# Qwen3 30B A3B Thinking 2507 — price & specs

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

| Field | Value |
|---|---|
| Vendor | Qwen (Alibaba) |
| Input price | $0.2 / 1M tokens |
| Output price | $2.4 / 1M tokens |
| Cached input | n/a / 1M tokens |
| Context window | 81,920 tokens |
| Max output | 32,768 tokens |
| Input modalities | text |
| Reasoning / tool use | yes / yes |
| Intelligence / coding index | 9.8 / 12.1 |
| Released | 2025-08-28 |
| Retirement date | 2026-10-09 |

## About

Qwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimized for complex tasks requiring extended multi-step thinking. The model is designed specifically for “thinking mode,” where internal reasoning traces are separated...

## Price history

- 2026-09-24: $0.2 in / $2.4 out

## Cheaper alternatives with similar intelligence

- [GLM 5.3 Flash](https://modelbank.ai/models/glm-5.3-flash): $0.0399 / $0.0784, intelligence 27.8
- [DeepSeek V4.1 Flash 1017](https://modelbank.ai/models/deepseek-v4.1-flash-1017): $0.098 / $0.29, intelligence 28.6
- [MiMo-V2.6-Flash](https://modelbank.ai/models/mimo-v2.6-flash): $0.14 / $0.28, intelligence 26.7
- [Claude Haiku 5.5](https://modelbank.ai/models/claude-haiku-5.5): $0.1 / $0.5, intelligence 36.5
- [GPT-6 Luna](https://modelbank.ai/models/gpt-6-luna): $0.1 / $0.5, intelligence 27.9

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