Qwen3.5 397B A17B
Qwen3.5-397B-A17B is Alibaba's most capable Qwen3.5 model, a Mixture-of-Experts architecture with 397B total parameters and 17B activated per token.
text + image + video → text · made by Alibaba
Sold by 31 ways
| Seller | Lane | Rate |
|---|---|---|
| DigitalOcean cloud | standard | $0.55per Mtok in$3.5per Mtok out$0.11per Mtok cachedmodels.dev · read 2026-09-16 |
| Thinking Machines Lab api | training | $3per Mtok in$7.5per Mtok out$0.6per Mtok cachedtinker-docs.thinkingmachines.ai · read 2026-08-25 |
| Thinking Machines Lab api | training-256k | $4per Mtok in$10per Mtok out$0.8per Mtok cachedtinker-docs.thinkingmachines.ai · read 2026-08-25 |
| Requesty 3 ways | $0.32per Mtok in$2.16per Mtok out$0.16per Mtok cached | |
| Requesty aggregatornot on the seller's list today | deepinfra flex | $0.32per Mtok in$2.16per Mtok out$0.16per Mtok cachedrouter.requesty.ai · read 2026-08-25 |
| Requesty aggregator | deepinfra | $0.36per Mtok in$2.4per Mtok out$0.18per Mtok cachedrouter.requesty.ai · read 2026-09-16 |
| Requesty aggregator | nebius | $0.6per Mtok in$3.6per Mtok out$0.6per Mtok cachedrouter.requesty.ai · read 2026-08-28 |
| Requesty aggregator | novita | $0.6per Mtok in$3.6per Mtok out$0.6per Mtok cachedrouter.requesty.ai · read 2026-08-28 |
| Nous Research aggregator | standard | $0.39per Mtok in$2.34per Mtok out$0.18per Mtok cachedinference-api.nousresearch.com · read 2026-09-12 |
| OpenRouter 11 ways | $0.55per Mtok in$3.5per Mtok out$0.23per Mtok cached | |
| OpenRouter aggregator | alibaba | $0.39per Mtok in$2.34per Mtok outopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | deepinfra/fp8 | $0.45per Mtok in$3per Mtok out$0.22per Mtok cachedopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | parasail/fp8 | $0.5per Mtok in$3.6per Mtok out$0.3per Mtok cachedopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | standard | $0.55per Mtok in$3.5per Mtok out$0.23per Mtok cachedopenrouter.ai · read 2026-09-09 |
| OpenRouter aggregator | atlas-cloud/fp8 | $0.55per Mtok in$3.5per Mtok out$0.55per Mtok cachedopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | digitalocean | $0.55per Mtok in$3.5per Mtok out$0.11per Mtok cachedopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | phala | $0.55per Mtok in$3.5per Mtok out$0.23per Mtok cachedopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | gmicloud/fp8 | $0.6per Mtok in$3.6per Mtok outopenrouter.ai · read 2026-08-27 |
| OpenRouter aggregator | novita | $0.6per Mtok in$3.6per Mtok outopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | streamlake | $0.6per Mtok in$3.6per Mtok out$0.12per Mtok cachedopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | venice | $0.75per Mtok in$4.5per Mtok outopenrouter.ai · read 2026-08-25 |
| SiliconFlow aggregator | standard | $0.39per Mtok in$2.34per Mtok outmodels.dev · read 2026-09-16 |
| DeepInfra aggregator | standard | $0.45per Mtok in$3per Mtok out$0.22per Mtok cachedapi.deepinfra.com · read 2026-08-25 |
| Hugging Face Inference Providers 5 ways | $0.6per Mtok in$3.6per Mtok out | |
| Hugging Face Inference Providers aggregator | deepinfra | $0.45per Mtok in$3per Mtok outrouter.huggingface.co · read 2026-08-25 |
| Hugging Face Inference Providers aggregator | standard | $0.6per Mtok in$3.6per Mtok outmodels.dev · read 2026-09-16 |
| Hugging Face Inference Providers aggregator | novita | $0.6per Mtok in$3.6per Mtok outrouter.huggingface.co · read 2026-08-25 |
| Hugging Face Inference Providers aggregator | scaleway | $0.68per Mtok in$4.1per Mtok outrouter.huggingface.co · read 2026-08-25 |
| Hugging Face Inference Providers aggregator | ovhcloud | $0.71per Mtok in$4.25per Mtok outrouter.huggingface.co · read 2026-08-25 |
| Nebius Token Factory aggregator | standard | $0.6per Mtok in$3.6per Mtok outtokenfactory.nebius.com · read 2026-08-25 |
| Novita AI aggregator | standard | $0.6per Mtok in$3.6per Mtok outapi.novita.ai · read 2026-08-25 |
| Together AI aggregator | standard | $0.6per Mtok in$3.6per Mtok out$0.35per Mtok cachedmodels.dev · read 2026-09-16 |
| ElectronHub aggregator | standard | $1per Mtok in$4per Mtok outapi.electronhub.ai · read 2026-09-16 |
| PPIO aggregator | standard | $3per Mtok in$18per Mtok outapi.ppinfra.com · read 2026-09-16 |
Measured 22 standings
About
Qwen3.5 397B A17B — a text model from Alibaba, sold by 13 companies from $0.39 in and $2.34 out per million tokens, placed 1st of 8 on τ²-bench Leaderboard (Overall: Retail · Airline · Telecom).
It takes text, images and video and returns text, with a context window of 262,144 tokens. It was published in July 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 and agents. Thirteen companies sell it. The cheapest is $0.39 in and $2.34 out per million tokens at Nous Research. Beside the standard rate there are separately routed and regional lanes. It has been measured on 22 boards, and stands best at 1st of 8 on τ²-bench Leaderboard (Overall: Retail · Airline · Telecom).
Every current figure
- Maker
- Alibaba
- Register
- model
- Takes
- text + image + video
- Returns
- text
- Context
- 262,144 tokens
- Published
- July 2025
- Knowledge to
- April 2025
- Parameters
- 403 billion
- Licence
- not read
- Sellers
- 13
- Maker's own price
- not read
- Price
- $0.39 in and $2.34 out per million tokens — Nous Research
- Boards
- 22
- Best place
- 1st of 8 — τ²-bench Leaderboard (Overall: Retail · Airline · Telecom)
Known as 7 names
Qwen3.5-397b-a17bQwen/Qwen3.5-397B-A17Bdeepinfra/Qwen/Qwen3.5-397B-A17Bdeepinfra/Qwen/Qwen3.5-397B-A17B:flexnebius/qwen/qwen3.5-397b-a17bnovita/qwen/qwen3.5-397b-a17bQwen/Qwen3.5-397B-A17B:peft:262144