Models
Price comparison

GLM-5

GLM-5 by Z.ai: 15 offers. From €0.45 per 1M input tokens, with EU processing from €1.15.

Calculate costs for this modelCompare offersView price history

Profile

Profile
DeveloperZ.ai
TypeLanguage models
OriginCN
Input typestext
Context (tokens)200,000
Max. output (tokens)128,000
Reasoningohne
Parameters (bn)753.86
Open weights✓ yes
LicenceMIT
VRAM at 4-bit (GB)419 (8 × RTX PRO 6000)
Released–

searchit Entity Extraction (24 Sept 2026): 48.7 %

Offers with processing in the EU (1)

ProviderCountryVariantInputOutputSourceAs of
HostYourAINLstandard€1.15€3.68hostyourai.com14 Oct 2026

€ per 1M tokens. Source: providers' pricing pages, read and checked by searchit. As of 14 Oct 2026.

Offers outside the EU (14)

ProviderCountryVariantInputOutputSourceAs of
AWS BedrockUSflex€0.45€1.43pricing.us-east-1.amazonaws.com14 Oct 2026
AWS BedrockUSbatch€0.45€1.43pricing.us-east-1.amazonaws.com14 Oct 2026
SiliconFlowSGstandard€0.85€2.28www.siliconflow.com2 Oct 2026
io.netUSstandard€0.77€2.46api.intelligence.io.solutions14 Oct 2026
Modular (Modular Cloud)USstandard€0.85€2.82www.modular.com14 Oct 2026
AWS BedrockUSstandard€0.89€2.86pricing.us-east-1.amazonaws.com14 Oct 2026
Google Vertex AIUSstandard€0.89€2.86cloud.google.com14 Oct 2026
Novita AIUSstandard€0.89€2.86novita.ai13 Oct 2026
ParasailUSstandard€0.89€2.86www.parasail.io2 Oct 2026
ParasailUSserverless€0.89€2.86www.parasail.io2 Oct 2026
Venice.aiUSstandard€0.89€2.86docs.venice.ai14 Oct 2026
Z.aiSGstandard€0.89€2.86docs.z.ai10 Oct 2026
CrusoeUSstandard€1.25€3.94www.crusoe.ai10 Oct 2026
AWS BedrockUSpriority€1.56€5.01pricing.us-east-1.amazonaws.com14 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)82
Humanity's Last Exam (Artificial Analysis)29.3
ARC-AGI-2 (ARC Prize Foundation)4.9
OTIS Mock AIME 2024-2025 (Epoch AI)80
FrontierMath Tiers 1-3 v2 (Epoch AI)16.4
SWE-bench Verified (Epoch AI)72.1
Vectara HHEM-2.310.1
Vectara HHEM-2.3 – antwortrate99.7
Vectara HHEM-2.3 – halluzination10.1
LiveBench (Aufgabensatz 2026-01-08)68.9
searchit Extraktions-Messlauf REPO-9 (PROMPT-CRAWLER-TEXT-START, 8 Dokumente × 3 Läufe) – treffer beziehungen37.8
searchit Extraktions-Messlauf REPO-9 (PROMPT-CRAWLER-TEXT-START, 8 Dokumente × 3 Läufe) – treffer entitaeten59.6
MMLU-Pro (TIGER-Lab Leaderboard)86

Report an error on this page