DeepSeek R1 Distill 70B on Groq is a distilled version of DeepSeek's reasoning model at the 70B scale, delivering chain-of-thought deliberation with Groq's ultra-fast LPU inference.
https://api.groq.com/openai/v1 deepseek-r1-distill-70b deepseek-r1-distill-70b is listed for chat, reasoning workloads and supports a 131K context window.
Check Groq's current endpoint status before integrating this listing. Use the alternatives table if the provider listing is unavailable.
We only found this deepseek-r1-distill-70b listing on Groq in the current catalog. Use the related models section for nearby alternatives.
| Provider | Model listing | Access | Context | API | Limits |
|---|---|---|---|---|---|
| | deepseek-r1-distill-70b | Check provider | 131K | OpenAI-style | 30 RPM, 14,400 RPD |
| Model | Provider | Context | Access |
|---|---|---|---|
| Moonshot Kimi K2 | Groq | 131K | Free tier |
| Moonshot Kimi K2 0905 | Groq | 131K | Free tier |
| groq/compound | Groq | 131K | Free tier |
| groq/compound-mini | Groq | 131K | Free tier |
| llama-4-scout-17b-16e-instruct | Groq | 131K | Check provider |
deepseek-r1-distill-70b is tagged for chat in this catalog and works with OpenAI-compatible client libraries.
deepseek-r1-distill-70b is tagged for reasoning in this catalog and works with OpenAI-compatible client libraries.
deepseek-r1-distill-70b appears in the free model catalog for Groq, but its current endpoint availability should be confirmed with the provider before use.
The model ID shown in this catalog is deepseek-r1-distill-70b.
The listed free tier limit is 30 RPM, 14,400 RPD. Limits can change per account tier, so confirm against the provider dashboard.
The listed context window is 131K tokens with up to 8K output tokens.
DeepSeek R1 Distill 70B on Groq is a distilled version of DeepSeek's reasoning model at the 70B scale, delivering chain-of-thought deliberation with Groq's ultra-fast LPU inference. The combination of a reasoning architecture with Groq's low latency makes it practical for interactive problem-solving — math, debugging, logic puzzles — where you want reasoned answers without long wait times. The 8K output cap is the main constraint, limiting how many reasoning steps can be produced. Free tier: 14,400 requests per day at 30 RPM. OpenAI SDK compatible; registration required, no credit card.
For API keys, setup steps, and provider-level limits, see the Groq provider page.