All models

Qwen3 VL 235B A22B Thinking

open source

Qwen model, released 23 Sept 2025.

$0.4
per 1M input tokens
$4.00
per 1M output tokens
per 1M cached-read tokens
Calculate what your real prompts cost on Qwen3 VL 235B A22B Thinking

Price history

input $/1M output $/1M7 Jul 20267 Aug 2026

Specifications

Lab
Qwen
Released
23 Sept 2025
Context window
131k tokens
Max output
33k tokens
Input modalities
text, image
Output modalities
text
Knowledge cutoff
2025-03-31
Open source
Yes

Benchmarks

BenchmarkCategoryScoreAs of
LMArena (Chatbot Arena)coding1427.4 (1413.11441.8)20 Jul 2026
LMArena (Chatbot Arena)overall1400.8 (1394.11407.6)20 Jul 2026

LMArena (Chatbot Arena) data © their authors, CC-BY-4.0

Frequently asked questions

How much does Qwen3 VL 235B A22B Thinking cost?

Qwen3 VL 235B A22B Thinking costs $0.4 per 1M input tokens and $4.00 per 1M output tokens (list price, updated every 6 hours).

What is Qwen3 VL 235B A22B Thinking's context window?

Qwen3 VL 235B A22B Thinking supports a 131k-token context window with up to 33k output tokens.

Related models