GLM 4.7 is Zhipu's flagship reasoning model released December 2025, with 358 billion total parameters (32 billion active) and a three-mode thinking design. Interleaved thinking generates reasoning before each response and tool call, preserved thinking retains reasoning context across multi-turn conversations to improve cache reuse, and turn-level thinking lets developers toggle reasoning depth per interaction to trade latency against quality. With a 200K context window and up to 131K output, the model reaches frontier-level coding results, reported at 73.8% on SWE-bench Verified for end-to-end software engineering and 66.7% on multilingual coding. Its work on terminal-based task automation, multi-language programming, and mathematical reasoning makes it strong for agentic development and AI-assisted engineering, emphasizing reasoning quality over raw parameter count. Released under an MIT license, GLM 4.7 is built for developers creating coding agents, terminal automation, mathematical problem-solving, and reasoning-intensive multi-step workflows where transparent, controllable thinking is a differentiator.
GLM 4.7 runs on 4 different routes through the Opper gateway. Compare residency, ZDR, and training posture at a glance β full data-handling detail per route below.
Training posture across routes: No training on prompts by default.
Each route hosting GLM 4.7 has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.
Zero data retention is on by default on Pay-as-you-go β no action required. No training on customer data. EU; DPA available.
Zero data retention is available via Opper Enterprise contract. No training on customer data. US; SCCs; DPA available.
Zero data retention is available via Opper Enterprise contract. No training on customer data. US; unknown.
Zero data retention is available via Opper Enterprise contract. No training on customer data. US; SCCs; DPA available.
Independent benchmark scores β composite indices for reasoning, coding, and math, plus individual eval scores where available.
Call GLM 4.7 through the Opper gateway with one API key. Let your coding agent set it up, or call it directly β Opper is drop-in compatible with the OpenAI, Anthropic, and Google AI SDKs.
Copy this and paste it into your coding agent β Claude Code, Cursor, Codex, and more β 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: "berget/glm-4.7",messages: [{ role: "user", content: "Hello" }],});console.log(completion.choices[0].message.content);
Side-by-side on privacy, EU hosting, pricing, and benchmarks.
