Opper AI partners with Z.ai to add the first-party route to GLM
By Felix Wunderlich -
Stockholm, Sweden, November 2026. Opper AI and Z.ai are partnering to bring the GLM family to the Opper AI gateway from the lab that builds it. Builders can now reach Z.ai's first-party API through the Opper API, from GLM-5.3 and GLM-5.3-Flash to GLM-5.2, GLM-5.1 and GLM-5.
Why this matters
The lab behind the most widely hosted weights on the gateway. More than twenty providers on Opper serve a GLM model, which is the whole point of publishing weights openly and a fair measure of what Z.ai has given the field. Every one of those routes exists because Z.ai chose to release the family rather than keep it, and the team that trains GLM now serves it on the gateway too.
Release day, and the whole feature surface. New GLM versions land on this route when Z.ai ships them, and they arrive with everything the lab built into them: the full parameter set, the tool-calling behaviour, the reasoning controls. GLM-5.3, GLM-5.3-Flash and GLM-5.2 all carry a million-token context window here, and GLM-5.3-Flash is the cheap end of the family rather than a cut-down one.
Clear data handling. Z.ai does not train on customer data, and a DPA is available. Hosting region, retention and the rest of the detail sit on the Z.ai provider page.
More than a router: the AI control plane. Routing to Z.ai is just the entry point. Every call through Opper runs on its AI control plane: intelligent routing across models and regions, full observability, real-time PII masking and content filtering, and budget caps. Pin Z.ai for a task or set it as a fallback, and because Z.ai is OpenAI-compatible, getting there is a model string, not a migration.
Models live today
The catalog below is fetched live from Opper's model API and filtered to Z.ai-hosted models. Availability, context windows, and pricing stay in sync with what's actually callable through Opper.
| Model | Region | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|
| zai/glm-5 | SG | 203K | $1.00 | $3.20 |
| zai/glm-5.1 | SG | 192K | $1.40 | $4.40 |
| zai/glm-5.2 | SG | 1.0M | $1.40 | $4.40 |
| zai/glm-5.3 | SG | 1.0M | $1.40 | $4.40 |
| zai/glm-5.3-flash | SG | 1.0M | $0.15 | $0.50 |
Get started
Paste this into your coding agent (Claude Code, Cursor, Codex, and more) and it will set up Opper and route to Z.ai for you:
Use curl to download, read and follow: https://skills.opper.ai
Then set up Opper to use Z.ai as the provider, e.g. zai/glm-5.3.
Prefer a direct call? Opper is drop-in compatible with the OpenAI, Anthropic, and Google SDKs, so one API key and the model string are all you need:
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: "zai/glm-5.3",messages: [{ role: "user", content: "Hello" }],});console.log(completion.choices[0].message.content);
Follow the quick start in our docs for evaluations, fallbacks, and structured output.
About Z.ai
Z.ai builds the GLM family of models, publishes the weights openly, and serves GLM through its own OpenAI-compatible API.
About Opper AI
Opper AI is the European AI gateway for agents, based in Stockholm. It gives developers access to 700+ leading AI models through one EU-hosted, GDPR-compliant API, pay-as-you-go, with spend caps, model allowlists, zero data retention and full OpenAI SDK compatibility.