GitHub Models
permanent free · cloud_platform · verification: partially_verified (70%, doc_fetch, 2026-07-17) · setup guide →
The record
| Base URLs | https://models.github.ai/inference openai-compatible |
|---|---|
| API key required | yes |
| Credit card | no |
| Phone verification | no |
| May train on prompts | unknown |
| Quota | free_tier [rpm, rpd] “Low models (Copilot Free/Pro): 15 requests/minute, 150 requests/day, 8000 in / 4000 out tokens per request, 5 concurrent. High models (Free/Pro): 10 requests/minute, 50 requests/day, 8000 in / 4000 out tokens per request, 2 concurrent. Limits: Dependent on Copilot subscription tier (Free/Pro/Pro+/Business/Enterprise).” |
| Signup friction | 2 steps · ~5m to first key |
| Env var | GITHUB_TOKEN |
| Notes | Free prototyping tier for all GitHub users; 45+ models from multiple vendors. Chat completions endpoint confirmed at https://models.github.ai/inference/chat/completions (org-attributed variant: https://models.github.ai/orgs/ORG/inference/chat/completions). |
Models (5)
| model | capabilities | context | free | limits |
|---|---|---|---|---|
| deepseek/DeepSeek-R1 | chat, reasoning | 64,000 | yes | 15 rpm · 150 rpd |
| openai/gpt-4.1-mini | chat, tool_calling | 1,000,000 | yes | 15 rpm · 150 rpd |
| openai/gpt-4.1 | chat, tool_calling | 1,000,000 | yes | 10 rpm · 50 rpd |
| openai/gpt-4o | chat, vision, tool_calling | 128,000 | yes | 10 rpm · 50 rpd |
| openai/gpt-5 | chat, tool_calling, reasoning | 200,000 | yes | 10 rpm · 50 rpd |
Provenance
| source_github_models_docs | official_docs | trust: high | checked 2026-07-17 |
| source_repo_cheahjs | curated_repo | trust: medium_high | checked 2026-07-17 |
| source_repo_mnfst | curated_repo | trust: medium_high | checked 2026-07-17 |