Qwen

Qwen3.5 397B A17B: price, context window and ranking

As of 18 October 2026, Qwen3.5 397B A17B from Qwen costs $0.50 per million input tokens and $3.60 per million output tokens on OpenRouter, with a context window of 262K tokens. On the LMArena text leaderboard it ranks 81 with a score of 1,437.7.

Oesnada automated editorial system · Last updated: (2026-10-18)

Input price
$0.50

per 1M tokens

Output price
$3.60

per 1M tokens

Context window
262K

tokens

LMArena score
1,437.7

rank 81

Providers
10

uptime 86.6%

Specifications

Specifications
FieldValue
ProviderQwen
Input price per 1M tokens$0.50
Output price per 1M tokens$3.60
Blended price per 1M tokens (3:1)$1.275
Context window262,144
Providers serving it10
Average uptime, past day86.6%
LMArena1,437.7 (rank 81)
Arena score per dollar1,127.6
Added to OpenRouter2026-02-16
Modalitytext+image+video->text
OpenRouter model IDqwen/qwen3.5-397b-a17b

Price history

Qwen3.5 397B A17B: Price historyInput and output price per million tokens, one point per daily snapshot.$0.345$1.4817$2.6183$3.7552026-10-162026-10-172026-10-18
  • Input
  • Output
Qwen3.5 397B A17B: Price history
DateInputOutput
2026-10-16$0.50$3.60
2026-10-17$0.50$3.60
2026-10-18$0.50$3.60

Frequently asked questions

How much does Qwen3.5 397B A17B cost per million tokens?

Qwen3.5 397B A17B costs $0.50 per million input tokens and $3.60 per million output tokens on OpenRouter, as of 18 October 2026. At a mix of three parts input to one part output the blended price is $1.275 per million tokens.

What is the context window of Qwen3.5 397B A17B?

Qwen3.5 397B A17B has a context window of 262K tokens (262,144 exactly).

How does Qwen3.5 397B A17B rank on LMArena?

Qwen3.5 397B A17B is ranked 81 on the LMArena text leaderboard with a score of 1,437.7 from 93,567 votes. The listing used is "qwen3.5-397b-a17b".

When was Qwen3.5 397B A17B released?

OpenRouter lists Qwen3.5 397B A17B as added on 16 February 2026.

Who provides Qwen3.5 397B A17B?

Qwen3.5 397B A17B is served by 10 providers on OpenRouter, with average uptime of 86.6% over the past day.

Methodology and sources

The catalogue, prices, context lengths and provider counts come from OpenRouter's public Models API. They are fetched every day at 06:00 Istanbul time and stored as a daily snapshot. Weekly changes are calculated by Oesnada by comparing those snapshots; there is no data before 16 October 2026.

Usage shares are calculated from the daily token totals of OpenRouter's Data API: a model's tokens over the past 7 days divided by all tokens in the same period, including the aggregated long tail outside the top 50. Token counts come from each provider's own tokenizer and are not directly comparable across providers. The data is published by OpenRouter under CC BY 4.0. Variants such as ":free" are counted separately, so shares here can differ from OpenRouter's own ranking page.

Quality rankings come from LMArena's text (overall) leaderboard. A model is matched only when its name matches exactly; if a model has several listings, the highest-scoring one is used. "Frontier" means a model in the LMArena top 15.

"Best value" divides the LMArena score by the blended price (three parts input to one part output). Arena scores are not a linear scale, so the ratio is a rough guide. This page is produced automatically.

Related Oesnada stories: Qwen

No related stories yet.

All AI models

AI Models

Download the data

Cite this page

Oesnada, "Qwen3.5 397B A17B: price, context window and ranking", https://oesnada.com/ai-models/qwen-qwen3-5-397b-a17b, accessed 18 October 2026.