deepseek

DeepSeek: R1 Distill Llama 70B

The DeepSeek: R1 Distill Llama 70B is a text-based AI model developed by deepseek. It supports input and output in text modality only, with a maximum context length of 8192 tokens and completion limit of 7372 tokens. The model also enables reasoning capabilities. Considering its pricing, the DeepSeek: R1 Distill Llama 70B may be suitable for users who require text-based AI processing and have a budget to spend on input and output tokens at $0.8 per million tokens each. With a blended benchmark score of 8.3 across one independent test, it holds some level of performance standing, but further evaluation would be needed to confirm its value in specific applications.

Quality Score
60/100
price + capability + benchmarks
Input Price
$0.80
per 1M tokens · checked 2026-09-23
Output Price
$0.80
per 1M tokens · checked 2026-09-23
Context Window
8,192
tokens

Benchmark results

Independent, published benchmarks. Blended score 7.6 across 1 benchmark, last refreshed 2026-09-23. How scoring works →

BenchmarkMeasuresScore
AI Index broad capability composite 13.0
Model ID
deepseek/deepseek-r1-distill-llama-70b
Vendor
deepseek
Released
January 2025
Tokenizer
Llama3
Input Modalities
text
Output Modalities
text
Max Output
7,372 tokens
Tool Calling
not supported
Structured Output
not supported
Reasoning Mode
✓ supported
Vision
text only
Audio
no
Moderated
no

What it costs in practice

Computed from the current $0.80/M input and $0.80/M output rates. Run your own numbers →

JobTokensCost
Summarize a 50-page report 30k in / 1.5k out $0.03
Classify 1,000 customer emails 500k in / 50k out $0.44
A month of a busy support chatbot 5M in / 2M out $5.60

Price & spec history

Tracked daily by PicksByModel since 2026-07-17.

DateInput /MOutput /MContext
2026-07-22 $0.80 $0.80 8,192
2026-07-17 $0.80 $0.80 128,000

Similar models

Quick answers

How much does DeepSeek: R1 Distill Llama 70B cost?
$0.80 per million input tokens and $0.80 per million output tokens.
What is DeepSeek: R1 Distill Llama 70B's context window?
8,192 tokens, roughly 12 pages of text in a single request.
Does DeepSeek: R1 Distill Llama 70B support tool calling?
It supports a reasoning mode.
Can DeepSeek: R1 Distill Llama 70B process images?
No, it is text-only on the input side.

The Model Movers Report

One email every Friday, built from this site's own rankings: the current top five by benchmark score, every model released in the last seven days, and one note worked out from that week's numbers. You can unsubscribe from any issue with one click.