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
8K
Modalities
text

Capability Radar

30
general
28
coding
62
reasoning
30
scienceest.
52
agents
0
multimodal

Science uses a reasoning proxy when dedicated science benchmarks are unavailable.

Rankings

Domain#RankScoreSource
Code Ranking411
15.0
AA
General Ranking349
32.0
AA
Math Reasoning137
65.0
AA
Science356
32.0
AA

Benchmark Scores (LLM Stats)

Biology

GPQA65.2%SR

Code

LiveCodeBench57.5%SR

Math

MATH-50094.5%SR
AIME 202486.7%SR

AA Evaluation Indices

Math Index
53.7
Intelligence Index
9.9
Math 500
0.9
Mmlu Pro
0.8
Aime
0.7
Aime 25
0.5
Gpqa
0.4
Scicode
0.3
Ifbench
0.3
Livecodebench
0.3
Tau2
0.2
Lcr
0.1
Hle
0.1
Terminalbench Hard
0.0

LLM Stats Category Scores

Math
90
Reasoning
80
Physics
70
Biology
70
Chemistry
70
General
60
Code
60

Pricing

Input Price$0.7 / 1M tokens
Output Price$1.05 / 1M tokens
Blended Price (3:1)$0.787 / 1M tokens

Speed

Tokens/sec40.4
Time to First Token0.46s
Time to Answer50.02s

Provider Price Ranking

Provider Price Ranking

10 providers

Cheapest: ChutesMost Expensive: DigitalOcean
ProviderInputOutput
1ChutesCheapest
$0.0272
$0.1087
2Helicone
$0.03
$0.13
3FastRouter
$0.03
$0.14
4Alibaba (China)
$0.287
$0.861
5DeepSeekPRIMARY
$0.7
$1.05
6NanoGPT
$0.7
$0.7
7Kilo Gateway
$0.7
$0.8
8OpenRouter
$0.8
$0.8
9NovitaAI
$0.8
$0.8
10DigitalOcean
$0.99
$0.99

Compare pricing across different API providers for this model.

External Sources