Skip to content
ModelCap

GLM 4.6V

Current board #54Arena #164Open weights

Z.ai·z-ai/glm-4.6v

GLM 4.6V is a language model published by Z.ai. 2 OpenRouter endpoints are published in the latest snapshot. It accepts image, text, video input and returns text. The published context limit is 131K tokens. The catalogue declares support for reasoning, tool use.

ModelCap Index · Current board
53.8#54
Measured · 44% support · score interval 53.8–66.8
Market Gravity
15.8
Secondary market signal
Input
$0.30
per 1M tokens
Output
$0.90
per 1M tokens
Context
131K
tokens
Providers
2
endpoints
Gateway spend
—
latest · Vercel share

Providers

Uptime measured over the last 30 minutes
ProviderInputOutputContextQuantUptime
Novitabf16Cheapest$0.30$0.90131Kbf1684.04%
Z.AIfp8$0.30$0.90131Kfp877.02%

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
zai-org
live · model author
———2152 ms54.8 tok/stools

Other versions (1)

ModelCap Index · Current board

Methodology
53.8
Measured · 2 public benchmark observations across 2 boards
Current board
#54
Public rank basis
Measured (measured)
Index support
43.7% · moderate
Index interval
53.8–66.8
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-4.6v · aggregates disclosed benchmark configurations · endpoint configuration not claimed · artifact metadata zai-org/GLM-4.6V@4e2d47eb0b41c5280d8294b17cef9e94fdcfff46 (not the evaluation revision)
Direct benchmark observations
2
Breadth-adjusted BES point estimate
60.3
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
60.3
Evidence status
confirmed · 71% mass
General preference
60.4
Coding
59.7
Agents & tools
—
Reasoning
—
Evidence breadth
92%
Evidence coverage
44%
Market and catalogue signals · secondary, never the language Index rank
Usage (OpenRouter popularity)
5.9
Liquidity (providers × uptime)
36.6
Open reach (HF downloads)
9.6
Surface (context / tools / modalities)
85.2
Freshness
39.8
  • · OpenRouter popularity #213
  • · 2 live providers
  • · HF 30d downloads 9207
  • · Catalogue: context 131072, reasoning, tools, modalities Image/Text/Video
  • · First seen 2025-12-08

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
81.9
strong · 94% metadata coverage
Not capability
Artifact reproducibility
85.0
Access & legal clarity
100.0
Deployability
91.1
Evaluation provenance
45.3

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
15.8
OpenRouter weekly popularity
#213 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
#164 of 385
Rating
1377.3
95% confidence interval
1366–1389
Votes
3K
Source snapshot
6 Aug 2026, 13:00 UTC
Category
overall
Identity match confidence
100%

Market Gravity breakdown

Usage55%
5.9

OpenRouter weekly popularity across the full model catalogue.

Liquidity25%
36.6

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

Open reach15%
9.6

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

Freshness5%
39.8

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

Specification

Context window
131K tokens
Max output
33K tokens
Inputs
Image, Text, Video
Outputs
Text
Tokenizer
Other
Cached input tokens
$0.055 / 1M
First seen on OpenRouter
8 Dec 2025

Capabilities

  • Supported: Reasoning
  • Supported: Tool use
  • Not 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
4e2d47eb0b41
Parameters
107.7B
Architecture
Glm4vMoeForConditionalGeneration
Model type
glm4v_moe
Hugging Face downloads (30d)
9K
Downloads (all time)
426K
Likes
395
Repository
zai-org/GLM-4.6V
Repository updated
9 Dec 2025, 05:34 UTC