GLM 4.6
GLM 4.6 by Z.ai: 4 offers. From €0.38 per 1M input tokens. No offer with EU processing is listed.
Calculate costs for this modelCompare offersView price history
Profile
| Profile | |
|---|---|
| Developer | Z.ai |
| Type | Language models |
| Origin | CN |
| Input types | text |
| Context (tokens) | 200,000 |
| Max. output (tokens) | 128,000 |
| Reasoning | mit |
| Parameters (bn) | 357 |
| Open weights | ✓ yes |
| Licence | MIT |
| VRAM at 4-bit (GB) | 201 (4 × RTX PRO 6000) |
| Released | – |
Offers with processing in the EU (0)
No offers in this group.
Offers outside the EU (4)
| Provider | Country | Variant | Input | Output | Source | As of |
|---|---|---|---|---|---|---|
| Venice.ai | US | standard | €0.38 | €1.56 | docs.venice.ai | 14 Oct 2026 |
| io.net | US | standard | €0.46 | €1.82 | api.intelligence.io.solutions | 14 Oct 2026 |
| Novita AI | US | standard | €0.49 | €1.97 | novita.ai | 13 Oct 2026 |
| Z.ai | SG | standard | €0.54 | €1.97 | docs.z.ai | 10 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) | 78 |
| Humanity's Last Exam (Artificial Analysis) | 14.5 |
| Berkeley Function-Calling Leaderboard V4 | 72.38 |
| Vectara HHEM-2.3 | 9.5 |
| Vectara HHEM-2.3 – antwortrate | 94.5 |
| Vectara HHEM-2.3 – halluzination | 9.5 |
| SWE-bench Pro Public (Scale AI) | 9.67 |