Pass IndexThe State of AISign in

R1 Distill Llama 70B

DeepSeek-R1-Distill-Llama-70B is a highly efficient language model that leverages knowledge distillation to achieve state-of-the-art performance.

text → text · made by DeepSeek

$0.1$0.4per Mtok in / out
ElectronHub · 12 sellers

Sold by 13 ways

SellerLaneRate
DigitalOcean cloudstandard$0.99per Mtok in$0.99per Mtok outmodels.dev · read 2026-09-16
ElectronHub aggregatorstandard$0.1per Mtok in$0.4per Mtok outapi.electronhub.ai · read 2026-09-16
Requesty 2 ways$0.23per Mtok in$0.69per Mtok out$0.23per Mtok cached
Requesty aggregatordeepinfra$0.23per Mtok in$0.69per Mtok out$0.23per Mtok cachedrouter.requesty.ai · read 2026-08-28
Requesty aggregatornovita$0.8per Mtok in$0.8per Mtok out$0.8per Mtok cachedrouter.requesty.ai · read 2026-08-28
Nscale aggregatorstandard$0.38per Mtok in$0.38per Mtok outraw.githubusercontent.com · read 2026-09-16
DeepInfra aggregatorstandard$0.7per Mtok in$0.8per Mtok outapi.deepinfra.com · read 2026-08-25
SambaNova Cloud aggregatorstandard$0.7per Mtok in$1.4per Mtok outraw.githubusercontent.com · read 2026-09-16
Hugging Face Inference Providers aggregatornovita$0.8per Mtok in$0.8per Mtok outrouter.huggingface.co · read 2026-08-25
Novita AI aggregatorstandard$0.8per Mtok in$0.8per Mtok outapi.novita.ai · read 2026-08-25
OpenRouter aggregatorstandard$0.8per Mtok in$0.8per Mtok outopenrouter.ai · read 2026-08-24
Fireworks AI aggregatorstandard$0.9per Mtok in$0.9per Mtok outraw.githubusercontent.com · read 2026-09-16
Together AI aggregatorstandard$2per Mtok in$2per Mtok outraw.githubusercontent.com · read 2026-09-16
PPIO aggregatorstandard$5.8per Mtok in$5.8per Mtok outapi.ppinfra.com · read 2026-09-16

Measured 4 standings

PlaceBoardMetricScore
23rdof 54Live bench — Epoch AIGlobal average54.5
23rdof 108Math level 5 — Epoch AImean_score89.898
180thof 290OTIS Mock AIME 2024-2025mean_score51.389
215thof 313GPQA Diamondmean_score55.745

About

R1 Distill Llama 70B — a text model from DeepSeek, sold by 12 companies from $0.1 in and $0.4 out per million tokens, placed 23rd of 108 on Math level 5 — Epoch AI.

It takes text and returns text, with a context window of 131,072 tokens. It was published in 2025. Its sellers say it can reason step by step. The catalogue files it under reasoning. Twelve companies sell it. The cheapest is $0.1 in and $0.4 out per million tokens at ElectronHub. Beside the standard rate there is a separately routed lane. It has been measured on 4 boards, and stands best at 23rd of 108 on Math level 5 — Epoch AI.

Every current figure

Maker
DeepSeek
Register
model
Takes
text
Returns
text
Context
131,072 tokens
Published
2025
Parameters
71 billion
Licence
not read
Sellers
12
Maker's own price
not read
Price
$0.1 in and $0.4 out per million tokens — ElectronHub
Boards
4
Best place
23rd of 108 — Math level 5 — Epoch AI

Known as 4 names

deepseek-ai/DeepSeek-R1-Distill-Llama-70Bdeepseek/deepseek-r1-distill-llama-70bdeepinfra/deepseek-ai/DeepSeek-R1-Distill-Llama-70Bnovita/deepseek/deepseek-r1-distill-llama-70b