Qwen3 VL 235B A22B Instruct pricing & specs
Alibaba (Qwen) · released 2025-09-23 · ● verified 2026-11-14
Qwen3 VL 235B A22B Instruct is an Alibaba (Qwen) model released on 2025-09-23. At $0.20 per million input tokens and $0.88 per million output tokens, its blended price of $0.37 per 1M tokens is lower than 71% of the 184 models we track. It offers text and image input, a 262.1K-token context window, tool calling and structured output. Its weights are open, and it is available from 2 tracked hosting providers.
Ranked #12 of 20 in Cheapest Qwen Models.
// price history ($/1M tokens)
// cheaper or similar alternatives
| model | in | out | ctx | vs Qwen3 VL 235B A22B Instruct |
|---|---|---|---|---|
| Gemma 4 E2B IT | $0.04 | $0.08 | 131.1K | −86.5% |
| Qwen3.7 Flash | $0.03 | $0.13 | 1M | −85.1% |
| Gemma 3 27B IT | $0.08 | $0.16 | 131.1K | −73% |
| Ministral 3 3B | $0.10 | $0.10 | 131.1K | −73% |
| Qwen3.5 9B | $0.10 | $0.15 | 262.1K | −69.6% |
// price by host
| host | in $/1M | out $/1M |
|---|---|---|
| DeepInfra | $0.20 | $0.88 |
| Amazon Bedrock | $0.53 | $2.66 |
// embed this price badge
Show the live price of Qwen3 VL 235B A22B Instruct in your README or docs (updated daily):
[](https://aisignals.dev/models/alibaba/qwen3-vl-235b-a22b-instruct)
// faq
How much does Qwen3 VL 235B A22B Instruct cost?
Qwen3 VL 235B A22B Instruct costs $0.20 per million input tokens and $0.88 per million output tokens (cheapest tracked host: DeepInfra). At 50M input and 10M output tokens per month that is about $18.80.
What is the context window of Qwen3 VL 235B A22B Instruct?
262.1K tokens, with up to 32.8K output tokens per request.
Does Qwen3 VL 235B A22B Instruct support prompt caching?
Yes. Cached input tokens cost $0.11 per million.
What are cheaper alternatives to Qwen3 VL 235B A22B Instruct?
Gemma 4 E2B IT ($0.04 in / $0.08 out), Qwen3.7 Flash ($0.03 in / $0.13 out), Gemma 3 27B IT ($0.08 in / $0.16 out) offer the same input types and capabilities for less.
Is Qwen3 VL 235B A22B Instruct open weights?
Yes. It is available from 2 tracked hosts; the cheapest is DeepInfra at $0.20 input and $0.88 output per million tokens.
// spec sheet
- input / 1M
- $0.20
- output / 1M
- $0.88
- cache read / 1M
- $0.11
- blended (3:1)
- $0.37
- context
- 262.1K
- max output
- 32.8K
- input types
- text · image
- reasoning
- no
- tool calling
- yes
- structured output
- yes
- open weights
- yes
- knowledge cutoff
- 2025-03-31
- price source
- DeepInfra
// cost calculator
| model | in $/1M | out $/1M | = monthly |
|---|---|---|---|
| Gemma 4 E2B IT | $0.04 | $0.08 | $2.80 |
| Qwen3.7 Flash | $0.03 | $0.13 | $2.80 |
| Gemma 3 27B IT | $0.08 | $0.16 | $5.60 |
| Qwen3 VL 235B A22B Instruct | $0.20 | $0.88 | $18.80 |
Base-tier list prices. Long-context tiers, caching and batch discounts are not included.