DeepSeek: R1 Distill Llama 70B

deepseek/deepseek-r1-distill-llama-70b

R1 Distill Llama 70B is a 70B open-weight model, ranking #195 of 235 on the TryAii Score. Its best showing is #13 on LiveBench. It's served by 2 independent hosts from $0.8/$0.8 per million input/output tokens — about the going rate for its score class.

Prompt $/1M

$0.800

Completion $/1M

$0.800

Context

8,192 tok

Best provider

35 tok/s · DeepInfra

Specs

Model id: deepseek/deepseek-r1-distill-llama-70b
Display name: DeepSeek: R1 Distill Llama 70B
Modality: text->text
Tokenizer: Llama3
Instruct type: deepseek-r1
Context length: 8,192
Max completion: 7,372
Prompt $/1M: $0.800
Completion $/1M: $0.800
Free tier: no

Capabilities

Function callingno
JSON modeno
System promptyes
Visionno
Moderatedno

Benchmark scores

Each axis is one benchmark, normalized to the best model in the field.

No benchmark data for this model.

Speed by provider

Provider	tok/s	TTFT	Total latency
DeepInfra	35	1,205 ms	1,358 ms
Novitafastest	20	927 ms	1,047 ms
deepseekfastest	—	—	—
Artificial Analysis	0	0 ms	—