Baidu Qianfan — China🇨🇳
Zero data retention posture is not established for this route. Training posture pending review. GLOBAL; unknown.
- Zero data retention
- Not established.
- GDPR DPA
- No DPA
- Transfer mechanism
- unknown
Released 63 days after GLM-5.2 · All Z.ai releases
GLM-5.3 is Z.ai's flagship coding and agentic model, announced on August 14, 2026. It keeps the same mixture-of-experts base as GLM-5.2, the 744 billion parameter design with about 40 billion active per token, and every gain over its predecessor comes from a scaled-up post-training run rather than a new base. The model is text-only, supports a 1M-token context window with up to 128,000 tokens of output, and exposes a reasoning_effort parameter with low, high, and max levels that sets the thinking budget. Z.ai reports a 50% gain over GLM-5.2 on its in-house Code Bench, 28.3 on Terminal-Bench 3.0 against 4.6 for GLM-5.2, 66.9 on DeepSWE v1.1, and 88.2 on Terminal-Bench 2.1, and bills it as the most capable open-weights model for coding. The other headline is cybersecurity: vulnerability discovery was added to post-training and the capability grew faster than Z.ai expected, with a CyberGym score of 84.5, and the company says its models have turned up 2,436 vulnerabilities across 269 open-source projects since GLM-5.2. The weights were held back for a roughly two-week safety review before publication on Hugging Face, and unlike GLM-5.2 they ship under Z.ai's own GLM-5.3 license rather than MIT. It suits coding agents, long-horizon terminal work, and code review or vulnerability triage where the effort ladder lets you match reasoning depth to the task.
Call GLM-5.3 on Opper with the OpenAI SDK. Sign up without a credit card. Get started
GLM-5.3 runs on 18 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. In the EU it is served by GreenPT, Inceptron (Sweden), Melious (Germany) and 3 more. See every GLM model hosted in the EU.
| Provider | Region | Zero data retention | Training | Input | Output | Cache read |
|---|---|---|---|---|---|---|
| Multi | —Not established | — | $1.40 | $4.40 | $0.26 | |
| US | No | $1.20 | $4.00 | $0.12 | ||
| US | No | $1.40 | $4.40 | $0.26 | ||
| Multi | No | $1.40 | $4.40 | $0.26 | ||
| EU | No | $1.25 | $5.00 | $0.31 | ||
| EU | No | $0.79 | $2.65 | $0.20 | ||
| EU | No | $1.14 | $3.41 | $0.23 | ||
| EU | No | $1.40 | $4.40 | $0.14 | ||
| Multi | No (opt-in) | $1.40 | $4.40 | $0.26 | ||
| US | No | $1.00 | $3.41 | $0.20 | ||
| Multi | No | $1.40 | $4.40 | Input price | ||
| US | No | $1.40 | $4.40 | $0.26 | ||
| US | No | $1.40 | $4.40 | $0.26 | ||
| EU | No | $1.20 | $4.20 | $0.26 | ||
| Multi | No | $1.40 | $4.40 | $0.26 | ||
| EU | No | $1.75 | $4.50 | $0.44 | ||
| US | No | $1.19 | $4.40 | $0.26 | ||
| Multi | No | $1.40 | $4.40 | $0.26 |
GLM-5.3 runs on 6 independently monitored routes through the Opper gateway. A direct integration leaves you on one of them, the gateway serves whichever is healthy.
Measured over the last 30 days from each provider's official status feed via StatusGator. Refreshed hourly. 12 further routes for this model are not on the board yet and are not counted above. See uptime for every provider Opper monitors.
Each route hosting GLM-5.3 has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.
Zero data retention posture is not established for this route. Training posture pending review. GLOBAL; unknown.
Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. US; unknown; DPA available.
Zero data retention with abuse monitoring: nothing is logged or used for training; content flagged by abuse monitoring is held for review. No training on customer data. US; dpf sccs; DPA available.
Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. GLOBAL; SCCs; DPA available.
Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. EU; DPA available.
Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. EU; DPA available.
Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. EU; DPA available.
Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. EU; DPA available.
Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training by default; opt-in possible. GLOBAL; SCCs; DPA available.
Zero data retention with abuse monitoring: prompts and outputs are kept for up to 30 days for abuse monitoring only, and are not used for training. No training on customer data. US; SCCs; DPA available.
Content is retained: provider logging. No training on customer data. GLOBAL; SCCs; DPA available.
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: nothing is logged, held for abuse monitoring or used for training. No training on customer data. US; SCCs; DPA available.
Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. EEA; SCCs; DPA available.
Content is retained: limited debug logs, 30-day retention. No training on customer data. GLOBAL; SCCs; DPA available.
Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. EU; DPA available.
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 with abuse monitoring: nothing is logged or used for training; content flagged by abuse monitoring is held for review. No training on customer data. GLOBAL; unknown; DPA available.
Independent benchmark scores — composite indices for reasoning, coding, and math, plus individual eval scores where available.
Call GLM-5.3 through the Opper gateway with one API key. Opper is drop-in compatible with the OpenAI, Anthropic and Google AI SDKs.
GLM-5.3 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.
Copy this and paste it into a coding agent like Claude Code, Cursor or Codex and it'll wire up Opper for you.
import OpenAI from "openai";const client = new OpenAI({apiKey: process.env.OPPER_API_KEY,baseURL: "https://api.opper.ai/v3/compat",});const completion = await client.chat.completions.create({model: "glm-5.3",messages: [{ role: "user", content: "Hello" }],});console.log(completion.choices[0].message.content);
Pick your tool to see how to run it on GLM-5.3 through Opper.
Side-by-side on privacy, EU hosting, pricing, and benchmarks.