments on this line yet.
+ 122 • Unified pricing: $0.00001 USD per token unit
No comments on this line yet.
+ 123 • Token units = (input tokens x input multiplier) + (output tokens x output multiplier)
No comments on this line yet.
+ 124 • Multipliers vary by model (e.g., GPT-4o: 0.25x input, 1x output)
No comments on this line yet.
+ 125 • Example: 1M input + 1M output tokens on GPT-4o = ~$12.50
No comments on this line yet.
+ 126 • Billing is through your GitHub account, same as Copilot
No comments on this line yet.
+ 127
No comments on this line yet.
+ 129 • Connect your own OpenAI or Azure AI API key
No comments on this line yet.
+ 130 • Billing goes directly to your provider account
No comments on this line yet.
+ 131 • Access custom models and higher rate limits set by the provider
No comments on this line yet.
+ 132 • Rate limits are governed by your provider subscription, not GitHub
No comments on this line yet.
+ 133
No comments on this line yet.
+
134
No comments on this line yet.
+ 135
No comments on this line yet.
+ 137
No comments on this line yet.
+ 138 GitHub Models is more than just an API — it includes developer workflow features:
No comments on this line yet.
+ 139
No comments on this line yet.
+ 140 • Playground — interactive chat UI for testing any model with adjustable temperature, token limits, and system prompts
No comments on this line yet.
+
141
• Prompt files — save .prompt.yml files in your repo for version-controlled prompts with variables
No comments on this line yet.
+
142
• Evaluations — add testData and evaluators to prompt files for side-by-side model comparison
No comments on this line yet.
+
143
• GitHub Actions integration — call models from CI/CD workflows using the built-in GITHUB_TOKEN
No comments on this line yet.
+
144
• REST API — GET /catalog/models to list models, POST /inference/chat/completions for inference
No comments on this line yet.
+ 145 • Azure AI Inference SDK — compatible with the same SDK used for Azure OpenAI
No comments on this line yet.
+ 146
No comments on this line yet.
+
147
No comments on this line yet.
+ 148
No comments on this line yet.
+ 150
No comments on this line yet.
+ 151 • No separate Azure account needed — GitHub Models is powered by Azure AI under the hood, but you never need to create Azure resources for the free tier
No comments on this line yet.
+ 152 • Same API format as OpenAI — the inference endpoint uses the OpenAI-compatible chat completions format, so existing code often works with minimal changes
No comments on this line yet.
+
153
• Model switching is easy — just change the model parameter in your API call; the endpoint and auth stay the same
No comments on this line yet.
+ 154 • Students and OSS maintainers — qualifying users get free GitHub Copilot Pro, which may include enhanced GitHub Models limits
No comments on this line yet.
+ 155 • GitHub Actions caveat — model calls from Actions count against your account's rate limits just like direct API calls
No comments on this line yet.
+ 156 • Data privacy — prompts and outputs are processed within GitHub/Azure infrastructure; check GitHub's data policies for specifics on retention
No comments on this line yet.
+ 157 • Limits are strict — the 8K input / 4K output token cap per request means you cannot use the free tier for long-context tasks (e.g., summarizing large documents)
No comments on this line yet.
+ 158
No comments on this line yet.
+
159
No comments on this line yet.
+ 160
No comments on this line yet.
+ 161 Sources:
No comments on this line yet.
+ 162 • GitHub Models Marketplace
No comments on this line yet.
+ 163 • GitHub Models Features
No comments on this line yet.
+ 164 • Prototyping with AI Models - GitHub Docs
No comments on this line yet.
+ 165 • GitHub Models Quickstart
No comments on this line yet.
+ 166 • GitHub Models Billing
No comments on this line yet.
+ 167 • GitHub Models API - models:read Required
No comments on this line yet.
+ 168 • GitHub Models Pay-as-you-go
No comments on this line yet.
+ 169 • GitHub Copilot Plans & Pricing
No comments on this line yet.
+ 170 • REST API for Models Inference
No comments on this line yet.