Skip to content
ModelCap

GLM 4.7 Flash

Current board #52Arena #173Open weights

Z.ai·z-ai/glm-4.7-flash

GLM 4.7 Flash is a language model published by Z.ai. 4 OpenRouter endpoints are published in the latest snapshot. It accepts text input and returns text. The published context limit is 203K tokens. The catalogue declares support for reasoning, tool use, structured outputs.

ModelCap Index · Current board
55.4#52
Measured · 82% support · score interval 55.4–62.2
Market Gravity
38.2
Secondary market signal
Input
$0.06
per 1M tokens
Output
$0.40
per 1M tokens
Context
203K
tokens
Providers
4
endpoints
Gateway spend
—
latest · Vercel share

Providers

Uptime measured over the last 30 minutes
ProviderInputOutputContextQuantUptime
DeepInfrabf16Cheapest$0.06$0.40203Kbf1699.78%
Venicefp8$0.06$0.40128Kfp899.56%
Cloudflare$0.061$0.40131K—99.67%
Novitabf16$0.07$0.40200Kbf1688.40%

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
$0.06$0.40203K1240 ms35.0 tok/stools
novita
live
$0.07$0.40200K1255 ms70.4 tok/stools
featherless-ai
live
——————
zai-org
live · model author
———1639 ms87.9 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
cais/hle
hle
—14.4
Unpinned
not published
Reported
Quarantined
Idavidrein/gpqa
diamond
—75.2
Unpinned
not published
Reported
Quarantined
SWE-bench/SWE-bench_Verified
swe_bench_%_resolved
—59.2
Unpinned
not published
Reported
Quarantined

ModelCap Index · Current board

Methodology
55.4
Measured · 2 public benchmark observations across 2 boards
Current board
#52
Public rank basis
Measured (measured)
Index support
82.2% · strong
Index interval
55.4–62.2
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-4.7-flash · aggregates disclosed benchmark configurations · endpoint configuration not claimed · artifact metadata zai-org/GLM-4.7-Flash@7dd20894a642a0aa287e9827cb1a1f7f91386b67 (not the evaluation revision)
Direct benchmark observations
2
Breadth-adjusted BES point estimate
58.8
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
58.8
Evidence status
confirmed · 83% mass
General preference
58.5
Coding
60.4
Agents & tools
—
Reasoning
—
Evidence breadth
92%
Evidence coverage
82%
Market and catalogue signals · secondary, never the language Index rank
Usage (OpenRouter popularity)
18.3
Liquidity (providers × uptime)
58.8
Open reach (HF downloads)
74.3
Surface (context / tools / modalities)
73.4
Freshness
46.6
  • · OpenRouter popularity #105
  • · 4 live providers
  • · HF 30d downloads 1953685
  • · Catalogue: context 202752, reasoning, tools
  • · First seen 2026-01-19

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
83.9
strong · 94% metadata coverage
Not capability
Artifact reproducibility
85.0
Access & legal clarity
100.0
Deployability
94.4
Evaluation provenance
50.6

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
38.2
OpenRouter weekly popularity
#105 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
#173 of 385
Rating
1367.7
95% confidence interval
1362–1374
Votes
12K
Source snapshot
6 Aug 2026, 13:00 UTC
Category
overall
Identity match confidence
100%

Market Gravity breakdown

Usage55%
18.3

OpenRouter weekly popularity across the full model catalogue.

Liquidity25%
58.8

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

Open reach15%
74.3

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

Freshness5%
46.6

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

Specification

Context window
203K tokens
Max output
16K tokens
Inputs
Text
Outputs
Text
Tokenizer
Other
Cached input tokens
$0.01 / 1M
First seen on OpenRouter
19 Jan 2026

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
7dd20894a642
Parameters
31.2B
Architecture
Glm4MoeLiteForCausalLM
Model type
glm4_moe_lite
Hugging Face downloads (30d)
2.0M
Downloads (all time)
10.7M
Likes
2K
Repository
zai-org/GLM-4.7-Flash
Repository updated
29 Jan 2026, 08:06 UTC