Qwen3 30B-A3B Instruct (2507)
API ID qwen3-30b-a3b-instruct-2507
qwen3-30b-a3b-instruct-2507 was a Qwen model, released July 2025.
- Status
- Retired
- Released
- July 2025
- Shutdown
- Oct 10, 2026
- Replacement
- Qwen3.7 Plusqwen3.7-plus
qwen3-30b-a3b-instruct-2507 stopped serving on October 10, 2026. Recommended replacement: qwen3.7-plus.
How to migrate to Qwen3.7 Plus
Benchmarks
Scores as each source published themComparing with Qwen3 30B-A3B, the previous model in this line. A score is compared only with the same benchmark from the same source, at the same setting where both have it. Full comparison: prices, limits, features
Arena
| Arena | Qwen3 30B-A3B Instruct (2507) | Qwen3 30B-A3B | Change | Rank | Date | Source |
|---|---|---|---|---|---|---|
TextBy category
| 1382 ±5 | 1327 ±5 | +55 | 187 of 415 23,316 votes | Oct 13, 2026 | source |
| Text: Coding | 1437 ±9 | 1385 ±9 | +52 | 170 of 410 4,613 votes | Oct 13, 2026 | source |
Rated as qwen3-30b-a3b-instruct-2507; Qwen3 30B-A3B as qwen3-30b-a3b. Ratings come from people voting between two anonymous answers; Text is style-controlled, as on arena.ai. Data: Arena (arena.ai), CC BY 4.0.
Epoch AI
| Benchmark | Qwen3 30B-A3B Instruct (2507) | Qwen3 30B-A3B | Change | Setting | Run | Source |
|---|---|---|---|---|---|---|
| GPQA Diamond | 55.6% | 61.7% | −6.1 pts | Aug 30, 2026 | source | |
| OTIS Mock AIME 2024-2025 | 62.2% | 62.8% | −0.6 pts | Aug 30, 2026 | source |
Run independently by Epoch AI. Data: Epoch AI, Capabilities & benchmarking (epoch.ai/benchmarks), CC BY.
Price history
USD per 1M tokens, standard tierWe started recording this model's prices on Oct 5, 2026. The history grows with each daily check.
Show as a table
| From | Type | Price |
|---|---|---|
| Oct 5, 2026 | Input | $0.20 |
| Oct 5, 2026 | Output | $0.80 |
Prices
USD per 1M tokens, every type and band, by tier| Type | Price $/1M | In effect |
|---|---|---|
| Standard | ||
| input | $0.20 | |
| output | $0.80 | |
Changelog
Changes we detected on Qwen's pages- Retired
qwen3-30b-a3b-instruct-2507 has been retired
Info
- Feature changed
qwen3-30b-a3b-instruct-2507: Fine-tuning not supported → not supported (supported in the Beijing region only)
Info
- Feature changed
qwen3-30b-a3b-instruct-2507: Function calling not supported → not supported (supported in the Beijing region only)
Info
Last checked · Sources: Qwen models, Qwen deprecations, Qwen free terms