Skip to main content

DeepSeek R1 Distill Llama 70B

DeepSeekLlamaOpen WeightMIT · Commercial OK

Description

DeepSeek-R1 is the first-generation reasoning model built atop DeepSeek-V3 (671B total parameters, 37B activated per token). It incorporates large-scale reinforcement learning (RL) to enhance its chain-of-thought and reasoning capabilities, delivering strong performance in math, code, and multi-step reasoning tasks.

Release Date
2025-01-20
Parameters
70.6B
Context Length
164K
Modalities
text

Capability Radar

80
general
60
coding
90
reasoning
60
scienceest.
81
agents
0
multimodal

Science is estimated from LLM Stats science scores or reasoning when no dedicated science benchmarks are available.

Rankings

No ranking data available

Benchmark Scores (LLM Stats)

(LLM Stats (zeroeval))

Math

MATH-50094.5%SR
AIME 202486.7%SR

Reasoning

GPQANYU + Cohere + Anthropic (2023)65.2%SR
LiveCodeBench57.5%SR

AA Evaluation Indices

(Artificial Analysis)

No AA evaluation data available

LLM Stats Category Scores

(LLM Stats (zeroeval))
Math
90
Reasoning
80
General
80
Physics
70
Biology
70
Chemistry
70
Code
60

Pricing

Input Price$0.7 / 1M tokens
Output Price$1.1 / 1M tokens
Blended Price (3:1)$0.45023 / 1M tokens

Speed

No speed data available

Provider Price Ranking

Provider Price Ranking

3 providers

Cheapest: HeliconeMost Expensive: DeepSeek
ProviderInputOutput
1HeliconeCheapest
$0.03
$0.13
2Alibaba (China)
$0.287
$0.861
3DeepSeekPRIMARY
$0.7
$1.1

Compare pricing across different API providers for this model.

External Sources