Qwen3.5-27B
Qwen3.5-27B by Alibaba Cloud: 2 offers. From €0.27 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 | Language models |
| Origin | CN |
| Input types | text+bild+video |
| Context (tokens) | 262,144 |
| Max. output (tokens) | 65,536 |
| Reasoning | ohne |
| Parameters (bn) | 27.78 |
| Open weights | ✓ yes |
| Licence | Apache-2.0 |
| VRAM at 4-bit (GB) | 20 (RTX PRO 4000) |
| Released | – |
searchit Entity Extraction (24 Sept 2026): 55.1 %
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 |
|---|---|---|---|---|---|---|
| Novita AI | US | standard | €0.27 | €2.15 | novita.ai | 13 Oct 2026 |
| DeepInfra | US | standard | €0.23 | €2.32 | deepinfra.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) | 85.8 |
| Humanity's Last Exam (Artificial Analysis) | 23.9 |
| HallusionBench (llm-stats-Abzug) | 0.7 |
| Vectara HHEM-2.3 | 12.1 |
| Vectara HHEM-2.3 – antwortrate | 99.8 |
| Vectara HHEM-2.3 – halluzination | 12.1 |
| MMMU-Pro (llm-stats-Abzug, Rang 1..50 von 69) | 0.75 |
| searchit Extraktions-Messlauf REPO-9 (PROMPT-CRAWLER-TEXT-START, 8 Dokumente × 3 Läufe) – treffer beziehungen | 43.3 |
| searchit Extraktions-Messlauf REPO-9 (PROMPT-CRAWLER-TEXT-START, 8 Dokumente × 3 Läufe) – treffer entitaeten | 67 |
| MMLU-Pro (TIGER-Lab Leaderboard) | 86.1 |