# Qwen/Qwen3-VL-8B-Instruct API prices

Qwen/Qwen3-VL-8B-Instruct (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 | $0.08 | $0.5 | — | 131k |
| Kilo Gateway | $0.117 | $0.455 | — | 131k |
| SiliconFlow | $0.18 | $0.68 | — | 262k |
| SiliconFlow (China) | $0.18 | $0.68 | — | 262k |

## Summary

- Cheapest input: $0.08 per 1M tokens (NovitaAI)
- Cheapest output: $0.455 per 1M tokens (Kilo Gateway)
- First-party: not listed separately
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2025-10-15
- Inputs: image, text, video

HTML page: https://llmprice.gitlab.io/models/qwen-qwen3-vl-8b-instruct/
Full dataset: https://llmprice.gitlab.io/data/catalog.json