Z.ai · in Borg

GLM-4.7

GLM-4.7 is the successor to GLM-4.6 in Z.ai's text-only GLM line.

Reasoning200K tokens (vendor-stated)text

200K tokens (vendor-stated)Context window

—Median time to first token (gateway proxy)

40.6Output tokens per second (whole turn)

$0.6 / $2.2Vendor API price in / out · per 1M

Included in Borg

Download Borg Borg for Business

At a glance

Specification	Value
Provider	Z.ai
Family	GLM
Release date	2025-12-22 Vendor source
Context window	200K tokens (vendor-stated) Vendor source
Input modalities	text
Output modalities	text
Reasoning	Yes
Open weights	Yes
Borg lane ids	`glm-4.7`, `z-ai/glm-4.7`
Versions in Borg	GLM-4.5 · GLM-4.6 · GLM-4.7 · GLM-5 · GLM-5.1 · GLM-5.2 · GLM-5.3
Median tokens per second (end to end) on Borg	40.6 output tokens per second

Not published by the vendor: thinking modes, knowledge cutoff, fusion roles.

What GLM-4.7 is good for

GLM-4.7 is the successor to GLM-4.6 in Z.ai's text-only GLM line. Its emphasis shifts from producing a plausible code fragment to completing longer development tasks: breaking down requirements, coordinating front-end and back-end pieces and using tools across multiple steps. It keeps the expanded context of the previous generation, with thinking modes for harder work and structured output for integrations. Compared with the lighter Flash variants of its own series, this is the main higher-capability model; compared with GLM-5, it belongs to the earlier generation before the explicit agentic-engineering focus. It is a useful choice for executable prototypes, interactive applications and complicated coding-agent sessions. Borg includes it in the subscription; Fusion may route tasks to it, or you can select its lane directly.

end-to-end application prototypes
multi-step coding with tools
interactive front-end development
reasoning-intensive text tasks

How Borg uses it

GLM-4.7 is available as a subscription catalog lane in Borg. The catalog does not publish which Fusion profiles route to this model, so no routing role is claimed here. You can pick it directly by setting the OpenAI-compatible gateway model field to a listed lane id. Check the current catalog for availability before building a workflow around a lane.

model: "glm-4.7"

Measured on Borg

Metric	Median	95th percentile	Samples
Time to first token (gateway proxy)	—	—	69
Tokens per second (end to end)	40.6 output tokens per second	55 output tokens per second	585

Output tokens per second (whole turn)

Higher is fasterFleet median 31.9 tokens/s

GLM-4.740.6 tokens/s

Time to first token (gateway proxy): time until the first streamed response event reaches the gateway; our closest available measure of time to first token
Tokens per second (end to end): tokens per second, end to end: provider-reported output tokens divided by the whole turn's elapsed time, including queueing and reasoning; not a streaming per-token rate

Completion speed covers the whole turn including queueing and reasoning time; it is not a streaming tokens-per-second figure.

Measured on Borg: SearchAtlas AI Gateway production request logs. 30-day window ending 2026-10-08; 650 requests. Minimum 100 samples per published request metric.

Benchmarks

Benchmark	Vendor-reported score	Source
LiveCodeBench V6	84.9	Vendor source
SWE-bench Verified	73.8%	Vendor source
SWE-bench Multilingual	66.7%	Vendor source
Terminal Bench 2.0	41%	Vendor source
BrowseComp	67	Vendor source
τ²-Bench	84.7	Vendor source

Pricing

Included in Borg subscription. Vendor API list price: $0.6 input / $2.2 output per 1M tokens. Vendor price source.

Compare subscription and API pricing · Cost Savings Calculator

FAQ

What is GLM-4.7?

GLM-4.7 is listed in Borg's subscription catalog as glm-4.7. GLM-4.7 is the successor to GLM-4.6 in Z.ai's text-only GLM line.

Is GLM-4.7 in Borg?

Yes. GLM-4.7 is listed in Borg's subscription catalog under the lane glm-4.7. You can choose the lane directly, or explore the available Fusion profiles. Availability and model details can change; check the current catalog before deployment.

What context window does GLM-4.7 have?

The published context window is 200K tokens (vendor-stated). Consult the cited sources for details and current limits. Vendor source

Is GLM-4.7 good for coding?

Vendor-published evaluations appear in the benchmarks section; their settings may differ from your tasks. Its listed uses include end-to-end application prototypes, multi-step coding with tools, interactive front-end development, reasoning-intensive text tasks. Try the lane for your own tasks, and compare the output with your requirements before choosing a default.

How fast is GLM-4.7 on Borg?