AI Observatory / Model Radar DeepSeek / deepseek/deepseek-r1-distill-llama-70b

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...

131,072 Context
16,384 Max output
$0.70 / 1M Prompt price
2025-01-23 Created
01 / Snapshot

Pricing, context, modalities, and parameters.

Model Radar detail pages stay neutral and operator-readable: core metadata first, then workflow fit.

Provider DeepSeek Input modalities text
Output modalities text Prompt price $0.70 / 1M
Completion price $0.80 / 1M Request price N/A
Context length 131,072 Max completion tokens 16,384
Supported parameters frequency_penalty, include_reasoning, logit_bias, max_tokens, min_p, presence_penalty, reasoning, repetition_penalty, response_format, seed, stop, temperature, top_k, top_p
Best for deepseek/deepseek-r1-distill-llama-70b

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...

Deep analysis High-volume usage low-cost
03 / Colophon

Routes and exits.

Each model page stays simple: overview, compare, related models, then back to the public hub.