Z.AI: GLM 5V Turbo
This model is no longer available.Add AI to your application with Puter.js.
Explore Other ModelsModel Card
GLM-5V-Turbo is Z.ai's (Zhipu AI) native multimodal coding model, designed to bridge visual perception and code generation in a single architecture. It processes images, video, and text natively and is optimized for agentic workflows — turning design mockups, screenshots, and UI layouts into runnable code.
The model scores 94.8 on the Design2Code benchmark (vs. Claude Opus 4.6's 77.3) and leads on GUI agent benchmarks like AndroidWorld and WebVoyager. It also outperforms Claude Opus 4.5 on BrowseComp for agentic browsing tasks.
Built on a 744B-parameter MoE architecture (40B active per token) with a ~200K context window. Trained with reinforcement learning across 30+ task types to maintain strong text-only coding alongside its vision strengths.
Best suited for design-to-code generation, GUI automation, and vision-grounded agentic development.
Context Window 203K
tokens
Max Output 131K
tokens
Input Cost $0.79
per million tokens
Output Cost $3.44
per million tokens
Input text, image, video, file
modalities
Tool Use Yes
Release Date Apr 1, 2026
Code Example
Add AI to your app with the Puter.js AI API — no API keys or setup required.
// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';
puter.ai.chat("Explain quantum computing in simple terms").then(response => {
document.body.innerHTML = response.message.content;
});
<html>
<body>
<script src="https://js.puter.com/v2/"></script>
<script>
puter.ai.chat("Explain quantum computing in simple terms").then(response => {
document.body.innerHTML = response.message.content;
});
</script>
</body>
</html>
More AI Models From Z.AI
GLM 5.3
GLM 5.3 is Z.ai's latest open-weight foundation model, a post-training refresh of GLM-5.2 released August 14, 2026. It keeps the same 744B-parameter Mixture-of-Experts architecture (40B active) and 1M-token context window; all reported gains come from expanded reinforcement-learning post-training rather than a new base model. On Z.ai's internal Code Bench, GLM 5.3 scores 50% higher than GLM-5.2. It also improves on Terminal-Bench 3.0 (4.6 to 28.3) and DeepSWE v1.1 (46.2 to 66.9). Cybersecurity ability grew alongside coding: CyberGym rose from 77.2% to 84.5%, and ExploitBench more than doubled, from 24.4% to 54.4%. The model supports three reasoning-effort levels (low, high, max) via the API, and thinking can no longer be disabled. It is best suited to long-horizon coding agents, repository-scale engineering tasks, and vulnerability research.
ChatGLM 5.2 Fast
GLM 5.2 Fast is the high-speed serving tier of Z.ai's GLM-5.2, running the same model weights on inference infrastructure tuned for higher throughput. Output quality matches the standard GLM-5.2 endpoint; serving speed and price are the differences. It keeps the full 1M-token context window and 128K max output, along with tool calling, structured output, streaming, optional thinking mode with adjustable reasoning effort, and implicit prompt caching. Providers report roughly 2x the throughput of their standard GLM-5.2 endpoints, with peaks measured at 446 tokens per second. Because the weights are identical, it inherits GLM-5.2's coding results, including 62.1 on SWE-bench Pro. The tradeoff is a higher per-token price than standard GLM-5.2. A fit for agent loops that chain many model calls, real-time coding assistants, and other latency-sensitive workloads.
ChatGLM 5.2
GLM 5.2 is Z.ai's sixth-generation open-weight foundation model, built around a 1M-token context window that can hold entire mid-sized codebases in a single prompt. It uses a 744B-parameter Mixture-of-Experts architecture with an "IndexShare" attention optimization that cuts per-token FLOPs by 2.9x at 1M context, keeping long-context inference practical. A new MTP speculative decoding layer raises acceptance length by up to 20%, reducing latency. Dual reasoning modes (High/Max) let you trade speed for depth on complex tasks. GLM 5.2 scored 62.1 on SWE-bench Pro, outperforming GPT-5.5 (58.6) and its predecessor GLM-5.1 (58.4). It is the top-ranked open-weight model on long-horizon coding benchmarks. Best suited for repository-scale refactoring, multi-step agentic coding, full-codebase analysis, and any workflow that previously required chunking large inputs.
Frequently Asked Questions
You can access GLM 5V Turbo by Z.AI through Puter.js AI API. Include the library in your web app or Node.js project and start making calls with just a few lines of JavaScript — no backend and no configuration required. You can also use it with Python or cURL via Puter's OpenAI-compatible API.
Yes, it is free if you're using it through Puter.js. With the User-Pays Model, you can add GLM 5V Turbo to your app at no cost — your users pay for their own AI usage directly, making it completely free for you as a developer.
| Price per 1M tokens | |
|---|---|
| Input | $0.79 |
| Output | $3.44 |
GLM 5V Turbo was created by Z.AI and released on Apr 1, 2026.
GLM 5V Turbo supports a context window of 203K tokens. For reference, that is roughly equivalent to 406 pages of text.
GLM 5V Turbo can generate up to 131K tokens in a single response.
GLM 5V Turbo accepts the following input types: text, image, video, file. It produces: text.
Yes, GLM 5V Turbo supports tool use (function calling), allowing it to interact with external tools, APIs, and data sources as part of its response flow.
GLM 5V Turbo scores 35.3 on the Artificial Analysis Intelligence Index, outperforming 80% of tracked models.
Yes — the GLM 5V Turbo API works with any JavaScript framework, Node.js, or plain HTML through Puter.js. Just include the library and start building. See the documentation for more details.
Get started with Puter.js
Add AI to your application without worrying about API keys or setup.
Explore Models View Tutorials