Z.ai · Model guide

GLM-4.7

Q: What is GLM-4.7?

GLM-4.7 is available on CrossModel as z-ai/glm-4.7. It has a 200K-token context window and can return up to 128K tokens per request.

Q: How much does GLM-4.7 cost?

Currently $ 0.47 per 1M input tokens and $ 2.16 per 1M output tokens. Cached input is billed at $ 0.10 per 1M.

Q: Does GLM-4.7 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?

For text models, 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-4.7

Z.AI's late-2025 open coding model, focused on completing multi-step software tasks, terminal work, web research and polished front-end generation. It supports 200K context, switchable thinking and retained reasoning across tool-driven conversations.

Modalities

Context

200K

Max output

128K

Price / 1M tokens

$ 0.47in$ 2.16out

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 coding and agent model with more stable multi-step reasoning and execution.source

Best for

Agentic coding · Targets requirement decomposition, terminal execution and complete project delivery.(vendor claim)source
Search and research · Improves retrieval, cross-source synthesis and multi-round research.(vendor claim)source

Neighbouring models

z-ai/glm-5successor —GLM-5 is the next foundation-model generation for longer engineering work.

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	$ 0.47	$ 0.62
Output	$ 2.16	$ 2.47
Cache read	$ 0.10	$ 0.13
Cache write	$ 0.47	$ 0.62

Estimate a request

Input tokens10,000

Output tokens2,000

Cache hit rate0%

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

$ 0.0090

Estimated cost per request

10.0K × $ 0.47
+ 2.0K × $ 2.16

≈ $ 9.02 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.ai 1 huggingface.co 2Capabilitiesdocs.z.ai 1 docs.z.ai 2

Published benchmarks

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

Agentic coding

Terminal-Bench 2.0
pass_rate·Z.AI · 2025-12-22setup not fully disclosed
41%

Agentic search

BrowseComp (with tools)
accuracy·Z.AI · 2025-12-22setup not fully disclosed
Vendor page describes this as a web-task evaluation but does not disclose the full tool configuration.
67%

Coding

LiveCodeBench v6
pass_rate·Z.AI · 2025-12-22setup not fully disclosed
84.9%
SWE-Bench Verified
resolved_rate·Z.AI · 2025-12-22setup not fully disclosed
73.8%

Reasoning

Humanity's Last Exam
accuracy·Z.AI · 2025-12-22setup not fully disclosed
42.8%

Tool use

τ²-Bench
score·Z.AI · 2025-12-22setup not fully disclosed
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-4.7?

GLM-4.7 is available on CrossModel as z-ai/glm-4.7. It has a 200K-token context window and can return up to 128K tokens per request.

How much does GLM-4.7 cost?

Currently $ 0.47 per 1M input tokens and $ 2.16 per 1M output tokens. Cached input is billed at $ 0.10 per 1M.

Does GLM-4.7 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?

For text models, 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?