R1 Distill Llama 70B

Open weight

DeepSeek · Released January 2025 · Knowledge cutoff July 2024

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...

It is part of DeepSeek's open-weight line, known for delivering near-frontier reasoning and coding quality at a fraction of typical frontier pricing.

Facts and pricing

Provider
DeepSeek
Context window
128K tokens
Input price
8.8 credits / 1M tokens ($0.80 raw)
Output price
8.8 credits / 1M tokens ($0.80 raw)
Vision (image input)
No
Tool calling
No
Extended reasoning
No

Credits are what Zeplik bills: 1 credit = $0.10, computed from the raw provider rate with a 1.10x margin. Raw prices shown per 1M tokens.

Try R1 Distill Llama 70B now

Ask R1 Distill Llama 70B anything. Your prompt opens in the Zeplik app with this model selected.

R1 Distill Llama 70B

What R1 Distill Llama 70B is best for

Example prompts

Prompts that suit a open weight model like R1 Distill Llama 70B:

DeepSeek family

ModelContextInput cr/MOutput cr/MReleased
DeepSeek V4 Pro1.0M4.89.6April 2026
DeepSeek V4 Flash1.0M0.992.0April 2026
DeepSeek V3.2131K2.53.8December 2025
DeepSeek V3.2 Exp164K3.04.5September 2025
DeepSeek V3.1 Terminus164K3.010.5September 2025
DeepSeek V3.1164K2.38.7August 2025
R1 0528164K5.523.7May 2025
DeepSeek V3 0324164K2.69.9March 2025
R1 Distill Llama 70B128K8.88.8January 2025
R1164K7.727.5January 2025

All 11 DeepSeek models

Frequently asked questions

What is R1 Distill Llama 70B?
R1 Distill Llama 70B is an AI model by DeepSeek. 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...
How much does R1 Distill Llama 70B cost on Zeplik?
Input tokens cost 8.8 credits per million and output tokens 8.8 credits per million (1 credit = $0.10; the raw provider rates are $0.80 and $0.80 per million). New accounts start with free credits.
How long can a conversation with R1 Distill Llama 70B be?
R1 Distill Llama 70B has a 128K-token context window (128,000 tokens), which covers the conversation plus any documents you attach.
Does R1 Distill Llama 70B support images and tools?
R1 Distill Llama 70B is text-only and does not support tool calling.

Related models

DeepSeek V4 ProOpen weight

DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...

1.0M ctx9.6 cr/M outApril 2026
DeepSeek V4 FlashFast and light

DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...

1.0M ctx2.0 cr/M outApril 2026
DeepSeek V3.2Open weight

DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...

131K ctx3.8 cr/M outDecember 2025
DeepSeek V3.2 ExpOpen weight

DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...

164K ctx4.5 cr/M outSeptember 2025
DeepSeek V3.1 TerminusOpen weight

DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's...

164K ctx10.5 cr/M outSeptember 2025
DeepSeek V3.1Open weight

DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...

164K ctx8.7 cr/M outAugust 2025
R1 Distill Llama 70B - DeepSeek AI Model | Zeplik Chat