Qwen3 VL 235B A22B Instruct

Qwen · qwen/qwen3-vl-235b-a22b-instruct

← Back to leaderboard

Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table...

Qwen3 VL 235B A22B Instruct ranks #177 of 359 models in the default AI Benchmark Hub order (quality first, then cost). At $1.05 blended per million tokens, it is cheaper than 50% of models with published API pricing. Its 131,072-token context window is 2.0× smaller than the catalog median (262,144 tokens).

open weightsimagetexttext+image->text

Context

Max context: 131072
Max output: 32768

Pricing

Input / 1M: 0.21
Output / 1M: 1.90
Blend / 1M: 1.05

Quality

Quality index:

Provider

Provider: Qwen
Moderated: no

Monthly cost at this blended rate

Estimated API spend if every token is billed at $1.05per million (the blend of this model's input and output prices). Real bills depend on the input/output mix.

Tokens / monthEst. cost (USD)
1,000,000$1.05
10,000,000$10.55
100,000,000$105.50

Related models

Same lab, similar price, or similar quality — useful next comparisons.

More from Qwen

Closest API price