Z.ai: GLM 4.6

Z.ai (GLM) · Tools · Structured output · Reasoning controls · Sampling controls · Output limits · Released Sep 30, 2025

Compare provider prices ↓Compare models

Best input$0.43Lowest linked input observation · live snapshot

Best output$1.75May come from a different provider

Context window202.8K202,752 tokens

Provider profiles4Price observed Sep 25, 2026 04:57 UTC

Provider pricing

Compare provider prices

Published rates for providers serving this model. Open any source to see where and when the price was checked.

Provider	Input	Output	Cached input	Batch input	Evidence
OpenRouteropenrouter.ai ↗	$0.43/ 1M	$1.75/ 1M	$0.08	Not published	Source https://openrouter.ai/api/v1/models See where this value came from and when it was checked. Source type Marketplace or aggregator Source retrieved Sep 19, 2026 · 21:57 UTC Effective date Not stated Verification Source verified View source ↗
DeepInfradeepinfra.com ↗	$0.5/ 1M	$2/ 1M	$0.1	Not published	Source https://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked. Source type Official provider API Source retrieved Aug 26, 2026 · 11:15 UTC Effective date Not stated Verification Source verified View source ↗
Z.aiz.ai ↗	$0.6/ 1M	$2.2/ 1M	$0.11	Not published	Source https://docs.z.ai/guides/overview/pricing See where this value came from and when it was checked. Source type Official provider documentation Source retrieved Sep 1, 2026 · 23:21 UTC Effective date Not stated Verification Source verified View source ↗
IO Intelligenceio.net ↗	$0.52/ 1M	$2.038/ 1M	$0.26	Not published	Source https://api.intelligence.io.solutions/api/v1/models See where this value came from and when it was checked. Source type Official provider API Source retrieved Sep 25, 2026 · 04:57 UTC Effective date Not stated Verification Source verified View source ↗

Performance

Published benchmark results

Benchmark results collected from published sources. Scores from different benchmark versions or test setups may not be directly comparable.

View all →

Benchmark	Category	Score	Origin	Evidence
GPQA Diamond	reasoning	72.30	Public benchmark	Source GPQA Diamond via OpenRouter See where this value came from and when it was checked. Source type Independent benchmark Source retrieved Aug 26, 2026 · 06:00 UTC Effective date Aug 26, 2026 · 00:00 UTC Verification Source verified View source ↗
TAU-Bench	reasoning	72.70	Public benchmark	Source TAU-Bench via OpenRouter See where this value came from and when it was checked. Source type Independent benchmark Source retrieved Aug 26, 2026 · 06:00 UTC Effective date Aug 26, 2026 · 00:00 UTC Verification Source verified View source ↗
Artificial Analysis Intelligence	reasoning	29.30	Public benchmark	Source Artificial Analysis Intelligence via OpenRouter See where this value came from and when it was checked. Source type Independent benchmark Source retrieved Aug 26, 2026 · 08:35 UTC Effective date Aug 26, 2026 · 00:00 UTC Verification Source verified View source ↗
Artificial Analysis Coding	reasoning	45.80	Public benchmark	Source Artificial Analysis Coding via OpenRouter See where this value came from and when it was checked. Source type Independent benchmark Source retrieved Aug 26, 2026 · 08:35 UTC Effective date Aug 26, 2026 · 00:00 UTC Verification Source verified View source ↗
Artificial Analysis Agentic	reasoning	18.60	Public benchmark	Source Artificial Analysis Agentic via OpenRouter See where this value came from and when it was checked. Source type Independent benchmark Source retrieved Aug 26, 2026 · 08:35 UTC Effective date Aug 26, 2026 · 00:00 UTC Verification Source verified View source ↗