# Qwen3 VL 235B A22B Instruct API prices

Qwen3 VL 235B A22B Instruct (qwen) — 262k context, 262k max output.
17 metered per-token offers from 16 provider(s), in USD per 1M tokens.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Deep Infra | $0.2 | $0.88 | $0.11 | 262k |
| DevPass (LLM Gateway) | $0.2 | $0.88 | $0.11 | 262k |
| LLM Gateway | $0.2 | $0.88 | $0.11 | 262k |
| Kilo Gateway | $0.26 | $1.04 | — | 131k |
| Merge Gateway | $0.287 | $1.147 | $0.1578 | 131k |
| NanoGPT | $0.3 | $1.2 | $0.15 | 131k |
| Helicone | $0.3 | $1.5 | — | 256k |
| Hugging Face | $0.3 | $1.5 | — | 131k |
| Jalapeno Cloud | $0.3 | $1.5 | — | 129k |
| LLM Gateway | $0.3 | $1.5 | — | 131k |
| NovitaAI | $0.3 | $1.5 | — | 131k |
| OpenRouter | $0.21 | $1.9 | $0.1 | 262k |
| TensorX | $0.21 | $1.9 | $0.0525 | 131k |
| Eden AI | $0.4 | $1.6 | — | 131k |
| OrcaRouter | $0.4 | $1.6 | — | 131k |
| Vercel AI Gateway | $0.4 | $1.6 | — | 131k |
| Amazon Bedrock | $0.53 | $2.66 | — | 262k |

## Summary

- Cheapest input: $0.2 per 1M tokens (Deep Infra)
- Cheapest output: $0.88 per 1M tokens (Deep Infra)
- 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-instruct/
Full dataset: https://llmprice.gitlab.io/data/catalog.json