# Qwen/Qwen3-VL-30B-A3B-Thinking API prices

Qwen/Qwen3-VL-30B-A3B-Thinking (qwen) — 262k context, 262k max output.
4 metered per-token offers from 4 provider(s), in USD per 1M tokens.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| NovitaAI | $0.2 | $1 | — | 131k |
| SiliconFlow | $0.29 | $1 | — | 262k |
| SiliconFlow (China) | $0.29 | $1 | — | 262k |
| Kilo Gateway | $0.2 | $2.4 | — | 131k |

## Summary

- Cheapest input: $0.2 per 1M tokens (NovitaAI)
- Cheapest output: $1 per 1M tokens (NovitaAI)
- First-party: not listed separately
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2025-10-11
- Inputs: image, text, video

HTML page: https://llmprice.gitlab.io/models/qwen-qwen3-vl-30b-a3b-thinking/
Full dataset: https://llmprice.gitlab.io/data/catalog.json