DeepSeek

R1 Distill Llama 70B

deepseek/deepseek-r1-distill-llama-70b

JSON

Specification

Published by the vendor; the platform bills at the target's declared price.

R1 Distill Llama 70B

reasoning open weights

DeepSeek deepseek/deepseek-r1-distill-llama-70b

DeepSeek R1 Distill Llama 70B is a distilled large language model based on [Llama-3.3-70B-Instruct](/meta-llama/llama-3.3-70b-instruct), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). The model combines advanced distillation techniques to achieve high performance across...

Input $/1M: $0.80
Output $/1M: $0.80
Context: 8K
Max output: 7K
Released: Jan 23, 2025
Modalities: text

On this deployment

No routing target resolves to this model yet. Declare one and the router picks it up without retraining.

Not routable here yet

Add a target with metadata.model set to this id.

targets.yamlyaml

# targets.yaml - declare a target that runs R1 Distill Llama 70B
targets:
  - id: deepseek-r1-distill-llama-70b
    kind: llm
    name: R1 Distill Llama 70B
    metadata:
      model: deepseek/deepseek-r1-distill-llama-70b          # links the target to this catalogue entry
    capabilities:
      domains: [general]
      supports_tools: false
      context_window: 8192
    cost:
      usd_per_1k_tokens: 0.000800

Price among DeepSeek models

Input list price per million tokens; R1 Distill Llama 70B is the 10th cheapest of 13 listed.

More from DeepSeek

Other models by the same vendor in the catalogue.