GLM 5.1
GLM 5.1 by Z.ai: 13 offers. From €0.88 per 1M input tokens, with EU processing from €1.25.
Calculate costs for this modelCompare offersView price history
Profile
| Profile | |
|---|---|
| Developer | Z.ai |
| Type | Language models |
| Origin | CN |
| Input types | text |
| Context (tokens) | 198,000 |
| Max. output (tokens) | 128,000 |
| Reasoning | mit |
| Parameters (bn) | 754 |
| Open weights | ✓ yes |
| Licence | – |
| VRAM at 4-bit (GB) | 419 (8 × RTX PRO 6000) |
| Released | – |
searchit Entity Extraction (–): 51.5 %
Offers with processing in the EU (3)
| Provider | Country | Variant | Input | Output | Source | As of |
|---|---|---|---|---|---|---|
| cortecs | AT | standard | €1.24 | €3.90 | api.cortecs.ai | 14 Oct 2026 |
| Nebius Token Factory | NL | standard | €1.25 | €3.93 | tokenfactory.nebius.com | 14 Oct 2026 |
| HostYourAI | NL | standard | €1.48 | €4.66 | hostyourai.com | 14 Oct 2026 |
€ per 1M tokens. Source: providers' pricing pages, read and checked by searchit. As of 14 Oct 2026.
Offers outside the EU (10)
| Provider | Country | Variant | Input | Output | Source | As of |
|---|---|---|---|---|---|---|
| Chutes | – | standard | €0.88 | €2.75 | llm.chutes.ai | 14 Oct 2026 |
| SiliconFlow | SG | standard | €1.06 | €3.34 | www.siliconflow.com | 2 Oct 2026 |
| Modular (Modular Cloud) | US | standard | €1.16 | €3.84 | www.modular.com | 14 Oct 2026 |
| Novita AI | US | standard | €1.23 | €3.93 | novita.ai | 13 Oct 2026 |
| FriendliAI | US | standard | €1.25 | €3.93 | friendli.ai | 13 Oct 2026 |
| Parasail | US | standard | €1.25 | €3.93 | www.parasail.io | 2 Oct 2026 |
| Parasail | US | serverless | €1.25 | €3.93 | www.parasail.io | 2 Oct 2026 |
| Z.ai | SG | standard | €1.25 | €3.93 | docs.z.ai | 10 Oct 2026 |
| io.net | US | standard | €1.25 | €3.93 | api.intelligence.io.solutions | 14 Oct 2026 |
| Venice.ai | US | standard | €1.38 | €4.33 | docs.venice.ai | 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) | 86.8 |
| Humanity's Last Exam (Artificial Analysis) | 30.1 |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 93.3 |
| FrontierMath Tiers 1-3 v2 (Epoch AI) | 36.8 |
| SimpleQA Verified (Epoch AI) | 34 |
| SWE-bench Verified (Epoch AI) | 74.2 |
| searchit Extraktions-Messlauf REPO-9 (PROMPT-CRAWLER-TEXT-START, 8 Dokumente × 3 Läufe) – treffer beziehungen | 38.1 |
| searchit Extraktions-Messlauf REPO-9 (PROMPT-CRAWLER-TEXT-START, 8 Dokumente × 3 Läufe) – treffer entitaeten | 64.9 |