GLM-5-Turbo

At a glance

Specification	Value
Provider	Z.ai
Family	GLM
Context window	200K tokens (vendor-stated) Vendor source
Input modalities	text
Output modalities	text
Reasoning	Yes
Open weights	No
Borg lane ids	glm-5-turbo, z-ai/glm-5-turbo
Median time to first token (gateway proxy) on Borg	6222 ms
Median tokens per second (end to end) on Borg	16.4 output tokens per second

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

What GLM-5-Turbo is good for

GLM-5-Turbo is a public Z.ai variant optimized around OpenClaw-style agent workflows, rather than a generic promise of faster responses. Relative to baseline GLM-5, the vendor emphasizes command following, dependable tool calls, scheduled or persistent activities and execution across long action chains. The text-only model supports thinking modes and MCP connections, making it better suited to orchestrating external tools than to interpreting pictures or generating media. Choose it for automation that repeatedly invokes skills, carries out multi-stage instructions or coordinates work over time. Z.ai documents the model but does not list it in the checked per-token pricing table, so its separate API rate should not be inferred from GLM-5. Borg includes this lane in its subscription; Fusion can route to it or you can explicitly select it.

• OpenClaw agent automation
• scheduled tool-driven workflows
• multi-step command execution
• MCP-backed agent orchestration

How Borg uses it

GLM-5-Turbo 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-5-turbo"

Measured on Borg

Time to first token (gateway proxy)

Output tokens per second (whole turn)

• 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; 32201 requests. Minimum 100 samples per published request metric.

Borg coding bench

Hard-graded with tests plus lint, no LLM judge; 3 tasks, 15 runs, 2026-09-20.

Source: Borg coding bench, hard-graded by tests and ruff; no LLM judge

Pricing

Included in Borg subscription. Vendor API list price: Not published.

Compare subscription and API pricing · Cost Savings Calculator

FAQ

What is GLM-5-Turbo?

GLM-5-Turbo is listed in Borg's subscription catalog as glm-5-turbo. GLM-5-Turbo is a public Z.ai variant optimized around OpenClaw-style agent workflows, rather than a generic promise of faster responses.

Is GLM-5-Turbo in Borg?

Yes. GLM-5-Turbo is listed in Borg's subscription catalog under the lane glm-5-turbo. 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-5-Turbo have?

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

Is GLM-5-Turbo good for coding?

No vendor-published coding evaluation is listed here. Its listed uses include OpenClaw agent automation, scheduled tool-driven workflows, multi-step command execution, MCP-backed agent orchestration. Try the lane for your own tasks, and compare the output with your requirements before choosing a default.

How fast is GLM-5-Turbo on Borg?

Measured on Borg: SearchAtlas AI Gateway production request logs. 30-day window ending 2026-10-08; 32201 requests. Minimum 100 samples per published request metric.

How does GLM-5-Turbo do on Borg's coding bench?

GLM-5-Turbo passed 60% overall and 67% of hidden tests across 15 runs.

How much does GLM-5-Turbo cost on Borg vs the API?

This model is included in the Borg subscription. A vendor API price is not published here. See the pricing explainer and cost savings calculator to compare billing approaches.

Sources

• https://docs.z.ai/guides/llm/glm-5-turbo.md
• https://docs.z.ai/release-notes/new-released.md
• https://docs.z.ai/guides/overview/pricing.md

Related

Other Z.ai models: GLM-4.5 · GLM-4.5-Air · GLM-4.6 · GLM-4.7 · GLM-5 · GLM-5.1 · GLM-5.2 · GLM-5.3

Models sharing a Fusion role: Not published

All makers and models