Skip to content
ModelCap

GLM 4.6

All-versions archive #66Arena #99Open weights

Z.ai·z-ai/glm-4.6

GLM 4.6 is a language model published by Z.ai. 5 OpenRouter endpoints are published in the latest snapshot. It accepts text input and returns text. The published context limit is 205K tokens. The catalogue declares support for reasoning, tool use, structured outputs.

ModelCap Index · All-versions archive
69.8#66
Measured · 89% support · score interval 69.8–75.6
Market Gravity
39.1
Secondary market signal

Superseded by GLM 5.2. It no longer holds a current-board position; its all-versions archive rank is #66.

Input
$0.50
per 1M tokens
Output
$2.00
per 1M tokens
Context
205K
tokens
Providers
5
endpoints
Gateway spend
—
latest · Vercel share

Providers

Uptime measured over the last 30 minutes
ProviderInputOutputContextQuantUptime
Venicefp4Cheapest$0.43$1.75198Kfp499.15%
DeepInfrafp4$0.50$2.00203Kfp4100.0%
Novitabf16$0.55$2.20205Kbf1698.57%
Z.AIfp4$0.60$2.20203Kfp498.15%
AtlasCloudfp8$0.60$2.20203Kfp894.84%

Hugging Face Inference Providers

Exact repository identity

Provider economics and telemetry published by the Hugging Face Router. These are operational signals, not benchmark results.

ProviderInputOutputContextTTFTThroughputFeatures
deepinfra
live
$0.50$2.00203K864 ms30.3 tok/stools · structured
novita
live
$0.55$2.20205K1183 ms39.4 tok/stools
featherless-ai
live
——————
zai-org
live · model author
———4139 ms34.9 tok/stools

Reported evaluation leads (3)

Excluded from score

Structured rows reported in this exact model repository at the pinned revision below. They are useful research leads, but remain quarantined until dataset revision, harness, configuration and identity pass ModelCap’s independent admission review.

Dataset / taskMetricValueRevisionProvenance
harborframework/terminal-bench-2.0
terminalbench_2
—24.5
Unpinned
not published
Reported
Quarantined
mercor/apex-agents
apex-agents
—4
Unpinned
not published
Reported
Quarantined
ScaleAI/SWE-bench_Pro
SWE_Bench_Pro
—9.67
Unpinned
not published
Reported
Quarantined

Other versions (5)

ModelCap Index · All-versions archive

Methodology
69.8
Measured · 4 public benchmark observations across 4 boards
All-versions archive
#66
Public rank basis
Measured (measured)
Index support
88.7% · strong
Index interval
69.8–75.6
Rank posterior
Not available
Top 5 / Top 10 probability
Not available / Not available
Posterior as of
Snapshot timestamp unavailable
Identity binding
Exact catalogue product · z-ai/z-ai/glm-4.6 · aggregates disclosed benchmark configurations · endpoint configuration not claimed · artifact metadata zai-org/GLM-4.6@be72194883d968d7923a07e2f61681ea9a2826d1 (not the evaluation revision)
Direct benchmark observations
4
Breadth-adjusted BES point estimate
72.7
Bayesian Evidence Score · measured evidence input only

BES normalizes admitted public benchmark evidence for measured Index rows. Its legacy score and observables prior do not define the public language rank.

Observed capability
72.7
Evidence status
confirmed · 95% mass
General preference
74.4
Coding
55.0
Agents & tools
91.9
Reasoning
—
Evidence breadth
97%
Evidence coverage
89%
Market and catalogue signals · secondary, never the language Index rank
Usage (OpenRouter popularity)
15.8
Liquidity (providers × uptime)
87.4
Open reach (HF downloads)
46.8
Surface (context / tools / modalities)
73.5
Freshness
30.6
  • · OpenRouter popularity #121
  • · 5 live providers
  • · HF 30d downloads 27092
  • · Catalogue: context 204800, reasoning, tools
  • · First seen 2025-09-30

These adoption and deployment observations remain context only. They do not change this model's ModelCap Index score or rank.

BES evidence selected · measured input only

The bounded 0–100 capability score blends each source’s competitive placement with its published achievement, then combines capability families. Evidence breadth adds a modest uncertainty adjustment; price and popularity are not part of benchmark-led rank.

Deployment readiness

Metadata index
90.2
strong · 94% metadata coverage
Not capability
Artifact reproducibility
85.0
Access & legal clarity
100.0
Deployability
95.3
Evaluation provenance
80.5

Missing: artifactReproducibility.base-lineage, evaluationProvenance.evaluation-dataset-revisions.

A metadata completeness and deployability index—not a safety certification, quality grade, or production-readiness claim.

Market activity

Venue coverage
Market Gravity
39.1
OpenRouter weekly popularity
#121 of 298

Market Gravity uses OpenRouter’s full-catalogue popularity order. Sparse Vercel top-ten observations appear only when published and do not affect the score.

Arena preference

Status
Ranked
Source
Arena
Official rank
#99 of 385
Rating
1425.0
95% confidence interval
1421–1429
Votes
36K
Source snapshot
6 Aug 2026, 13:00 UTC
Category
overall
Identity match confidence
100%

Market Gravity breakdown

Usage55%
15.8

OpenRouter weekly popularity across the full model catalogue.

Liquidity25%
87.4

Independent providers versus the model's open or closed cohort, weighted by uptime.

Open reach15%
46.8

Hugging Face 30-day downloads for open models; neutral for closed models.

Freshness5%
30.6

Time since first public availability, on a six-month half-life.

Specification

Context window
205K tokens
Max output
131K tokens
Inputs
Text
Outputs
Text
Tokenizer
Other
Cached input tokens
$0.10 / 1M
First seen on OpenRouter
30 Sept 2025
Knowledge cutoff
2025-03-31

Capabilities

  • Supported: Reasoning
  • Supported: Tool use
  • Supported: Structured output
  • Supported: Response format
  • Not supported: Moderated

Weights & access

Open weights. Downloadable weights are published under an OSI or free-culture license in the current repository metadata. This describes weight availability, not whether the full training stack qualifies as Open Source AI.

Access
Open weights
Licence
mit
Pinned revision
be72194883d9
Parameters
356.8B
Architecture
Glm4MoeForCausalLM
Model type
glm4_moe
Hugging Face downloads (30d)
27K
Downloads (all time)
774K
Likes
1K
Repository
zai-org/GLM-4.6
Repository updated
30 Sept 2025, 10:17 UTC