Pass IndexThe State of AISign in

DeepSeek-R1-Distill-Qwen-1.5B

We introduce our first-generation reasoning models, DeepSeek-R1-Zero and DeepSeek-R1.

text → text · made by DeepSeek

$0.09$0.09per Mtok in / out
Nscale · 3 sellers

Sold by 3 ways

SellerLaneRate
Nscale aggregatorstandard$0.09per Mtok in$0.09per Mtok outraw.githubusercontent.com · read 2026-09-16
Fireworks AI aggregatorstandard$0.1per Mtok in$0.1per Mtok outraw.githubusercontent.com · read 2026-09-16
Together AI aggregatorstandard$0.18per Mtok in$0.18per Mtok outraw.githubusercontent.com · read 2026-09-16

Measured 3 standings

PlaceBoardMetricScore
215thof 222Chess puzzles — Epoch AImean_score0
229thof 290OTIS Mock AIME 2024-2025mean_score21.389
282ndof 313GPQA Diamondmean_score33.586

About

DeepSeek-R1-Distill-Qwen-1.5B — a text model from DeepSeek, sold by 3 companies from $0.09 in and $0.09 out per million tokens, placed 229th of 290 on OTIS Mock AIME 2024-2025.

It takes text and returns text, with a context window of 32,768 tokens. It was published in January 2025. Its sellers say it can reason step by step and call a tool. The catalogue files it under reasoning. Its weights are published under MIT, so you may run it on your own machine, or buy it from whoever serves it cheapest. Three companies sell it. The cheapest is $0.09 in and $0.09 out per million tokens at Nscale. It has been measured on 3 boards, and stands best at 229th of 290 on OTIS Mock AIME 2024-2025.

Every current figure

Maker
DeepSeek
Register
model
Takes
text
Returns
text
Context
32,768 tokens
Longest answer
16,384 tokens
Published
January 2025
Parameters
1.8 billion · read from its own weights
Licence
mit
Sellers
3
Maker's own price
not read
Price
$0.09 in and $0.09 out per million tokens — Nscale
Boards
3
Best place
229th of 290 — OTIS Mock AIME 2024-2025

Known as 1 name

deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B