DeepSeek R1 distilled into Llama 70B architecture.
OffRail routes requests to the best providers that are able to handle your prompt size and parameters.
DeepSeek R1 distilled into Llama 70B architecture. You can access it through OffRail's OpenAI-compatible API with automatic provider routing, fallback, and cost analytics.
Pricing for DeepSeek R1 Distill Llama 70B on OffRail starts at $0.75 per million input tokens and $0.99 per million output tokens, depending on the provider. The pricing table above always reflects the current per-provider rates.
DeepSeek R1 Distill Llama 70B supports a context window of up to 131,072 tokens on its largest provider deployment.
DeepSeek R1 Distill Llama 70B is served by Groq through OffRail. Requests are automatically routed to the best available provider, with fallback when a provider has issues.
DeepSeek R1 Distill Llama 70B supports tool (function) calling and soft JSON output, but NOT strict JSON output schema (its upstream provider does not enforce it).
DeepSeek R1 Distill Llama 70B was released on January 20, 2025.