# Qwen3 30B A3B Instruct 2507 API prices

Qwen3 30B A3B Instruct 2507 (qwen) — 262k context, 262k max output.
6 metered per-token offers from 8 provider(s), in USD per 1M tokens.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| OpenRouter | $0.09 | $0.3 | — | 262k |
| Cortecs | $0.099 | $0.299 | — | 262k |
| Nebius Token Factory | $0.1 | $0.3 | $0.01 | 262k |
| Weights & Biases | $0.1 | $0.3 | $0.1 | 262k |
| NanoGPT | $0.2 | $0.5 | $0.1 | 256k |
| Clarifai | $0.3 | $0.5 | — | 262k |

## Summary

- Cheapest input: $0.09 per 1M tokens (OpenRouter)
- Cheapest output: $0.299 per 1M tokens (Cortecs)
- First-party: not listed separately
- Free offers: ModelScope
- Subscription plans (not per-token): none
- Released: 2025-07-29
- Inputs: text

HTML page: https://llmprice.gitlab.io/models/qwen3-30b-a3b-instruct-2507/
Full dataset: https://llmprice.gitlab.io/data/catalog.json