Call the full DeepSeek R1 reasoning model free via OpenRouter's OpenAI-compatible :free tier — no credit card required.
DeepSeek R1 is the open reasoning model that put DeepSeek on the map, with strong chain-of-thought performance and broad free availability. The providers below cover the free options.
For a stronger free upgrade, we recommend DeepSeek V4 Pro — a 1.6T-parameter MoE that rivals top proprietary models in coding, also free here.
OpenRouter serves the full DeepSeek R1 (not a distilled version) behind a single OpenAI-compatible endpoint. Use the model id `deepseek/deepseek-r1:free` — it costs nothing and needs no credit card.
cURL:
```bash curl https://openrouter.ai/api/v1/chat/completions \ -H "Authorization: Bearer $OPENROUTER_API_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"deepseek/deepseek-r1:free","messages":[{"role":"user","content":"Explain the Monty Hall problem."}]}' ```
Python (OpenAI SDK):
```python from openai import OpenAI
client = OpenAI(base_url="https://openrouter.ai/api/v1", api_key="OPENROUTER_API_KEY") resp = client.chat.completions.create( model="deepseek/deepseek-r1:free", messages=[{"role": "user", "content": "Explain the Monty Hall problem."}], ) print(resp.choices[0].message.content) ```
Free traffic shares capacity with paid users, so expect occasional rate-limit (429) responses at peak — retry with backoff.
No examples provided yet.
