Qwen3 VL 30B A3B Instruct pricing & specs
Alibaba (Qwen) · released 2025-10-04 · ● verified 2026-10-11
input / 1M$0.15via DeepInfra
output / 1M$0.60via DeepInfra
context262.1K
max output32.8K
// price history ($/1M tokens)
// cheaper or similar alternatives
| model | in | out | ctx | vs Qwen3 VL 30B A3B Instruct |
|---|---|---|---|---|
| Gemma 4 E2B IT | $0.04 | $0.08 | 131.1K | −81% |
| Qwen3.7 Flash | $0.03 | $0.13 | 1M | −79% |
| Gemma 3 12B IT | $0.05 | $0.10 | 131.1K | −76.2% |
| Gemma 3 27B IT | $0.08 | $0.16 | 131.1K | −61.9% |
| Ministral 3 3B | $0.10 | $0.10 | 131.1K | −61.9% |
// price by host
| host | in $/1M | out $/1M |
|---|---|---|
| DeepInfra | $0.15 | $0.60 |
| Novita AI | $0.20 | $0.70 |
// faq
How much does Qwen3 VL 30B A3B Instruct cost?
Qwen3 VL 30B A3B Instruct costs $0.15 per million input tokens and $0.60 per million output tokens (cheapest tracked host: DeepInfra). At 50M input and 10M output tokens per month that is about $13.50.
What is the context window of Qwen3 VL 30B A3B Instruct?
262.1K tokens, with up to 32.8K output tokens per request.
What are cheaper alternatives to Qwen3 VL 30B A3B Instruct?
Gemma 4 E2B IT ($0.04 in / $0.08 out), Qwen3.7 Flash ($0.03 in / $0.13 out), Gemma 3 12B IT ($0.05 in / $0.10 out) offer the same input types and capabilities for less.
Is Qwen3 VL 30B A3B Instruct open weights?
Yes. It is available from 2 tracked hosts; the cheapest is DeepInfra at $0.15 input and $0.60 output per million tokens.
// spec sheet
- input / 1M
- $0.15
- output / 1M
- $0.60
- blended (3:1)
- $0.2625
- context
- 262.1K
- max output
- 32.8K
- input types
- text · image
- reasoning
- no
- tool calling
- yes
- structured output
- yes
- open weights
- yes
- knowledge cutoff
- n/a
- 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 12B IT | $0.05 | $0.10 | $3.50 |
| Qwen3 VL 30B A3B Instruct | $0.15 | $0.60 | $13.50 |
Base-tier list prices. Long-context tiers, caching and batch discounts are not included.