All modelsCalculate what your real prompts cost on Qwen3 30B A3B Instruct 2507
Qwen3 30B A3B Instruct 2507
open sourceQwen model, released 29 Jul 2025.
$0.0482
per 1M input tokens
$0.193
per 1M output tokens
—
per 1M cached-read tokens
Price history
input $/1M output $/1M7 Jul 2026 → 3 Oct 2026
Specifications
- Lab
- Qwen
- Released
- 29 Jul 2025
- Context window
- 262k tokens
- Max output
- 32k tokens
- Input modalities
- text
- Output modalities
- text
- Knowledge cutoff
- 2025-06-30
- Open source
- Yes
Benchmarks
| Benchmark | Category | Score | As of |
|---|---|---|---|
| LMArena (Chatbot Arena) | coding | 1417.1 (1408.3–1425.9) | 13 Sept 2026 |
| LMArena (Chatbot Arena) | overall | 1383.6 (1378.7–1388.5) | 13 Sept 2026 |
LMArena (Chatbot Arena) data © their authors, CC-BY-4.0
Frequently asked questions
How much does Qwen3 30B A3B Instruct 2507 cost?
Qwen3 30B A3B Instruct 2507 costs $0.0482 per 1M input tokens and $0.193 per 1M output tokens (list price, updated every 6 hours).
What is Qwen3 30B A3B Instruct 2507's context window?
Qwen3 30B A3B Instruct 2507 supports a 262k-token context window with up to 32k output tokens.