Qwen3-VL 30B-A3B Instruct
Qwen3-VL 30B-A3B Instruct by Alibaba Cloud: 2 offers. From €0.13 per 1M input tokens. No offer with EU processing is listed.
Calculate costs for this modelCompare offersView price history
Profile
| Profile | |
|---|---|
| Developer | Alibaba Cloud |
| Type | Image models |
| Origin | CN |
| Input types | text+bild+video |
| Context (tokens) | 262,144 |
| Max. output (tokens) | – |
| Reasoning | ohne |
| Parameters (bn) | 31.07 |
| Open weights | ✓ yes |
| Licence | Apache-2.0 |
| VRAM at 4-bit (GB) | 22 (RTX PRO 4000) |
| Released | – |
Offers with processing in the EU (0)
No offers in this group.
Offers outside the EU (2)
| Provider | Country | Variant | Input | Output | Source | As of |
|---|---|---|---|---|---|---|
| DeepInfra | US | standard | €0.13 | €0.54 | deepinfra.com | 14 Oct 2026 |
| Novita AI | US | standard | €0.18 | €0.63 | novita.ai | 13 Oct 2026 |
€ per 1M tokens. Source: providers' pricing pages, read and checked by searchit. As of 14 Oct 2026.
AI Act
Whether the developer has signed the Code of Practice for general-purpose AI models: unknown. What this means is explained under “EU and AI Act”. EU processing and AI Act
Benchmarks
| Benchmarks | |
|---|---|
| GPQA Diamond (Artificial Analysis) | 69.5 |
| Humanity's Last Exam (Artificial Analysis) | 6.3 |
| HallusionBench (llm-stats-Abzug) | 0.61 |
| OCRBench v2, englische Spur (llm-stats-Abzug) | 0.63 |