Pass IndexThe State of AISign in

DeepSeek R1 (Turbo)

We introduce DeepSeek-R1, which incorporates cold-start data before RL.

text → text · made by DeepSeek

$0.7$2.5per Mtok in / out
Novita AI · 4 sellers

Sold by 4 ways

SellerLaneRate
Novita AI aggregatorstandard$0.7per Mtok in$2.5per Mtok outapi.novita.ai · read 2026-08-25
Requesty aggregatornovita$0.7per Mtok in$2.5per Mtok out$0.7per Mtok cachedrouter.requesty.ai · read 2026-08-28
DeepInfra aggregatorstandard$1per Mtok in$3per Mtok outapi.deepinfra.com · read 2026-08-25
PPIO aggregatorstandard$4per Mtok in$16per Mtok outapi.ppinfra.com · read 2026-09-10

About

DeepSeek R1 (Turbo) — a text model from DeepSeek, sold by 4 companies from $0.7 in and $2.5 out per million tokens.

It takes text and returns text, with a context window of 40,960 tokens. It was published in March 2025. Its sellers say it can reason step by step and call a tool. The catalogue files it under chat. Four companies sell it. The cheapest is $0.7 in and $2.5 out per million tokens at Novita AI. Beside the standard rate there is a separately routed lane.

Every current figure

Maker
DeepSeek
Register
model
Takes
text
Returns
text
Context
40,960 tokens
Longest answer
16,000 tokens
Published
March 2025
Sellers
4
Maker's own price
not read
Price
$0.7 in and $2.5 out per million tokens — Novita AI

Known as 3 names

deepseek-ai/DeepSeek-R1-Turbodeepseek/deepseek-r1-turbonovita/deepseek/deepseek-r1-turbo