# Qwen3.5 397B A17B: price, benchmarks, context

- **URL canônica:** https://meirinho.com.br/en/ia/modelos/qwen3-5-397b-a17b/
- **Idioma:** en
- **Atualizado:** 2026-11-17

---
**41st–69th of 85**

Methodology v2 · updated November 21, 2026 · [Technical tie](https://meirinho.com.br/en/ia/modelos/metodologia/#empate-tecnico) · [Minimum of 4 benchmarks](https://meirinho.com.br/en/ia/modelos/metodologia/#minimo-3-benchmarks) · [Methodology](https://meirinho.com.br/en/ia/modelos/metodologia/)

Alibaba

# Qwen3.5 397B A17B

Benchmarks, price, context and versions

GPQA Diamond

Epoch AI

FrontierMath (tiers 1 to 3)

Epoch AI

Input US$/1M

Official pricing

Output US$/1M

Official pricing

Context

tokens

## Direct answer

**Direct answer:** Qwen3.5 397B A17B is a model from Alibaba. 86.4% on GPQA Diamond, per Epoch AI. US$ 0.60 per 1 million input tokens and US$ 3.60 per 1 million output tokens.

## ✓ Good for

- running on your own infrastructure (open weights)

## ✕ Not the best for

- the ceiling of reasoning on research-level math (67th of 85 on FrontierMath (tiers 1 to 3), per Epoch AI)

This block follows a rule of this section, using source data: if the model is in the top 25% of the metric, the item goes under "Good for"; if it is in the bottom half, it goes under "Not the best for". The middle band appears in neither. The price is official pricing, published by the lab itself for its own API. Context uses OpenRouter. Scores use Epoch AI or OpenRouter Benchmarks, in the latest version we checked.

## Benchmarks

| GPQA Diamond[? what it is](https://meirinho.com.br/en/ia/modelos/glossario/gpqa-diamond/) | 86.4%**highest score on this metric 96.8%69º / 195 · [Epoch AI](https://epoch.ai/benchmarks/gpqa-diamond), latest version we checked |
| --- | --- |
| OTIS Mock AIME[?](https://meirinho.com.br/en/ia/modelos/glossario/otis-mock-aime/) | 88.9%**highest score on this metric 100%68º / 182 · [Epoch AI](https://epoch.ai/benchmarks/otis-mock-aime-2024-2025), latest version we checked |
| FrontierMath (tiers 1 to 3)[?](https://meirinho.com.br/en/ia/modelos/glossario/frontiermath/) | 31.2%**highest score on this metric 95.1%67º / 85 · [Epoch AI](https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2), latest version we checked |
| GPQA Diamond (OpenRouter)[?](https://meirinho.com.br/en/ia/modelos/glossario/gpqa-diamond-openrouter/) | 88.1%**highest score on this metric 96.5%52º / 134 · [OpenRouter Benchmarks](https://openrouter.ai/benchmarks/gpqa-diamond), latest version we checked |
| τ-bench Verified (airline)[?](https://meirinho.com.br/en/ia/modelos/glossario/tau-bench/) | 80.2%**highest score on this metric 82%4º / 130 · [OpenRouter Benchmarks](https://openrouter.ai/benchmarks/tau2-bench-airline), latest version we checked |

## Input US$/1M · Output US$/1M

Input US$/1M

US$ 0.60

Third-party provider pricing, OpenRouter: US$ 0.45 / US$ 3.00

Output US$/1M

US$ 3.60

## Key specs

| Lab | [Alibaba](https://meirinho.com.br/en/ia/modelos/lab/alibaba/) |
| --- | --- |
| Origin | China |
| Family | Qwen provisional data |
| Weights[?](https://meirinho.com.br/en/ia/modelos/glossario/pesos-abertos/) | open |
| License | [apache-2.0](https://huggingface.co/Qwen/Qwen3.5-397B-A17B) |
| Also known as | API name: [qwen3.5-397b-a17b](https://www.alibabacloud.com/help/en/model-studio/model-pricing) |
| Context[?](https://meirinho.com.br/en/ia/modelos/glossario/janela-de-contexto/) | 262,144 tokens |
| Parameters | 403,397,928,944 |
| Input | image, text, video |
| OpenRouter usage[?](https://meirinho.com.br/en/ia/modelos/glossario/uso-no-openrouter/) | 0.01% OpenRouter |
| Downloads (30 days)[?](https://meirinho.com.br/en/ia/modelos/glossario/downloads-hugging-face/) | 826,220 |
| Use cases provisional data | [Text](https://meirinho.com.br/en/ia/modelos/uso/texto/) [Agents](https://meirinho.com.br/en/ia/modelos/uso/agentes/) |
| Dates in sources | no official dateFebruary 13, 2026, published, per Epoch AIFebruary 16, 2026, listed on OpenRouterFebruary 16, 2026, Hugging Face repo created |

Collected November 17, 2026

## Version history

- August 14, 2026 [Qwen: Qwen3.8 27B](https://openrouter.ai/qwen/qwen3.8-27b) OpenRouter, listed on OpenRouter
- August 13, 2026 [Qwen3.8-27B-FP8](https://huggingface.co/Qwen/Qwen3.8-27B-FP8) Hugging Face Hub, Hugging Face repo created
- August 12, 2026 [Qwen: Qwen3.8 2.4T A95B](https://openrouter.ai/qwen/qwen3.8-2.4t-a95b) OpenRouter, listed on OpenRouter

Dates come from the sources: OpenRouter listing or Hugging Face repo creation, which may differ from the official launch.

## Sources for this model

- Official model page, [Alibaba](https://www.alibabacloud.com/help/en/model-studio/models).
- Official pricing, [Alibaba](https://www.alibabacloud.com/help/en/model-studio/model-pricing).
- No official launch announcement.
- Weights and license (apache-2.0), [Hugging Face](https://huggingface.co/Qwen/Qwen3.5-397B-A17B).
- Benchmarks: each score carries its own source, in the table above.

## FAQ

Qwen3.5 397B A17B is a model from Alibaba, with open weights, used for text, agents.

US$ 0.60 per 1 million input tokens and US$ 3.60 per 1 million output tokens.

262,144 tokens, per OpenRouter.

Yes, it has open weights. License: apache-2.0.

86.4% on GPQA Diamond, per Epoch AI.

No data: there is no SWE-bench Verified measurement for it in open sources.

It was made by Alibaba, a lab from China.

provisional data

## Compare with

### Models from Alibaba

- [Qwen1.5-32B](https://meirinho.com.br/en/ia/modelos/qwen1-5-32b/)
- [Qwen1.5-72B](https://meirinho.com.br/en/ia/modelos/qwen1-5-72b/)
- [Qwen2-72B](https://meirinho.com.br/en/ia/modelos/qwen2-72b/)
- [Qwen2.5-32B](https://meirinho.com.br/en/ia/modelos/qwen2-5-32b/)
- [Qwen2.5-72B](https://meirinho.com.br/en/ia/modelos/qwen2-5-72b/)
- [Qwen2.5-7B](https://meirinho.com.br/en/ia/modelos/qwen2-5-7b/)
- [Qwen3 14B](https://meirinho.com.br/en/ia/modelos/qwen3-14b/)
- [Qwen3 30B A3B](https://meirinho.com.br/en/ia/modelos/qwen3-30b-a3b/)
- [Qwen3 32B](https://meirinho.com.br/en/ia/modelos/qwen3-32b/)
- [Qwen3-1.7B](https://meirinho.com.br/en/ia/modelos/qwen3-1-7b/)
- [Qwen3-235B-A22B](https://meirinho.com.br/en/ia/modelos/qwen3-235b-a22b/)
- [Qwen3-4B](https://meirinho.com.br/en/ia/modelos/qwen3-4b/)

[See lab](https://meirinho.com.br/en/ia/modelos/lab/alibaba/)

## How to cite

If you use this data, cite the page and the date you accessed it.

```
Adriano Meirinho. "Qwen3.5 397B A17B". meirinho.com.br. https://meirinho.com.br/en/ia/modelos/qwen3-5-397b-a17b/. Accessed November 21, 2026.
```

Third-party data follows the license of each source. The full table is available as [CSV](https://meirinho.com.br/ia/modelos/dados.csv) and [JSON](https://meirinho.com.br/ia/modelos/dados.json).

[#](#)
