← Model list

DeepSeek R1 Distill Llama 70B

deepseek·deepseek/deepseek-r1-distill-llama-70b-2·GA·Closed·deepseek-thinking series

DeepSeek reasoning model for multi-step analysis, math, coding, and tools

At a glance
Reference price$0.99 / $0.99 per 1M
Cache read · DigitalOcean
Lowest paid$0.03 / $0.13
Helicone Gateway · 33× spread
Context32,678
⚠ Providers report 8,192–131,072; the table below is authoritative
Output limit8,192
Capabilities
ReasoningTool useStructured outputTemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
Text
Knowledge cutoff2024-10
Released / updated2025-01-23 / 2025-01-30

Quality & performanceArtificial Analysis · Intelligence Index v4.1

Intelligence9.8
Value178
Coding
Agentic
Output speed25 tok/s
TTFT1.02 s
Value formulaIQ 9.8 ÷ min blended $0.055 = 178

Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.

Available at 6 providers6 with public prices

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
Helicone
deepseek-r1-distill-llama-70b
Gateway$0.03$0.13128,0004,096
FastRouter
deepseek-ai/deepseek-r1-distill-llama-70b
Gateway$0.03$0.14131,072131,072
Alibaba (China)
deepseek-r1-distill-llama-70b
First-party$0.287$0.86132,76816,384
NovitaAI
deepseek/deepseek-r1-distill-llama-70b
Gateway$0.80$0.808,1928,192
Kilo Gateway
deepseek/deepseek-r1-distill-llama-70b
Gateway$0.80$0.808,1928,192
DigitalOcean
deepseek-r1-distill-llama-70b
Cloud$0.99$0.9932,6788,192

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Your usage cost

1Helicone$12.50
2FastRouter$13.00
3Alibaba (China)$100.45
4NovitaAI$200.00
5Kilo Gateway$200.00
6DigitalOcean$247.50
The cheapest paid channel is the only channel.

Benchmark

No upstream benchmark data for this model. For quality, see the Artificial Analysis intelligence score above.

Reasoning control

effort = noneeffort = higheffort = loweffort = mediumeffort = max

4 / 6 providers expose no reasoning control (reasoning_options: []).

Related models

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$0.99$02026-08-052026-08-132026-08-05 · Input list $0.802026-08-06 · Input list $0.802026-08-07 · Input list $0.802026-08-08 · Input list $0.802026-08-09 · Input list $0.802026-08-10 · Input list $0.802026-08-11 · Input list $0.802026-08-12 · Input list $0.802026-08-13 · Input list $0.992026-08-05 · Output list $0.802026-08-06 · Output list $0.802026-08-07 · Output list $0.802026-08-08 · Output list $0.802026-08-09 · Output list $0.802026-08-10 · Output list $0.802026-08-11 · Output list $0.802026-08-12 · Output list $0.802026-08-13 · Output list $0.992026-08-05 · Min blended $0.802026-08-06 · Min blended $0.802026-08-07 · Min blended $0.802026-08-08 · Min blended $0.802026-08-09 · Min blended $0.802026-08-10 · Min blended $0.802026-08-11 · Min blended $0.802026-08-12 · Min blended $0.802026-08-13 · Min blended $0.055