Qwen3 235B A22B
Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models.
text → text · made by Alibaba
Sold by 15 ways
| Seller | Lane | Rate |
|---|---|---|
| IO.NET 0 ways | $0.11per Mtok in$0.6per Mtok out$0.055per Mtok cached$0.22per Mtok cache write | |
| IO.NET aggregatornot on the seller's list today | standard | $0.11per Mtok in$0.6per Mtok out$0.055per Mtok cached$0.22per Mtok cache writemodels.dev · read 2026-08-27 |
| DeepInfra aggregator | standard | $0.18per Mtok in$0.54per Mtok outapi.deepinfra.com · read 2026-08-25 |
| Hugging Face Inference Providers 2 ways | $0.2per Mtok in$0.8per Mtok out | |
| Hugging Face Inference Providers aggregator | standard | $0.2per Mtok in$0.8per Mtok outmodels.dev · read 2026-11-01 |
| Hugging Face Inference Providers aggregatornot on the seller's list today | novita | $0.2per Mtok in$0.8per Mtok outrouter.huggingface.co · read 2026-08-25 |
| Hugging Face Inference Providers aggregator | nscale | $0.2per Mtok in$0.6per Mtok outrouter.huggingface.co · read 2026-08-25 |
| Novita AI 0 ways | $0.2per Mtok in$0.8per Mtok out | |
| Novita AI aggregatornot on the seller's list today | standard | $0.2per Mtok in$0.8per Mtok outapi.novita.ai · read 2026-08-25 |
| Requesty 2 ways | $0.2per Mtok in$0.6per Mtok out$0.2per Mtok cached | |
| Requesty aggregator | deepinfra | $0.2per Mtok in$0.6per Mtok out$0.2per Mtok cachedrouter.requesty.ai · read 2026-08-28 |
| Requesty aggregator | novita | $0.2per Mtok in$0.8per Mtok out$0.2per Mtok cachedrouter.requesty.ai · read 2026-08-28 |
| Fireworks AI aggregator | standard | $0.22per Mtok in$0.88per Mtok outraw.githubusercontent.com · read 2026-11-01 |
| Vercel AI Gateway aggregator | standard | $0.22per Mtok in$0.88per Mtok outai-gateway.vercel.sh · read 2026-08-25 |
| Featherless AI aggregator | standard | $0.46per Mtok in$1.82per Mtok outapi.featherless.ai · read 2026-09-20 |
| Nous Research 0 ways | $0.46per Mtok in$1.82per Mtok out | |
| Nous Research aggregatornot on the seller's list today | standard | $0.46per Mtok in$1.82per Mtok outinference-api.nousresearch.com · read 2026-09-12 |
| OpenRouter 0 ways | $0.46per Mtok in$1.82per Mtok out | |
| OpenRouter aggregatornot on the seller's list today | standard | $0.46per Mtok in$1.82per Mtok outopenrouter.ai · read 2026-08-24 |
| PPIO 0 ways | $1.45per Mtok in$5.8per Mtok out | |
| PPIO aggregatornot on the seller's list today | standard | $1.45per Mtok in$5.8per Mtok outapi.ppinfra.com · read 2026-10-08 |
| Hyperbolic aggregator | standard | $2per Mtok in$2per Mtok outraw.githubusercontent.com · read 2026-11-01 |
Measured 11 standings
| Place | Board | Metric | Score |
|---|---|---|---|
| 11thof 49 | Lech mazur writing — Epoch AI | Mean score | 8.3 |
| 25thof 69 | Aider polyglot coding leaderboard | Percent correct | 59.6 |
| 28thof 72 | Aider polyglot — Epoch AI | Percent correct | 59.6 |
| 38thof 92 | Forecastbench — Epoch AI | Overall score | 64.1 |
| 45thof 108 | Math level 5 — Epoch AI | mean_score | 68.857 |
| 51stof 111 | Vectara Hallucination Leaderboard | Hallucination Rate | 9.3 |
| 80thof 102 | Simplebench — Epoch AI | Score (AVG@5) | 0.31 |
| 132ndof 173 | Weirdml — Epoch AI | Accuracy | 37.28 |
| 150thof 235 | Dtbench — Epoch AI | Accuracy | 75.73 |
| 152ndof 197 | Lmca — Epoch AI | Score | 25 |
| 187thof 326 | GPQA Diamond | mean_score | 70.707 |
About
Qwen3 235B A22B — a text model from Alibaba, sold by 7 companies from $0.18 in and $0.54 out per million tokens, placed 11th of 49 on Lech mazur writing — Epoch AI.
It takes text and returns text, with a context window of 32,768 tokens. It was published in April 2025, trained on material up to April 2025. Its sellers say it can reason step by step and call a tool. The catalogue files it under reasoning, code and agents. Seven companies sell it. The cheapest is $0.18 in and $0.54 out per million tokens at DeepInfra. Beside the standard rate there is a separately routed lane. It has been measured on 11 boards, and stands best at 11th of 49 on Lech mazur writing — Epoch AI.
Every current figure
- Maker
- Alibaba
- Register
- model
- Takes
- text
- Returns
- text
- Context
- 32,768 tokens
- Published
- April 2025
- Knowledge to
- April 2025
- Parameters
- 235 billion
- Licence
- not read
- Sellers
- 7
- Maker's own price
- not read
- Price
- $0.18 in and $0.54 out per million tokens — DeepInfra
- Boards
- 11
- Best place
- 11th of 49 — Lech mazur writing — Epoch AI
Known as 7 names
Qwen3 235B A22B diff, no think, Alibaba APIQwen3-235B-A22BQwen/Qwen3-235B-A22Bqwen/qwen3-235b-a22b-fp8deepinfra/Qwen/Qwen3-235B-A22Bnovita/qwen/qwen3-235b-a22b-fp8alibaba/qwen-3-235b