Qwen3-235B-A22B-Instruct-2507
Qwen3-235B-A22B-Instruct-2507 is the updated version of the Qwen3-235B-A22B non-thinking mode, featuring Significant improvements in general capabilities, including instruction following, logical reasoning, text comprehension, mathematics, science, coding and tool usage.
text → text · made by Alibaba
Sold by 31 ways
| Seller | Lane | Rate |
|---|---|---|
| AWS Bedrock cloud | batch | $0.11per Mtok in$0.44per Mtok outraw.githubusercontent.com · read 2026-09-16 |
| Google Vertex AI 0 ways | $0.11per Mtok in$0.44per Mtok out | |
| Google Vertex AI cloudnot on the seller's list today | batch | $0.11per Mtok in$0.44per Mtok outcloud.google.com · read 2026-08-24 |
| AWS Bedrock cloud | standard | $0.22per Mtok in$0.88per Mtok outmodels.dev · read 2026-09-16 |
| Crusoe cloud | standard | $0.22per Mtok in$0.8per Mtok out$0.11per Mtok cachedmodels.dev · read 2026-09-16 |
| Google Vertex AI 0 ways | $0.22per Mtok in$0.88per Mtok out | |
| Google Vertex AI cloudnot on the seller's list today | standard | $0.22per Mtok in$0.88per Mtok outcloud.google.com · read 2026-08-24 |
| Requesty 2 ways | $0.071per Mtok in$0.1per Mtok out | |
| Requesty aggregator | deepinfra | $0.071per Mtok in$0.1per Mtok outrouter.requesty.ai · read 2026-08-28 |
| Requesty aggregator | nebius | $0.2per Mtok in$0.6per Mtok out$0.2per Mtok cachedrouter.requesty.ai · read 2026-08-28 |
| Nous Research aggregator | standard | $0.087per Mtok in$0.35per Mtok out$0.018per Mtok cachedinference-api.nousresearch.com · read 2026-09-12 |
| OpenRouter 11 ways | $0.087per Mtok in$0.35per Mtok out$0.018per Mtok cached | |
| OpenRouter aggregator | standard | $0.087per Mtok in$0.35per Mtok out$0.018per Mtok cachedopenrouter.ai · read 2026-09-12 |
| OpenRouter aggregator | gmicloud/fp8 | $0.087per Mtok in$0.35per Mtok out$0.018per Mtok cachedopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | deepinfra/fp8 | $0.09per Mtok in$0.55per Mtok outopenrouter.ai · read 2026-08-27 |
| OpenRouter aggregator | novita/fp8 | $0.09per Mtok in$0.58per Mtok outopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | parasail/fp8 | $0.14per Mtok in$0.8per Mtok out$0.05per Mtok cachedopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | alibaba | $0.15per Mtok in$0.6per Mtok outopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | venice/fp8 | $0.15per Mtok in$0.75per Mtok outopenrouter.ai · read 2026-08-27 |
| OpenRouter aggregator | atlas-cloud/fp8 | $0.2per Mtok in$0.88per Mtok out$0.2per Mtok cachedopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | nebius/fp8 | $0.2per Mtok in$0.6per Mtok outopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | streamlake | $0.21per Mtok in$0.84per Mtok outopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | google-vertex/us-south1 | $0.22per Mtok in$0.88per Mtok outopenrouter.ai · read 2026-08-25 |
| DeepInfra aggregator | standard | $0.09per Mtok in$0.55per Mtok outapi.deepinfra.com · read 2026-08-25 |
| Hugging Face Inference Providers 5 ways | $0.85per Mtok in$2.56per Mtok out | |
| Hugging Face Inference Providers aggregator | deepinfra | $0.09per Mtok in$0.55per Mtok outrouter.huggingface.co · read 2026-08-25 |
| Hugging Face Inference Providers aggregator | novita | $0.09per Mtok in$0.58per 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 |
| Hugging Face Inference Providers aggregator | standard | $0.85per Mtok in$2.56per Mtok outmodels.dev · read 2026-09-16 |
| Hugging Face Inference Providers aggregator | scaleway | $0.85per Mtok in$2.56per Mtok outrouter.huggingface.co · read 2026-08-25 |
| Novita AI aggregator | standard | $0.09per Mtok in$0.58per Mtok outapi.novita.ai · read 2026-08-25 |
| Venice AI aggregator | standard | $0.15per Mtok in$0.75per Mtok outmodels.dev · read 2026-09-16 |
| Nebius Token Factory aggregator | standard | $0.2per Mtok in$0.6per Mtok outtokenfactory.nebius.com · read 2026-08-25 |
| Fireworks AI aggregator | standard | $0.22per Mtok in$0.88per Mtok outraw.githubusercontent.com · read 2026-09-16 |
| ElectronHub aggregator | standard | $0.24per Mtok in$0.72per Mtok outapi.electronhub.ai · read 2026-09-16 |
| PPIO aggregator | standard | $1.45per Mtok in$5.8per Mtok outapi.ppinfra.com · read 2026-09-16 |
Measured 18 standings
| Place | Board | Metric | Score |
|---|---|---|---|
| 23rdof 109 | Berkeley Function-Calling Leaderboard (BFCL) V4 | Overall Acc | 52.15 |
| 29thof 72 | Aider polyglot — Epoch AI | Percent correct | 59.6 |
| 71stof 161 | Dtbench — Epoch AI | Accuracy | 78.4 |
| 82ndof 123 | Lmca — Epoch AI | Score | 23.52 |
| 119thof 170 | Weirdml — Epoch AI | Accuracy | 38.7 |
| 126thof 152 | Design Arena · dataviz (models) | Elo | 1085 |
| 127thof 147 | Design Arena · 3d (models) | Elo | 1022 |
| 131stof 156 | Design Arena · codecategories (models) | Elo | 1054 |
| 133rdof 162 | Design Arena · website (models) | Elo | 1070 |
| 136thof 150 | Design Arena · uicomponent (models) | Elo | 980 |
| 147thof 155 | Design Arena · gamedev (models) | Elo | 974 |
| 168thof 216 | ARC-AGI-2 (Public Eval) | Score (%) | 0.83 |
| 186thof 205 | ARC-AGI-1 (Public Eval) | Score (%) | 17 |
| 189thof 227 | Arc agi 2 — Epoch AI | Score | 1.25 |
| 193rdof 232 | ARC-AGI-2 (Semi-Private) | Score (%) | 1.25 |
| 211thof 230 | ARC-AGI-1 (Semi-Private) | Score (%) | 11 |
| 226thof 244 | Arc agi — Epoch AI | Score | 11 |
| 462ndof 656 | Epoch capabilities index — Epoch AI | ECI Score | 138.95 |
About
Qwen3-235B-A22B-Instruct-2507 — a text model from Alibaba, sold by 13 companies from $0.087 in and $0.35 out per million tokens, placed 23rd of 109 on Berkeley Function-Calling Leaderboard (BFCL) V4.
It takes text and returns text, with a context window of 262,144 tokens. It was published in April 2025, trained on material up to April 2025. Its sellers say it can call a tool. The catalogue files it under reasoning and agents. Thirteen companies sell it. The cheapest is $0.087 in and $0.35 out per million tokens at Nous Research. Beside the standard rate there are batch, separately routed and regional lanes. It has been measured on 18 boards, and stands best at 23rd of 109 on Berkeley Function-Calling Leaderboard (BFCL) V4.
Every current figure
- Maker
- Alibaba
- Register
- model
- Takes
- text
- Returns
- text
- Context
- 262,144 tokens
- Published
- April 2025
- Knowledge to
- April 2025
- Parameters
- 235 billion
- Licence
- not read
- Sellers
- 13
- Maker's own price
- not read
- Price
- $0.087 in and $0.35 out per million tokens — Nous Research
- Boards
- 18
- Best place
- 23rd of 109 — Berkeley Function-Calling Leaderboard (BFCL) V4
Known as 6 names
Qwen3-235B-A22B-Instruct-2507 (Prompt)Qwen/Qwen3-235B-A22B-Instruct-2507qwen/qwen3-235b-a22b-2507deepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507nebius/qwen/qwen3-235b-a22b-instruct-2507Qwen: Qwen3 235B A22B Instruct 2507