When was GLM 4.6 released?

Z.ai released GLM 4.6 on 30 Sep 2025. It is available through the Opper gateway.

Does GLM 4.6 support zero data retention?

Yes. GLM 4.6 is available with zero data retention on DeepInfra, Novita through the Opper gateway.

Where is GLM 4.6 hosted?

GLM 4.6 runs on US hosting routes through the Opper gateway.

Is GLM 4.6 trained on prompts and outputs?

No. Every hosting route for GLM 4.6 is configured so customer prompts and outputs are not used to train models by default.

Is a GDPR DPA available for GLM 4.6?

Yes. A GDPR Data Processing Agreement is available on at least one route serving GLM 4.6. Contact hello@opper.ai to receive it.

GLM 4.6

by Z.ai

Released 50 days after GLM 4.5V · Announcement · All Z.ai releases

GLM 4.6 is Zhipu's iterative advance over GLM-4.5, with 357 billion total parameters (32 billion active) in a Mixture-of-Experts configuration tuned for extended reasoning and agent workflows. Its 200K context window, with up to 128K output, supports long documents, multi-turn technical conversations, and complex tool-driven agentic systems. Released September 2025, GLM 4.6 improves coding performance, function calling, and search-based agent integration over GLM-4.5, making it well suited to retrieval-augmented generation, support automation, and information synthesis. It keeps the bilingual training and hybrid reasoning design of the earlier release, balancing depth and speed. Available as open weights under an MIT license, GLM 4.6 targets developers building production agents that need deeper context for sophisticated multi-step reasoning, tool coordination, and long-horizon planning, including code review automation, document-heavy question answering, and multi-document reasoning.

Call GLM 4.6 on Opper with the OpenAI SDK. Sign up without a credit card. Get started

Get your API key Try in chat Compare

Key info

Input

Output

Features

Context window

203K

Max output

203K

Input price

$0.50 /1M$0.10 cache read

Output price

$2.00 /1M

Released

30 Sep 2025

Web search

Via Opper

US residency available
Zero data retention on pay-as-you-go
No training by default
GDPR DPA available

Available routes

GLM 4.6 runs on 2 different routes through the Opper gateway. Compare residency, zero data retention and training posture at a glance, with full data-handling detail per route below. One route also sells flex processing: the same model at another price, picked per request with service_tier. How service tiers work.

Provider	Region	Zero data retention	Training	Input	Output	Cache read
DeepInfra	US		No	$0.50	$2.00	$0.10
Novita	US		No	$0.55	$2.20	$0.11	Not offered on this route

Live routes and prices as JSON: api.opper.ai/v3/models?q=glm-4.6

Uptime and availability

GLM 4.6 runs on 2 independently monitored routes through the Opper gateway. A direct integration leaves you on one of them, the gateway serves whichever is healthy.

100%effective uptime, last 30 days

Averaged across these routes on their own, a single provider reached 99.93% over the same window.

Daily status through the gateway, which serves each request from whichever route is healthy.

2 monitored providers serve GLM 4.6.

Measured over the last 30 days from each provider's official status feed via StatusGator. Refreshed hourly. See uptime for every provider Opper monitors.

Data handling per route

Each route hosting GLM 4.6 has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

DeepInfra — United States🇺🇸

Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. US; SCCs; DPA available.

Zero data retention: Yes. Nothing is logged, held for abuse monitoring or used for training.
Training: No training on customer data.
Logging: None
Abuse monitoring: No classifier
GDPR DPA: DPA available
Transfer mechanism: SCCs

Novita — United States🇺🇸

Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. US; SCCs; DPA available.

Zero data retention: Yes. Nothing is logged, held for abuse monitoring or used for training.
Training: No training on customer data.
Logging: None
Abuse monitoring: On by default, keeps nothing
GDPR DPA: DPA available
Transfer mechanism: SCCs

Best for

Where GLM 4.6 ranks among the models on Opper with a score for each use case.

Multilingual#18 of 3585.6

Tasks across languagesSee the Multilingual ranking →

Benchmarks

Independent benchmark scores: the Intelligence Index and the individual evaluations behind it, grouped by skill.

Global rank#162 of 505 LLMs

TierEfficient

Output speed36 tok/s

Intelligence Index (previous version)18.5

Coding

LiveCodeBench

70%

Agentic & knowledge work

GDPval

13%

Terminal-Bench Hard

29%

τ²-Bench Telecom

77%

Science & reasoning

Humanity's Last Exam

14%

GPQA Diamond

78%

Long-context reasoning

54%

Knowledge

MMLU-Pro

83%

Math & instruction following

AIME 2025

86%

IFBench

43%

See full leaderboard →Benchmarks via Artificial Analysis · View on AA

Get started

Call GLM 4.6 through the Opper gateway with one API key. Opper is drop-in compatible with the OpenAI, Anthropic and Google AI SDKs.

GLM 4.6 is a premium model on Opper. Sign up needs no credit card: you get an API key straight away and the free models work in the playground and the API. Add a card to use premium models, pay-as-you-go with no minimum.

Set it up with your agent

Copy this and paste it into a coding agent like Claude Code, Cursor or Codex and it'll wire up Opper for you.

Or call it directly

1import OpenAI from "openai";
2
3const client = new OpenAI({
4  apiKey: process.env.OPPER_API_KEY,
5  baseURL: "https://api.opper.ai/v3/compat",
6});
7
8const completion = await client.chat.completions.create({
9  model: "glm-4.6",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);