Language modelActive

GLM-4.7-Flash

Z.ai

Released: January 19, 2026
Data date: September 8, 2026

Speed: 106.3 tokens/s
Output throughput
Price: $0.06 · $0.4
Input · Output / 1M tokens
Input: Text
Output: Text

GLM-4.7-Flash reduces the GLM-4.7 class to a 30B MoE with 3B active parameters. Its context remains roughly 200K tokens, matching the larger model. The Flash label therefore identifies a separate compact weight class rather than a shortened setting of the large model.

The model card documents thinking and non-thinking modes together with API access alongside the weights. Flash denotes the smaller text-oriented weight class in the GLM-4.7 line, not an additional multimodal model.

Specifications and access

Specification	Value and source
Weights	Open weightsSource
Access	API, LocalSource
Parameters	30BSource
Active parameters	3BSource
Context window	200,000 tokensSource
License	MITSource
Architecture	MoE hybrid reasoning modelSource
Parameters	30 BSource
Active parameters	3 BSource
Rounded context label	200KSource
Model configuration context	202,752 tokens (Native checkpoint context; distinct from the rounded serving label.)Source
Input	TextSource
Output	TextSource
Reasoning mode	thinking, non-thinkingSource
Tool calling	YesSource

Measurements without matching peer values

These measurements have no matching peer values under the same test conditions. Their original values and sources remain available here.

AIME 25 (Show measurement, test conditions, and source)

Source value: 91.6
Score: 91.6
Metric: percent
Unit: %
Category: mixed
Direction: Higher is better
Source type: vendor-reported
Evaluator: GLM-4.7-Flash model card
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. vendor table; exact temperature/effort not stated in table

Source GLM-4.7-Flash model card

GPQA (Show measurement, test conditions, and source)

Source value: 75.2
Score: 75.2
Metric: percent
Unit: %
Category: mixed
Direction: Higher is better
Source type: vendor-reported
Evaluator: GLM-4.7-Flash model card
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. vendor table; exact temperature/effort not stated in table

Source GLM-4.7-Flash model card

LCB v6 (Show measurement, test conditions, and source)

Source value: 64
Score: 64
Metric: percent
Unit: %
Category: mixed
Direction: Higher is better
Source type: vendor-reported
Evaluator: GLM-4.7-Flash model card
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. vendor table; exact temperature/effort not stated in table

Source GLM-4.7-Flash model card

HLE (Show measurement, test conditions, and source)

Source value: 14.4
Score: 14.4
Metric: percent
Unit: %
Category: mixed
Direction: Higher is better
Source type: vendor-reported
Evaluator: GLM-4.7-Flash model card
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. vendor table; exact temperature/effort not stated in table

Source GLM-4.7-Flash model card

SWE-bench Verified (Show measurement, test conditions, and source)

Source value: 59.2
Score: 59.2
Metric: percent
Unit: %
Category: mixed
Direction: Higher is better
Source type: vendor-reported
Evaluator: GLM-4.7-Flash model card
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. vendor table; exact temperature/effort not stated in table

Source GLM-4.7-Flash model card

tau2-Bench (Show measurement, test conditions, and source)

Source value: 79.5
Score: 79.5
Metric: percent
Unit: %
Category: mixed
Direction: Higher is better
Source type: vendor-reported
Evaluator: GLM-4.7-Flash model card
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. vendor table; exact temperature/effort not stated in table

Source GLM-4.7-Flash model card

BrowseComp (Show measurement, test conditions, and source)

Source value: 42.8
Score: 42.8
Metric: percent
Unit: %
Category: mixed
Direction: Higher is better
Source type: vendor-reported
Evaluator: GLM-4.7-Flash model card
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. vendor table; exact temperature/effort not stated in table

Source GLM-4.7-Flash model card

Artificial Analysis Intelligence Index (Show measurement, test conditions, and source)

Source value: 14.8719733920138
Score: 14.8719733920138
Metric: points
Unit: points
Direction: Higher is better
Source type: independent-evaluator
Evaluator: Artificial Analysis
Status: active
Retrieved at: 2026-09-08
Methodology: Independent evaluation. unknown

Source Artificial Analysis

Output speed (Show measurement, test conditions, and source)

Source value: 106.345239576466
Score: 106.345239576466
Metric: tokens/s
Unit: tokens/s
Direction: Higher is better
Source type: independent-evaluator
Evaluator: Artificial Analysis
Status: active
Retrieved at: 2026-09-08
Methodology: Independent evaluation. unknown; default 10K-input workload only
Context: Artificial Analysis performance timing; output speed is decoded after the first streaming chunk. Provider basis: serving-provider median. Deprecated model. Artificial Analysis only continues benchmarking the default 10K-input workload.

Source Artificial Analysis

Latency reasoning time (Show measurement, test conditions, and source)

Source value: 18.806671628793776
Score: 18.806671628793776
Metric: seconds
Unit: seconds
Direction: Lower is better
Source type: independent-evaluator
Evaluator: Artificial Analysis
Status: active
Retrieved at: 2026-09-08
Methodology: Independent evaluation. unknown; default 10K-input workload only
Context: Artificial Analysis performance timing; output speed is decoded after the first streaming chunk. Provider basis: serving-provider median. Deprecated model. Artificial Analysis only continues benchmarking the default 10K-input workload.

Source Artificial Analysis

Latency input time (Show measurement, test conditions, and source)

Source value: 1.05293614000038
Score: 1.05293614000038
Metric: seconds
Unit: seconds
Direction: Lower is better
Source type: independent-evaluator
Evaluator: Artificial Analysis
Status: active
Retrieved at: 2026-09-08
Methodology: Independent evaluation. unknown; default 10K-input workload only
Context: Artificial Analysis performance timing; output speed is decoded after the first streaming chunk. Provider basis: serving-provider median. Deprecated model. Artificial Analysis only continues benchmarking the default 10K-input workload.

Source Artificial Analysis

Answer generation time (end-to-end timing breakdown) (Show measurement, test conditions, and source)

Source value: 4.701667907198444
Score: 4.701667907198444
Metric: seconds
Unit: seconds
Direction: Lower is better
Source type: independent-evaluator
Evaluator: Artificial Analysis
Status: active
Retrieved at: 2026-09-08
Methodology: Independent evaluation. unknown; default 10K-input workload only
Context: Artificial Analysis performance timing; output speed is decoded after the first streaming chunk. Provider basis: serving-provider median. Deprecated model. Artificial Analysis only continues benchmarking the default 10K-input workload.

Source Artificial Analysis

Page 1 of 2

Sources and data date

Type	Evidence and data date
Speed	Median across serving providers. Output speed after the first streaming chunk, not total response time. Classified as deprecated by Artificial Analysis. Artificial Analysis maintains only the default 10K-input workload there. Retrieved September 8, 2026. Source: Artificial Analysis · Artificial Analysis (retrieved September 8, 2026)Speed measurement methodology
Price	Base API prices without caching or batch discounts. Higher context tiers and other rates are listed under Costs. Source: Pricing · API pricing
Input	Documented modalities. Retrieved September 8, 2026. Source: Model documentation · GLM-4.7-Flash model card (retrieved September 8, 2026) · GLM-4.7-Flash documentation · Editorial description reviewed October 2, 2026
Output	Documented modalities. Retrieved September 8, 2026. Source: Model documentation · GLM-4.7-Flash model card (retrieved September 8, 2026) · GLM-4.7-Flash documentation · Editorial description reviewed October 2, 2026
Research status	Research date September 8, 2026. 4 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication.
Unresolved	release-date Original wording No normalized release-date field.
Additional source	Model metadata · GLM-4.7-Flash model card · Editorial description reviewed October 2, 2026
Additional source	Model metadata (retrieved September 8, 2026) · GLM release notes · Editorial description reviewed October 2, 2026
Additional source	Model metadata (retrieved September 8, 2026)
Additional source	OpenRouter: Popularity index (derived), CC BY 4.0
Additional source	Vercel AI Gateway: Popularity index (derived), CC BY 4.0
Additional source	Creative Commons Attribution 4.0

GLM-4.7-Flash

Specifications and access

Measurements without matching peer values

Our tests

Pelican on a bicycle

Popularity

Published prices

Sources and data date