DeepSeek R1

Free rate-limited DeepSeek R1 via GitHub Models — authenticate with a GitHub Token, no credit card.

Updated 8/30/20262 code examples

About the Model

Why Choose DeepSeek R1?

DeepSeek R1 is a reasoning model built for math, code, and multi-step problem solving. It delivers strong chain-of-thought outputs for structured verification.

How to Access for Free (via DeepSeek)

GitHub Models offers free, rate-limited access to DeepSeek R1 with a GitHub token. It is the simplest free route if you want full reasoning-model behavior without setting up a separate provider account.

Use this endpoint for math, debugging, and multi-step planning. Reasoning models can be slower than small chat models, so expect longer responses.

Try it in your browser

Pick a model, paste your own free key, and run. Your key is sent once to call the provider and never stored on our servers.

Pick a model, paste your own free key, and run. Your key is sent once to call the provider and never stored on our servers.

Code Examples

curl https://models.github.ai/inference/chat/completions \
  -H "Authorization: Bearer $GITHUB_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"model":"deepseek/DeepSeek-R1","messages":[{"role":"user","content":"Explain the Monty Hall problem step by step."}]}'

Community Feedback

Comments are tied to your GitHub account — sign in to join the discussion.