# Qwen3 VL 235B A22B Thinking API prices

Qwen3 VL 235B A22B Thinking (qwen) — 131k context, 41k max output.
11 metered per-token offers from 11 provider(s), in USD per 1M tokens.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Merge Gateway | $0.287 | $2.867 | $0.0574 | 131k |
| Eden AI | $0.4 | $4 | — | 131k |
| Kilo Gateway | $0.4 | $4 | — | 131k |
| OpenRouter | $0.4 | $4 | — | 131k |
| OrcaRouter | $0.4 | $4 | — | 131k |
| Hugging Face | $0.98 | $3.95 | — | 131k |
| Jalapeno Cloud | $0.98 | $3.95 | — | 131k |
| DevPass (LLM Gateway) | $0.98 | $3.95 | — | 131k |
| LLM Gateway | $0.98 | $3.95 | — | 131k |
| NovitaAI | $0.98 | $3.95 | — | 131k |
| NanoGPT | $0.5 | $6 | $0.25 | 33k |

## Summary

- Cheapest input: $0.287 per 1M tokens (Merge Gateway)
- Cheapest output: $2.867 per 1M tokens (Merge Gateway)
- First-party: not listed separately
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2025-09-23
- Inputs: image, text, video

HTML page: https://llmprice.gitlab.io/models/qwen3-vl-235b-a22b-thinking/
Full dataset: https://llmprice.gitlab.io/data/catalog.json