Skip to content
Metered.
Qwen (Alibaba) model

Qwen3 VL 235B A22B Instruct

API pricing per million tokens

qwen3-vl-235b-a22b-instruct Open weightsChecked 6h ago
Cost calculator Compare
Input
$0.26
per 1M, list
Output
$1.04
per 1M tokens
Cached input
n/a
no batch tier listed
Context
262K
33K max output

Where to buy it (5)

  • DeepInfrafp8, fp8-19%$0.2 / $0.88cached $0.11
  • Qwen (Alibaba) (list)the lab's own API$0.26 / $1.04$0.455 blended
  • Novita AIbf16, bf16+32%$0.3 / $1.5$0.6 blended
  • Parasailfp8, fp8+39%$0.21 / $1.9cached $0.1
  • Venicefp8, fp8+39%$0.21 / $1.9cached $0.1

Through a gateway

Your own numbers

100M input and 20M output tokens a month: $46.80 direct.

Related models

About Qwen3 VL 235B A22B Instruct

Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video.

Takes text, image in and returns text. First listed Sep 23, 2026. Blended price $0.455 per 1M tokens at 3 input to 1 output.

OpenRouter listing Qwen (Alibaba) pricing page
Across fru.devCompany profile

Questions

How much does Qwen3 VL 235B A22B Instruct cost?

$0.26 per million input tokens and $1.04 per million output tokens.

What is the context window of Qwen3 VL 235B A22B Instruct?

262K tokens, with up to 33K tokens of output.

Where is Qwen3 VL 235B A22B Instruct cheapest?

Of 5 routes tracked, DeepInfra is cheapest at $0.2 input and $0.88 output per million tokens.

List prices from providers' pages on the date shown; your contract may differ. Logos via logo.dev; trademarks belong to their owners.

Weekly: LLM API list prices that changed, Thursday mornings.