Pass IndexThe State of AISign in

Qwen2.5 Coder 32B Instruct

Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen).

text → text · made by Alibaba

$0.05$0.1per Mtok in / out
Lambda · 11 sellers

Sold by 12 ways

SellerLaneRate
Lambda aggregatorstandard$0.05per Mtok in$0.1per Mtok outraw.githubusercontent.com · read 2026-09-16
DeepInfra aggregatorstandard$0.06per Mtok in$0.15per Mtok outapi.deepinfra.com · read 2026-08-25
Hugging Face Inference Providers 2 ways$0.06per Mtok in$0.2per Mtok out
Hugging Face Inference Providers aggregatorstandard$0.06per Mtok in$0.2per Mtok outmodels.dev · read 2026-09-16
Hugging Face Inference Providers aggregatornscale$0.06per Mtok in$0.2per Mtok outrouter.huggingface.co · read 2026-08-25
Nscale aggregatorstandard$0.06per Mtok in$0.2per Mtok outraw.githubusercontent.com · read 2026-09-16
Requesty aggregatordeepinfra$0.07per Mtok in$0.16per Mtok out$0.07per Mtok cachedrouter.requesty.ai · read 2026-08-28
Hyperbolic aggregatorstandard$0.12per Mtok in$0.3per Mtok outraw.githubusercontent.com · read 2026-09-16
Cloudflare aggregatorstandard$0.66per Mtok in$1per Mtok outmodels.dev · read 2026-09-16
OpenRouter aggregatorstandard$0.66per Mtok in$1per Mtok outopenrouter.ai · read 2026-08-24
ElectronHub aggregatorstandard$0.8per Mtok in$0.8per Mtok outapi.electronhub.ai · read 2026-09-16
Together AI aggregatorstandard$0.8per Mtok in$0.8per Mtok outraw.githubusercontent.com · read 2026-09-16
Fireworks AI aggregatorstandard$0.9per Mtok in$0.9per Mtok outraw.githubusercontent.com · read 2026-09-16

Measured 4 standings

PlaceBoardMetricScore
3rdof 170Gsm8k — Epoch AIEM0.93
35thof 54Live bench — Epoch AIGlobal average46.23
60thof 69Aider polyglot coding leaderboardPercent correct16.4
63rdof 72Aider polyglot — Epoch AIPercent correct16.4

About

Qwen2.5 Coder 32B Instruct — a text model from Alibaba, sold by 11 companies from $0.05 in and $0.1 out per million tokens, placed 3rd of 170 on Gsm8k — Epoch AI.

It takes text and returns text, with a context window of 32,768 tokens. It was published in November 2024. The catalogue files it under code. Eleven companies sell it. The cheapest is $0.05 in and $0.1 out per million tokens at Lambda. Beside the standard rate there is a separately routed lane. It has been measured on 4 boards, and stands best at 3rd of 170 on Gsm8k — Epoch AI.

Every current figure

Maker
Alibaba
Register
model
Takes
text
Returns
text
Context
32,768 tokens
Published
November 2024
Parameters
33 billion
Licence
not read
Sellers
11
Maker's own price
not read
Price
$0.05 in and $0.1 out per million tokens — Lambda
Boards
4
Best place
3rd of 170 — Gsm8k — Epoch AI

Known as 3 names

Qwen/Qwen2.5-Coder-32B-Instructqwen/qwen-2.5-coder-32b-instructdeepinfra/Qwen/Qwen2.5-Coder-32B-Instruct