Zhipu AI: GLM-5-Turbo

Faster GLM-5 lane for coding agents that need lower latency

glm-5-turbo

AvailableZhipu AIChat

Input / Output: $1.20 / $4.00
Context: 200K
Max output: 128K
Modalities: Chat
Capabilities: Tool usePrompt Cache

About GLM-5-Turbo

GLM-5-Turbo is a Z.ai model built on GLM-5 and tuned from training for OpenClaw agent workflows. Z.ai reports gains over GLM-5 in tool-call reliability, decomposing complex instructions, and time-aware or long-running tasks, with faster execution for long chains. It takes text in and gives text out, and suits agents that call many tools.

Where it works well

Z.ai says tool invocation is more dependable than in GLM-5, which reduces failed calls inside multi-step agent chains.
Instruction decomposition for complex multi-step tasks is a stated improvement over the base model.
Scheduling and persistence for time-dependent and long-running jobs were tuned, which fits agents that wait on external events.
MCP tool integration, structured JSON output, context caching, streaming, and thinking mode are supported.

When to choose another model

It is optimized for agent execution, so for general coding review or long-form analysis the base GLM-5 or GLM-5.1 may be the more natural pick.
Input is text only; image or document understanding requires a vision model.

Getting started

Create API key
Create a key in Console, then use it with every model on the platform.

Send your first request

Copy the example for your language and run it against the endpoint.

Text to textMessages API

POST/v1/messages

API format:

curl https://api.tokenlab.sh/v1/messages \
  -H "Content-Type: application/json" \
  -H "x-api-key: sk-xxx" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "glm-5-turbo",
    "max_tokens": 1024,
    "messages": [
      {"role": "user", "content": "Hello!"}
    ]
  }'

Pricing

The Verified price applies to Verified, which costs less on most models. The Official price is the model maker's published price and applies to the more reliable Official route. Auto bills the route that completes the request.

Default spec

per 1M tokens

Official price: Input $1.20 / Output $4.00 / Cache read $0.24 / Cache write $0.00
Verified price: —
Discount: —

Prompt cache pricing

Cache read

Official price: $0.24
Verified price: —
Discount: —

Cache write

Official price: $0.00
Verified price: —
Discount: —

	Official priceper 1M tokens	Verified priceper 1M tokens	Discount
Default spec	Input $1.20 / Output $4.00 / Cache read $0.24 / Cache write $0.00	—	—
Prompt cache pricing
Cache read	$0.24	—	—
Cache write	$0.00	—	—

Usage & activity

Success rate is the share of requests that completed. Latency is how long a full response takes; P95 means 95% of requests finished within that time.

Usage & availability

Last 24 hours

Requests
Success rate
P95 latency
Total tokens

Model performance

Last updated Nov 1, 2026, 8:13 AM UTC

Metrics appear once privacy and data volume thresholds are met.

Data is based on aggregate user requests, excluding status checks.

Open in Console

Open GLM-5-Turbo in Console with a prompt ready to edit or send.

Help me try glm-5-turbo with a short message at /v1/messages. Show the reply, latency, and cost.

Use cases

OpenClaw-style assistants
Power personal or team agents that schedule tasks, call tools, and report back over several hours.
Automation with many tool calls
Chain dozens of API calls for reporting or data cleanup, where one failed call can break the run.
Scheduled research jobs
Run recurring searches and summaries that must remember earlier results and act at the right time.

Prompt examples

Every morning, pull open tickets with the helpdesk tool, rank them by age, and post a summary to the team channel.

Break this task into steps, call the right tools for each, and stop to tell me if a tool returns an error.

Watch the build status tool until the pipeline finishes, then open a ticket if any test failed.

This model has conditional pricing. Monthly token totals alone cannot produce a reliable estimate; use the detailed pricing for the request specification, cache, and applicable time window.

FAQ

What is GLM-5-Turbo for?

It is for agent workloads, especially OpenClaw scenarios. Z.ai tuned it for reliable tool calls, step-by-step instruction handling, and long-running or time-dependent tasks, so it fits assistants that act rather than just answer.

Is GLM-5-Turbo better than GLM-5?

For agent execution, Z.ai reports substantial improvements in OpenClaw scenarios. For other work, such as code review or analysis, GLM-5 remains the general base model and may be preferable.

Does GLM-5-Turbo support function calling?

Yes. GLM-5-Turbo supports function calling and MCP tool integration, which agents rely on, along with structured JSON output, context caching, streaming output, and a thinking mode you can enable for harder steps.

Can it process images?

No, GLM-5-Turbo works with text input and text output only. Use a vision-capable GLM such as GLM-5V-Turbo when screenshots, mock-ups, or other images are part of the task.

How much does GLM-5-Turbo cost?

On TokenLab, GLM-5-Turbo costs Input $1.20 / Output $4.00 per 1M tokens. The pricing table above shows the full breakdown. Rates depend on the billing unit, specification, and usage. Compare matching conditions in the model's detailed pricing; a single rate does not determine the total cost.

What are the context window and output limit of GLM-5-Turbo?

GLM-5-Turbo accepts up to 200,000 tokens of context and returns up to 128,000 tokens in one response.

Which endpoint should GLM-5-Turbo use?

Use https://api.tokenlab.sh/v1/messages for GLM-5-Turbo. The request example below shows the matching code shape.

Which operations does GLM-5-Turbo support?

GLM-5-Turbo supports Text to text. Select an operation above to see its endpoint and request example.