# Qwen3 30B A3B Instruct 2507 — price & specs

Source: https://modelbank.ai/models/qwen3-30b-a3b-instruct-2507 · updated 2026-11-12 · ModelBank

| Field | Value |
|---|---|
| Vendor | Qwen (Alibaba) |
| Input price | $0.1 / 1M tokens |
| Output price | $0.3 / 1M tokens |
| Cached input | $0.1 / 1M tokens |
| Context window | 262,144 tokens |
| Max output | 235,929 tokens |
| Input modalities | text |
| Reasoning / tool use | no / yes |
| Intelligence / coding index | — / — |
| Released | 2025-07-29 |
| Retirement date | none announced |

## About

Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and...

## Price history

- 2026-09-24: $0.0482 in / $0.19 out
- 2026-09-24: $0.1 in / $0.3 out
- 2026-09-29: $0.0482 in / $0.19 out
- 2026-10-02: $0.1 in / $0.3 out
- 2026-10-02: $0.0482 in / $0.19 out
- 2026-10-03: $0.1 in / $0.3 out
- 2026-10-03: $0.0482 in / $0.19 out
- 2026-10-06: $0.1 in / $0.3 out
- 2026-10-07: $0.0482 in / $0.19 out
- 2026-10-08: $0.1 in / $0.3 out
- 2026-10-18: $0.09 in / $0.3 out
- 2026-10-26: $0.1 in / $0.3 out


JSON: https://modelbank.ai/api/v1/models/qwen3-30b-a3b-instruct-2507