Zhipu AI: GLM-5

General GLM flagship for coding, analysis, and tool-heavy engineering workflows

glm-5

AvailableZhipu AIChat

Input / Output: $1.00 / $3.20
Context: 200K
Max output: 128K
Modalities: Chat
Capabilities: Tool usePrompt Cache

About GLM-5

GLM-5 is Z.ai's foundation model for agentic engineering and complex system tasks, with 744B total parameters and 40B active, trained on 28.5T tokens. It is a text-only model. Within the GLM line it is the base generation that GLM-5-Turbo and GLM-5.1 build on, and Z.ai reports software-engineering results aligned with Claude Opus 4.5.

Where it works well

Z.ai reports 77.8 on SWE-bench Verified and 56.2 on Terminal Bench 2.0, which it describes as aligned with Claude Opus 4.5 in software engineering.
Z.ai ranks it first among open-weight models on BrowseComp, MCP-Atlas, and tau2-Bench agent evaluations.
Function calling, context caching, streaming, and a thinking mode are all supported.
The parameter count grew from 355B in GLM-4.5 to 744B, with active parameters rising from 32B to 40B.

When to choose another model

It is a text-only model with text input and output.
GLM-5.1 and later GLM releases report higher coding results, so GLM-5 suits stable existing integrations more than new builds.

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",
    "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

per 1M tokens

Official price: Input $1.00 / Output $3.20 / Cache read $0.20 / Cache write $1.00 / Text Input $1.00 / Text Output $3.20
Verified price: —
Discount: —

Prompt cache pricing

Cache read

Official price: $0.20
Verified price: —
Discount: —

Cache write

Official price: $1.00
Verified price: —
Discount: —

	Official priceper 1M tokens	Verified priceper 1M tokens	Discount
Default	Input $1.00 / Output $3.20 / Cache read $0.20 / Cache write $1.00 / Text Input $1.00 / Text Output $3.20	—	—
Prompt cache pricing
Cache read	$0.20	—	—
Cache write	$1.00	—	—

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, 8:12 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 in Console with a prompt ready to edit or send.

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

Use cases

Backend code generation
Generate and review services, migrations, and tests where the surrounding architecture is described in text.
Tool-using agents
Run agents that call search, database, and ticketing tools through function calling and return results in a fixed format.
Technical analysis
Read logs, specs, and design documents and produce findings in a consistent list format for downstream systems.

Prompt examples

Review this pull request diff for race conditions and list each finding with file, line, and a suggested fix.

Use the query_db tool to find users with duplicate emails, then draft a safe merge plan as numbered steps.

Write a Python script that watches a directory, uploads new CSVs, and retries failed uploads with backoff.

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 exactly is GLM-5?

GLM-5 is Z.ai's fifth-generation GLM foundation model, aimed at agentic engineering. It has 744B total parameters with 40B active, is a text-only model, and supports thinking mode and function calling.

How does GLM-5 differ from GLM-5-Turbo?

GLM-5-Turbo is tuned from training time for OpenClaw-style agent workflows, with more reliable tool calls and faster long chains. GLM-5 is the general base model for coding, analysis, and engineering tasks.

What input does GLM-5 take?

Text only. GLM-5 reads prompts, code, logs, and documents as plain text and replies with text, so the whole task needs to be expressible in text.

Should I move from GLM-5 to GLM-5.1?

GLM-5.1 is aimed at long-horizon autonomous work and reports 58.4 on SWE-Bench Pro. Move if you run long agent sessions; keep GLM-5 where a tested prompt set already works.

How much does GLM-5 cost?

On TokenLab, GLM-5 costs Input $1.00 / Output $3.20 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?

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

Which endpoint should GLM-5 use?

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

Which operations does GLM-5 support?

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