Qwen3.8-2.4T-A95B
Qwen 3.8 Max is a 2.4-trillion-parameter MoE model delivering a comprehensive leap in coding and professional work.
text + image → text · made by Alibaba
$1→$4per Mtok in / out
Featherless AI · 13 sellers
Sold by 25 ways
| Seller | Lane | Rate |
|---|---|---|
| Featherless AI aggregator | standard | $1per Mtok in$4per Mtok outapi.featherless.ai · read 2026-09-24 |
| DeepInfra aggregator | standard | $2per Mtok in$6per Mtok out$0.2per Mtok cachedapi.deepinfra.com · read 2026-08-25 |
| ElectronHub aggregator | standard | $2per Mtok in$6per Mtok outapi.electronhub.ai · read 2026-11-01 |
| Fireworks AI aggregator | standard | $2per Mtok in$6per Mtok out$0.25per Mtok cachedmodels.dev · read 2026-11-01 |
| Hugging Face Inference Providers 3 ways | $2.5per Mtok in$6.25per Mtok out | |
| Hugging Face Inference Providers aggregator | deepinfra | $2per Mtok in$6per Mtok outrouter.huggingface.co · read 2026-08-28 |
| Hugging Face Inference Providers aggregator | novita | $2per Mtok in$6per Mtok outrouter.huggingface.co · read 2026-08-28 |
| Hugging Face Inference Providers aggregatornot on the seller's list today | together | $2per Mtok in$6per Mtok outrouter.huggingface.co · read 2026-09-02 |
| Hugging Face Inference Providers aggregator | standard | $2.5per Mtok in$6.25per Mtok outmodels.dev · read 2026-11-01 |
| Nous Research aggregator | standard | $2per Mtok in$6per Mtok out$0.25per Mtok cachedinference-api.nousresearch.com · read 2026-09-12 |
| Nous Research aggregatornot on the seller's list today | batch | $2per Mtok in$6per Mtok out$0.25per Mtok cachedinference-api.nousresearch.com · read 2026-09-12 |
| Novita AI aggregator | standard | $2per Mtok in$6per Mtok out$0.25per Mtok cachedapi.novita.ai · read 2026-09-20 |
| OpenRouter 6 ways | $2per Mtok in$6per Mtok out$0.25per Mtok cached | |
| OpenRouter aggregator | standard | $2per Mtok in$6per Mtok out$0.25per Mtok cachedopenrouter.ai · read 2026-08-24 |
| OpenRouter aggregator | alibaba | $2per Mtok in$6per Mtok out$0.25per Mtok cached$2.5per Mtok cache writeopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregatornot on the seller's list today | batch | $2per Mtok in$6per Mtok out$0.25per Mtok cachedopenrouter.ai · read 2026-09-02 |
| OpenRouter aggregatornot on the seller's list today | deepinfra/fp4 | $2per Mtok in$6per Mtok out$0.2per Mtok cachedopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregatornot on the seller's list today | modal | $2per Mtok in$6per Mtok out$0.25per Mtok cachedopenrouter.ai · read 2026-09-02 |
| OpenRouter aggregator | novita | $2per Mtok in$6per Mtok out$0.25per Mtok cachedopenrouter.ai · read 2026-09-02 |
| OpenRouter aggregator | siliconflow/fp8 | $2per Mtok in$6per Mtok out$0.25per Mtok cachedopenrouter.ai · read 2026-09-02 |
| OpenRouter aggregator | together | $2per Mtok in$6per Mtok out$0.25per Mtok cachedopenrouter.ai · read 2026-09-04 |
| OpenRouter aggregator | venice | $2per Mtok in$6per Mtok out$0.25per Mtok cachedopenrouter.ai · read 2026-09-13 |
| SiliconFlow aggregator | standard | $2per Mtok in$6per Mtok out$0.25per Mtok cachedmodels.dev · read 2026-11-01 |
| Together AI aggregator | standard | $2per Mtok in$6per Mtok out$0.25per Mtok cachedraw.githubusercontent.com · read 2026-11-01 |
| Vercel AI Gateway aggregator | standard | $2per Mtok in$6per Mtok out$0.25per Mtok cachedai-gateway.vercel.sh · read 2026-08-25 |
| Requesty aggregator | tensorx | $2.5per Mtok in$6per Mtok out$0.63per Mtok cachedrouter.requesty.ai · read 2026-09-20 |
| PPIO aggregator | standard | $12per Mtok in$36per Mtok outapi.ppinfra.com · read 2026-11-01 |
Measured 2 standings
| Place | Board | Metric | Score |
|---|---|---|---|
| 16thof 131 | Artificial Analysis · Agentic Index | Index | 50.1 |
| 32ndof 163 | Artificial Analysis · Coding Index | Index | 71.9 |
About
Qwen3.8-2.4T-A95B — a text model from Alibaba, sold by 13 companies from $1 in and $4 out per million tokens, placed 16th of 131 on Artificial Analysis · Agentic Index.
It takes text and images and returns text, with a context window of 262,144 tokens. It was published in August 2026. Its sellers say it can reason step by step and call a tool. The catalogue files it under chat. Thirteen companies sell it. The cheapest is $1 in and $4 out per million tokens at Featherless AI. Beside the standard rate there are separately routed and regional lanes. It has been measured on 2 boards, and stands best at 16th of 131 on Artificial Analysis · Agentic Index.
Every current figure
- Maker
- Alibaba
- Register
- model
- Takes
- text + image
- Returns
- text
- Context
- 262,144 tokens
- Published
- August 2026
- Parameters
- 2446 billion
- Licence
- not read
- Sellers
- 13
- Maker's own price
- not read
- Price
- $1 in and $4 out per million tokens — Featherless AI
- Boards
- 2
- Best place
- 16th of 131 — Artificial Analysis · Agentic Index
Known as 4 names
Qwen3.8 2.4T A95BQwen/Qwen3.8-2.4T-A95Btensorx/qwen3.8-2.4t-a95balibaba/qwen3.8-2.4t-a95b