Z.ai · Model guide

GLM-5 Turbo

Q: What is GLM-5 Turbo?

GLM-5 Turbo is available on CrossModel as z-ai/glm-5-turbo. It has a 200K-token context window and can return up to 128K tokens per request.

Q: How much does GLM-5 Turbo cost?

Currently $ 0.90 per 1M input tokens and $ 3.70 per 1M output tokens. Cached input is billed at $ 0.18 per 1M.

Q: Does GLM-5 Turbo support tool calling and structured output?

Tool calling: Supported · Structured output (JSON): Supported · Image input: Not supported · Streaming: Supported · Thinking mode: Supported

Q: Which endpoint do I call?

OpenAI Chat Completions (/v1/chat/completions), OpenAI Responses (/v1/responses) and Anthropic Messages (/v1/messages) all work — pick whichever your SDK already speaks.

Q: Can I try it without writing code?

Yes. Sign in and open the Playground on this page to chat with the model directly — no API key needed. Usage is billed from your wallet at the normal rate.

Compare

z-ai/glm-5-turbo

A GLM-5 variant trained specifically for OpenClaw-style agent workflows. It focuses on reliable tool invocation, complex instruction decomposition, scheduled and persistent tasks, multi-agent coordination and stable high-throughput long chains.

Modalities

Context

200K

Max output

128K

Price / 1M tokens

$ 0.90in$ 3.70out

StreamingTool callingJSON outputImage inputThinking mode · can be turned off

What this model is good at

What the vendor positions it for, and which of our models to reach for instead.

VendorA foundation model deeply optimized for OpenClaw workflows.source

Best for

Persistent agent workflows · Optimized for scheduled triggers, continuous execution and tool-heavy business workflows.(vendor claim)source

Neighbouring models

z-ai/glm-5.2stronger —Use GLM-5.2 when general coding capability and a 1M context matter more than OpenClaw specialization.

Compare them side by side →

Pricing and billing

Tiered pricing: the rate changes once the input passes the threshold.

Price / 1M tokens by input size	Input < 32.0K	Input ≥ 32.0K
Input	$ 0.90	$ 1.10
Output	$ 3.70	$ 4.30
Cache read	$ 0.18	$ 0.27
Cache write	$ 0.90	$ 1.10

Estimate a request

Input tokens10,000

Output tokens2,000

Cache hit rate0%

At this input size you are on the Input < 32.0K tier.

$ 0.0164

Estimated cost per request

10.0K × $ 0.90
+ 2.0K × $ 3.70

≈ $ 16.40 per 1,000 requests

Capabilities and limits

What CrossModel guarantees across every route this model can take right now.

Context window: 200.0K tokens
Max output: 128.0K tokens
Input / output modalities: Text → Text
Streaming: Supported
Tool calling: Supported
Structured output (JSON): Supported
Image input: Not supported
Thinking mode: Supported· can be turned off
Available endpoints: /v1/chat/completions · /v1/responses · /v1/messages

First-party sources:Specsdocs.z.aiCapabilitiesdocs.z.ai 1 docs.z.ai 2

Published benchmarks

Scores the vendor reported, with the evaluation setup each one came from.

Coding

SciCode
score·Artificial Analysis · 2026-08-13enabledsetup not fully disclosed
Artificial Analysis 独立评测。
43.6%

Long context

AA-LCR
score·Artificial Analysis · 2026-08-13enabledsetup not fully disclosed
Artificial Analysis 独立长上下文推理评测。
66.7%

Reasoning

AA Intelligence Index v4.1.1
score·Artificial Analysis · 2026-08-13enabledsetup not fully disclosed
Artificial Analysis 基于部分已完成分项估算的九项复合指数，不是完整实测值或百分比；GDPval-AA v2、tau3-Banking 与 Terminal-Bench 2.1 尚无结果。
39.1
Humanity's Last Exam
accuracy·Artificial Analysis · 2026-08-13enabledsetup not fully disclosed
Artificial Analysis 独立评测。
27.8%

Scientific reasoning

CritPt
score·Artificial Analysis · 2026-08-13enabledsetup not fully disclosed
Artificial Analysis 独立物理推理评测。
0.3%
GPQA Diamond
accuracy·Artificial Analysis · 2026-08-13enabledsetup not fully disclosed
Artificial Analysis 独立评测。
84.7%

Vendor-reported numbers, not CrossModel measurements. Scores are only comparable when the benchmark version, metric and evaluation setup match, so nothing here is averaged or ranked.

Use it in your tools

Point the base URL at CrossModel and paste this model ID — every tool below has a setup guide.

Claude Code

Anthropic's official command-line coding assistant

Cursor

AI-first code editor

Cline

Open-source AI coding agent for VS Code

Codex

OpenAI's coding agent for ChatGPT desktop and the terminal

OpenCode

Open-source terminal coding assistant

Zed

High-performance, AI-native code editor

Open WebUI

Open-source, self-hosted AI chat interface

Continue

Open-source AI coding assistant for VS Code & JetBrains

See all integration guides →

Frequently asked questions

What is GLM-5 Turbo?

GLM-5 Turbo is available on CrossModel as z-ai/glm-5-turbo. It has a 200K-token context window and can return up to 128K tokens per request.

How much does GLM-5 Turbo cost?

Currently $ 0.90 per 1M input tokens and $ 3.70 per 1M output tokens. Cached input is billed at $ 0.18 per 1M.

Does GLM-5 Turbo support tool calling and structured output?

Tool calling: Supported · Structured output (JSON): Supported · Image input: Not supported · Streaming: Supported · Thinking mode: Supported

Which endpoint do I call?

OpenAI Chat Completions (/v1/chat/completions), OpenAI Responses (/v1/responses) and Anthropic Messages (/v1/messages) all work — pick whichever your SDK already speaks.

Can I try it without writing code?