Skip to content
LLMs
Qwen logo

Qwen: Qwen3.5 397B A17B

by Qwen

Qwen: Qwen3.5 397B A17B is a large language model from Qwen. It costs $0.550 per million input tokens and $3.50 per million output tokens. Its context window is 262K tokens.

ReasoningTool callingStructured outputPrompt cachingOpen weightsimage inputvideo input
Input / 1M tokens
$0.550
Output / 1M tokens
$3.50
Cached input / 1M
$0.225

On repeated prefixes

Context window
262K

tokens

Who serves it cheapest

10 hosts serve Qwen3.5 397B A17B. Same weights, same API - the price difference is pure margin and routing.

Providers serving Qwen: Qwen3.5 397B A17B, cheapest first
ProviderInput / 1MOutput / 1MContextThroughputUptime 24h
AlibabaCheapest$0.390$2.34262K-100.0%
DeepInfrafp8$0.450$3.00262K-97.3%
Parasailfp8$0.500$3.60262K-99.9%
DigitalOcean$0.550$3.50131K-98.0%
Phala$0.550$3.50262K-99.5%
AtlasCloudfp8$0.550$3.50262K-97.2%
StreamLake$0.600$3.60256K-93.6%
GMICloudfp8$0.600$3.60262K-94.6%
Novita$0.600$3.60262K-99.7%
Venice$0.750$4.50128K-95.1%

The spread between Alibaba and Venice is 1.9× for identical weights. Quantization and context limits differ, so check both columns before switching.

Benchmarks

Independent scores published alongside the catalogue.

Intelligence index
19.1
Coding index
48.2
Agentic index
10.6

About Qwen3.5 397B A17B

The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers...

Specifications

Qwen: Qwen3.5 397B A17B specifications
Model IDqwen/qwen3.5-397b-a17b
ProviderQwen
Context window262K tokens
Max output236K tokens
Input modalitiestext, image, video
Output modalitiestext
Knowledge cutoff-
Open weightsYes - Qwen/Qwen3.5-397B-A17B
ReleasedFebruary 16, 2026

Cheaper alternatives

Models that cost less than Qwen3.5 397B A17B while keeping at least half its context window and every input modality it supports.

Frequently asked

How much does Qwen: Qwen3.5 397B A17B cost?

$0.550 per million input tokens and $3.50 per million output tokens. Cached input reads cost $0.225 per million tokens.

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

262K tokens, with up to 236K tokens of output per request.

Which provider serves Qwen: Qwen3.5 397B A17B cheapest?

Alibaba at $0.390 per million input tokens - 1.9× cheaper than Venice, the most expensive of the 10 hosts serving it.

Confirm against the source: Qwen official pricing.