DeepSeek R1 Distill Llama 70B on OVHcloud AI Endpoints combines DeepSeek's reasoning distillation with Llama's 70B architecture, delivered from OVHcloud's European infrastructure.
https://inference.api.nscale.com/v1 deepseek-r1-distill-llama-70b DeepSeek-R1-Distill-Llama-70B is listed for chat, reasoning workloads and supports a 128K context window.
Check Nscale'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-llama-70b listing on Nscale in the current catalog. Use the related models section for nearby alternatives.
| Provider | Model listing | Access | Context | API | Limits |
|---|---|---|---|---|---|
| | DeepSeek-R1-Distill-Llama-70B | Check provider | 128K | Native | Fair-use |
| Model | Provider | Context | Access |
|---|---|---|---|
| Llama-3.3-70B-Instruct | Nscale | 128K | Check provider |
DeepSeek-R1-Distill-Llama-70B is tagged for chat in this catalog.
DeepSeek-R1-Distill-Llama-70B is tagged for reasoning in this catalog.
DeepSeek-R1-Distill-Llama-70B appears in the free model catalog for Nscale, but its current endpoint availability should be confirmed with the provider before use.
The model ID shown in this catalog is deepseek-r1-distill-llama-70b.
The listed free tier limit is Fair-use. Limits can change per account tier, so confirm against the provider dashboard.
The listed context window is 128K tokens with up to 32K output tokens.
DeepSeek R1 Distill Llama 70B on OVHcloud AI Endpoints combines DeepSeek's reasoning distillation with Llama's 70B architecture, delivered from OVHcloud's European infrastructure. With chain-of-thought reasoning, 131K context, and 32K output, it is well-suited for complex analytical tasks that benefit from step-by-step deliberation. OpenAI-compatible API; registration required. A good choice for EU developers who need reasoning capabilities with GDPR-compliant hosting.
For API keys, setup steps, and provider-level limits, see the Nscale provider page.