Released 69 days after GLM 4.6 Β· All Z.ai releases
GLM 4.6V is Zhipu's next-generation vision-language model on a 106-billion-parameter MoE architecture (9-billion-parameter Flash variant also available) tuned for multimodal reasoning at scale. With a 128K context window, it adds native multimodal function calling, letting images, screenshots, and document pages pass directly as tool parameters without intermediate text conversion, which simplifies agentic integration. The model targets visual document understanding, chart parsing, GUI automation, and spatial reasoning, with improved grounding and long-document comprehension over GLM-4.5V. Its 128K context can hold roughly 150 pages of dense documents, around 200 slides, or about an hour of video in a single pass, and it handles images, video, and mixed-media documents together. Released December 2025 under an MIT license, GLM 4.6V suits developers building document intelligence platforms, web automation, accessibility tools, and vision-driven agents that need both extended context and tool-driven reasoning. The 9B GLM-4.6V-Flash variant offers a lighter option for cost-sensitive deployment.
GLM 4.6V runs on 1 route through the qynio gateway. Compare residency, zero retention, and training posture at a glance β full data-handling detail per route below.
| Provider | Region | Zero data retention | Training | Input | Output |
|---|---|---|---|---|---|
| US | Zero data retention | No | $0.30 | $0.90 |
GLM 4.6V runs on a single route through the qynio gateway today, so its availability is that provider's availability.
Name a second model in the same request and the gateway tries it on retriable errors, so a busy hour never has to reach your users. .
Measured over the last 30 days from each provider's official status feed via StatusGator. Refreshed hourly. See uptime for every provider qynio monitors.
Each route hosting GLM 4.6V has its own privacy posture, residency, and no-KYC terms. Postures are maintained by qynio 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. US; wallets; deposit available.
Independent benchmark scores β composite indices for reasoning, coding, and math, plus individual eval scores where available.
Call GLM 4.6V through the qynio gateway with one API key. Let your coding agent set it up, or call it directly β qynio is drop-in compatible with the OpenAI, Anthropic, and Google AI SDKs.
Copy this and paste it into a coding agent like Claude Code, Cursor or Codex and it'll wire up qynio for you.
import OpenAI from "openai";const client = new OpenAI({apiKey: process.env.QYN_API_KEY,baseURL: "https://api.qyn.io/v3/compat",});const completion = await client.chat.completions.create({model: "novita/zai-org/glm-4.6v",messages: [{ role: "user", content: "Hello" }],});console.log(completion.choices[0].message.content);
Side-by-side on privacy, crypto rails, pricing, and benchmarks.
