modelbenchmark.io

DeepSeek R1 Distill Llama 70B

DeepSeek · deepseek-r1-distill-llama-70b

Compare

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

Specification

most-agreed values

Context
8K
Max output
7K
Released
2025-01-30
Knowledge cutoff
2025-01
Retires
2026-03-20
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.80
Output
$0.80

Quality

3 benchmarks · 1 source

Composite
69th
percentile of 334 scored models
Rank
106 / 334
±0.06 sd
Evidence
3 × 1
one source, or fewer than 3 benchmarks
Effort range
one configuration only
reasoning42nd1/4 bench
math81st2/7 bench

Every score

one row per source and configuration — nothing averaged away

BenchmarkScoreConfigurationSourceRun
MATH level 589.9 ±0.7defaultEpoch AI2025-03-10
OTIS Mock AIME 2024-202551.4 ±6.1defaultEpoch AI2025-03-07
GPQA diamond55.7 ±3.0defaultEpoch AI2025-03-10

The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.

Available from 17 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
fastrouter · deepseek-ai$0.03$0.14131K131K
helicone$0.03$0.13128K4K
deepinfra$0.20$0.60131K131K
nebius$0.25$0.75128K128K
alibaba-cn$0.287$0.86133K16K
nscale$0.375$0.375
ovhcloud · ovhcloud$0.67$0.67131K131K
sambanova · sambanova$0.70$1.40131K131K2026-03-20
vercel_ai_gateway · vercel-ai-gateway$0.75$0.99131K131K
kilo$0.80$0.808K7K
novita$0.80$0.808K8K
novita-ai$0.80$0.808K8K
openrouter$0.80$0.808K7K
fireworks_ai$0.90$0.90131K131K
digitalocean$0.99$0.9933K8K
gradient_ai · gradient-ai$0.99$0.9933K8K
together_ai$2.00$2.00

Price history

append-only observations · a listing writes a row only when its price moves

DateHostField$/M
2026-09-02openrouterInput$0.80
2026-09-06openrouterInput$0.80
2026-09-02openrouterOutput$0.80
2026-09-06openrouterOutput$0.80

More from DeepSeek

most-hosted first