deepseek

DeepSeek: R1 Distill Llama 70B

DeepSeek R1 Distill Llama 70B is a text-focused AI model with an extensive context length of 8,192 tokens and supports reasoning but lacks structured output or tool integration. This model excels in handling complex textual queries and generating detailed responses within the same token limit. For those on a budget who prioritize performance without needing advanced features like structured outputs or interactive tools, DeepSeek R1 Distill Llama 70B stands out with its balanced pricing of $0.8 per million input and output tokens. Its benchmark score of 14.9 places it favorably in independent tests; however, the limited tool support might be a drawback for more complex use cases.

Quality Score
60/100
price + capability + benchmarks
Input Price
$0.80
per 1M tokens
Output Price
$0.80
per 1M tokens
Context Window
8,192
tokens

Benchmark results

Independent, published benchmarks. Blended score 14.9 across 1 benchmark, last refreshed 2026-08-02. How scoring works →

BenchmarkMeasuresScore
AI Index broad capability composite 16.4
Model ID
deepseek/deepseek-r1-distill-llama-70b
Vendor
deepseek
Released
January 2025
Tokenizer
Llama3
Input Modalities
text
Output Modalities
text
Max Output
8,192 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.