Classic open reasoning model for transparent math, coding, and deliberate problem solving
https://models.github.ai/inference deepseek-r1 | Benchmark | Score | Metric | Date |
|---|---|---|---|
| Aider Polyglot | 56.9 | percent correct | 2025-01-20 |
| Artificial Analysis Coding Index | 15.9 | index | 2026-03-11 |
| SciCode | 35.7 | percent correct | 2026-03-11 |
| Terminal-Bench Hard | 6.1 | success rate | 2026-03-11 |
DeepSeek-R1 is listed for chat, reasoning workloads and supports a 64K context window.
Check GitHub Models's current endpoint status before integrating this listing. Use the alternatives table if the provider listing is unavailable.
We found 2 provider listings for deepseek-r1. Check model ID, quota, pricing, and API format before switching providers.
| Provider | Model listing | Access | Context | API | Limits |
|---|---|---|---|---|---|
| | DeepSeek-R1 | Check provider | 64K | OpenAI-style | 15 RPM, 150 RPD |
| | DeepSeek-R1 | Free tier | 131K | OpenAI-style | Community-powered, no hard cap |
| Model | Provider | Context | Access |
|---|---|---|---|
| DeepSeek-R1 | Chutes.ai | 131K | Free tier |
| Phi-4 | GitHub Models | 131K | Free tier |
| Mistral Large (24.11) | GitHub Models | 131K | Free tier |
| AI21 Jamba 1.5 Large | GitHub Models | 256K | Free tier |
| gpt-5 | GitHub Models | 200K | Check provider |
DeepSeek-R1 is tagged for chat in this catalog and works with OpenAI-compatible client libraries.
DeepSeek-R1 is tagged for reasoning in this catalog and works with OpenAI-compatible client libraries.
DeepSeek-R1 appears in the free model catalog for GitHub Models, but its current endpoint availability should be confirmed with the provider before use.
The model ID shown in this catalog is deepseek-r1.
The listed free tier limit is 15 RPM, 150 RPD. Limits can change per account tier, so confirm against the provider dashboard.
The listed context window is 64K tokens with up to 8K output tokens.
DeepSeek-R1 is a reasoning-specialized model that uses chain-of-thought deliberation before producing final answers, making it particularly strong at math, logic puzzles, and multi-step coding problems. Available free on GitHub Models with 64K context and 8K output, it is fully OpenAI SDK-compatible — swap in the GitHub Models base URL and your GitHub token to use it with any OpenAI-compatible tool. The free tier allows up to 15 RPM and 150 requests per day, somewhat more generous than the GPT-4 family on GitHub Models. If your task benefits from explicit step-by-step reasoning rather than fast single-pass generation, R1 is one of the strongest free reasoning models available.
For API keys, setup steps, and provider-level limits, see the GitHub Models provider page.