borg Download

Z.ai · in Borg

GLM-4.6

GLM-4.6 follows GLM-4.5 as Z.ai's text-focused coding and agent model.

Reasoning200K tokens (vendor-stated)text

200K tokens (vendor-stated)Context window
—Median time to first token (gateway proxy)
—Output 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

SpecificationValue
ProviderZ.ai
FamilyGLM
Release date2025-09-30 Vendor source
Context window200K tokens (vendor-stated) Vendor source
Input modalitiestext
Output modalitiestext
ReasoningYes
Open weightsYes
Borg lane idsglm-4.6, z-ai/glm-4.6
Versions in BorgGLM-4.5 · GLM-4.6 · GLM-4.7 · GLM-5 · GLM-5.1 · GLM-5.2 · GLM-5.3

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

What GLM-4.6 is good for

GLM-4.6 follows GLM-4.5 as Z.ai's text-focused coding and agent model. Its longer context gives agents more room for source files, instructions and tool history than the preceding generation, while its updated reasoning and tool use target practical development rather than isolated code snippets. Z.ai also emphasizes better search-oriented agents, readable writing and front-end output. Unlike the smaller GLM-4.5-Air, this is positioned as a full flagship-class choice; GLM-4.7 subsequently improves multi-step execution further. Pick it for reviewing substantial repositories, implementing features through coding tools or managing search-and-write workflows that need extended context. Borg includes GLM-4.6 in its subscription, and you can let Borg Fusion select it when appropriate or pin its lane for repeatable coding runs.

How Borg uses it

GLM-4.6 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-4.6"

Measured on Borg

Measured on Borg: SearchAtlas AI Gateway production request logs. 30-day window ending 2026-10-08; 88 requests. Minimum 100 samples per published request metric.

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

Borg served 88 requests for this model in the last 30 days; not enough timed samples to publish a speed figure yet.

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-4.6?

GLM-4.6 is listed in Borg's subscription catalog as glm-4.6. GLM-4.6 follows GLM-4.5 as Z.ai's text-focused coding and agent model.

Is GLM-4.6 in Borg?

Yes. GLM-4.6 is listed in Borg's subscription catalog under the lane glm-4.6. 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-4.6 have?

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

Is GLM-4.6 good for coding?

No vendor-published coding evaluation is listed here. Its listed uses include large-repository code review, long-context coding agents, search-assisted technical writing, front-end implementation. Try the lane for your own tasks, and compare the output with your requirements before choosing a default.

How fast is GLM-4.6 on Borg?

Borg served 88 requests for this model in the last 30 days; not enough timed samples to publish a speed figure yet.

How much does GLM-4.6 cost on Borg vs the API?

This model is included in the Borg subscription. The vendor API list prices appear below with a source link. See the pricing explainer and cost savings calculator to compare billing approaches.

Sources