Qwen3.5-9B
Qwen3.5-9B by Alibaba Cloud: 7 offers. From €0.089 per 1M input tokens, with EU processing from €0.10.
Calculate costs for this modelCompare offersView price history
Profile
| Profile | |
|---|---|
| Developer | Alibaba Cloud |
| Type | Language models |
| Origin | CN |
| Input types | text |
| Context (tokens) | 262,144 |
| Max. output (tokens) | 235,929 |
| Reasoning | ohne |
| Parameters (bn) | 9.65 |
| Open weights | ✓ yes |
| Licence | Apache-2.0 |
| VRAM at 4-bit (GB) | 10 (RTX PRO 4000) |
| Released | – |
searchit Entity Extraction (24 Sept 2026): 29.3 %
Offers with processing in the EU (4)
| Provider | Country | Variant | Input | Output | Source | As of |
|---|---|---|---|---|---|---|
| cortecs | AT | standard | €0.10 | €0.15 | api.cortecs.ai | 14 Oct 2026 |
| OVHcloud | FR | standard | €0.10 | €0.15 | www.ovhcloud.com | 13 Oct 2026 |
| HostYourAI | NL | standard | €0.17 | €0.23 | hostyourai.com | 14 Oct 2026 |
| regolo.ai / Seeweb | IT | standard | €0.07 | €0.35 | api.regolo.ai | 13 Oct 2026 |
€ per 1M tokens. Source: providers' pricing pages, read and checked by searchit. As of 14 Oct 2026.
Offers outside the EU (3)
| Provider | Country | Variant | Input | Output | Source | As of |
|---|---|---|---|---|---|---|
| DeepInfra | US | standard | €0.089 | €0.13 | deepinfra.com | 14 Oct 2026 |
| SiliconFlow | SG | standard | €0.089 | €0.13 | www.siliconflow.com | 2 Oct 2026 |
| Modular (Modular Cloud) | US | standard | €0.15 | €0.22 | www.modular.com | 14 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) | 80.6 |
| Humanity's Last Exam (Artificial Analysis) | 14.9 |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 61.7 |
| HallusionBench (llm-stats-Abzug) | 0.69 |
| MMMU-Pro (llm-stats-Abzug, Rang 1..50 von 69) | 0.7 |
| searchit Extraktions-Messlauf REPO-9 (PROMPT-CRAWLER-TEXT-START, 8 Dokumente × 3 Läufe) – treffer beziehungen | 11.1 |
| searchit Extraktions-Messlauf REPO-9 (PROMPT-CRAWLER-TEXT-START, 8 Dokumente × 3 Läufe) – treffer entitaeten | 47.4 |
| MMLU-Pro (TIGER-Lab Leaderboard) | 82.5 |