[Z.AI](/ai-gateway/models/labs/zai) # GLM 5V Turbo GLM 5V Turbo is Z.AI's vision-enabled turbo model released April 1, 2026. It turns screenshots and designs into code, debugs visually, and operates GUIs autonomously, combining GLM-5's agentic capabilities with multimodal vision input at a compact parameter size. Your use is subject to Z.AI's [Terms](https://docs.z.ai/legal-agreement/terms-of-use) & [Privacy](https://docs.z.ai/legal-agreement/privacy-policy) Policies. ReasoningTool UseImplicit CachingVision (Image)File Input [Use with AI Gateway](https://vercel.com/d?to=%2F%5Bteam%5D%2F%7E%2Fai%3Futm_source%3Dgateway-model-page%26utm_campaign%3Dai-gateway-models&title=Get+Started+with+Vercel+AI+Gateway) [View docs](https://vercel.com/docs/ai-gateway) AI SDKChat CompletionsMessagesResponses ``` 1import { streamText } from 'ai' 2 3const result = streamText({ 4 model: 'zai/glm-5v-turbo', 5 prompt: 'Why is the sky blue?' 6}) ``` [Read docs](https://vercel.com/docs/ai-gateway/sdks-and-apis/ai-sdk) [Overview](/ai-gateway/models/glm-5v-turbo) [API](/ai-gateway/models/glm-5v-turbo/api) [About](/ai-gateway/models/glm-5v-turbo/about) [Providers](/ai-gateway/models/glm-5v-turbo/providers) [Throughput](/ai-gateway/models/glm-5v-turbo/throughput) [Latency](/ai-gateway/models/glm-5v-turbo/latency) [Uptime](/ai-gateway/models/glm-5v-turbo/uptime) [Status](/ai-gateway/models/glm-5v-turbo/status) [Similar](/ai-gateway/models/glm-5v-turbo/similar) [FAQ](/ai-gateway/models/glm-5v-turbo/faq) ## [Copy link to heading](#playground)Playground Try out GLM 5V Turbo by Z.AI. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days. ![zai logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fzai-256.png%3Fv%3D1786428782581&w=48&q=75)GLM 5V Turbo ![zai logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fzai-256.png%3Fv%3D1786428782581&w=96&q=75) GLM 5V Turbo ## [Copy link to heading](#providers)Providers Route requests across multiple providers. Copy a provider slug to set your preference. Visit the [docs](/docs/ai-gateway/provider-options) for more info. Using a provider means you agree to their terms, listed under Legal. | Provider | | --- | | Context | Max Output | Latency | Throughput | Input | Output | Cache | Web Search | Capabilities | ZDR | No Training | Release Date | | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | ![zai logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fzai-256.png%3Fv%3D1786428782581&w=48&q=75) [Z.AI](/ai-gateway/models/providers/zai) Legal:[Terms](https://docs.z.ai/legal-agreement/terms-of-use)•[Privacy](https://docs.z.ai/legal-agreement/privacy-policy) | 200K | 128K | 1.6s | 75tps | $1.20/M | $4/M | Read:$0.24/M Write:— | — | +2 | | | 04/01/2026 | | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | ## [Copy link to heading](#throughput)Throughput24 hours 1W 1D P50 throughput on live AI Gateway traffic, in tokens per second (TPS). Visit the [docs](https://vercel.com/docs/ai-gateway/models-and-providers/metrics) for more info. ## [Copy link to heading](#latency)Latency24 hours 1W 1D P50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds. View the [docs](https://vercel.com/docs/ai-gateway/models-and-providers/metrics) for more info. ## [Copy link to heading](#uptime)Uptime24 hours 1W 1D 1H Direct request success rate on AI Gateway and per-provider. Visit the [docs](https://vercel.com/docs/ai-gateway/models-and-providers/uptime) for more info. 1W 1D 1H ## [Copy link to heading](#more-models-by-zai)More models by Z.AI All Text Code | Model | | --- | | Context | Latency | Throughput | Input | Output | Cache | Web Search | Capabilities | Providers | ZDR | No Training | Release Date | | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | ![zai logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fzai-256.png%3Fv%3D1786428782581&w=48&q=75) [zai/glm-5.3](/ai-gateway/models/glm-5.3) | 1M | 3.0s | 64tps | $1.40/M | $4.40/M | Read:$0.26/M Write:— | — | | ![zai logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fzai-256.png%3Fv%3D1786428782581&w=48&q=75) | | | 08/18/2026 | | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | ![zai logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fzai-256.png%3Fv%3D1786428782581&w=48&q=75) [zai/glm-5.2-fast](/ai-gateway/models/glm-5.2-fast) | 1M | 0.6s | 175tps | $2.10/M | $6.60/M | Read:$0.21/M Write:— | — | | ![alibaba logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Falibaba%2520cloud.png&w=48&q=75) ![baseten logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fbaseten.png&w=48&q=75) ![fireworks logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Ffireworks.png&w=48&q=75) +1 | | | 06/23/2026 | | | ![zai logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fzai-256.png%3Fv%3D1786428782581&w=48&q=75) [zai/glm-5.2](/ai-gateway/models/glm-5.2) | 1M | 0.3s | 333tps | $1.40/M$0.80/M Fast $2.10/M | $4.40/M$2.52/M Fast $6.60/M | Read:$0.26/M$0.14/M Write:— | — | | ![alibaba logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Falibaba%2520cloud.png&w=48&q=75) ![baseten logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fbaseten.png&w=48&q=75) ![crusoe logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fcrusoe.png&w=48&q=75) +13 | | | 06/16/2026 | | | ![zai logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fzai-256.png%3Fv%3D1786428782581&w=48&q=75) [zai/glm-5.1](/ai-gateway/models/glm-5.1) | 205K | 1.0s | 84tps | $1.40/M | $4.40/M | Read:$0.26/M Write:— | — | | ![deepinfra logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fdeepinfra.png&w=48&q=75) ![novita logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fnovita.png&w=48&q=75) ![zai logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fzai-256.png%3Fv%3D1786428782581&w=48&q=75) | | | 04/07/2026 | | | ![zai logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fzai-256.png%3Fv%3D1786428782581&w=48&q=75) [zai/glm-5](/ai-gateway/models/glm-5) | 203K | 0.3s | 132tps | $0.80/M | $2.56/M | Read:$0.16/M Write:— | — | | ![bedrock logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Famazon%2520bedrock.png&w=48&q=75) ![deepinfra logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fdeepinfra.png&w=48&q=75) ![novita logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fnovita.png&w=48&q=75) +2 | | | 02/12/2026 | | | ![zai logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fzai-256.png%3Fv%3D1786428782581&w=48&q=75) [zai/glm-4.7-flash](/ai-gateway/models/glm-4.7-flash) | 200K | 0.1s | 140tps | $0.07/M | $0.40/M | Read:$0.01/M Write:— | — | | ![bedrock logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Famazon%2520bedrock.png&w=48&q=75) ![zai logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fzai-256.png%3Fv%3D1786428782581&w=48&q=75) | | | 01/19/2026 | | ## [Copy link to heading](#about-glm-5v-turbo)About GLM 5V Turbo GLM 5V Turbo was released April 1, 2026 as the vision-enabled turbo variant in Z.AI's GLM-5 generation. It combines GLM-5's agentic capabilities with multimodal vision input, purpose-built for workflows where visual understanding drives code generation and UI interaction. The model focuses on design-to-code generation. Given a screenshot or design mockup, GLM 5V Turbo produces responsive components that match the original layout. It can debug visually by examining screenshots of rendered output and identifying discrepancies, then generating fixes. The model also navigates real GUI environments autonomously, reading screen elements and performing actions without manual scripting. Despite these multimodal capabilities, GLM 5V Turbo operates at a smaller parameter size than comparable vision-language models. This translates to faster inference and lower cost per request, making high-volume visual coding workflows economically viable. Through AI Gateway, it's accessible via the same unified API with built-in observability and provider routing. ## [Copy link to heading](#what-to-consider-when-choosing-a-provider)What To Consider When Choosing a Provider - Configuration: GLM 5V Turbo converts visual designs to code. For best results, provide clean screenshots at sufficient resolution and specify the target framework (React, HTML/CSS, etc.) in your prompt. - Configuration: You can use GLM 5V Turbo in an iterative loop: render code, screenshot the result, feed it back to the model for corrections. This workflow leverages both vision and coding capabilities. - Configuration: The compact parameter size means faster inference, but the most complex visual reasoning tasks may benefit from the full GLM-4.6V (106B). Benchmark on your specific use cases. - Zero Data Retention: Zero Data Retention is offered on a per-provider and model basis. See the [documentation](https://vercel.com/docs/ai-gateway/security-and-compliance/zdr) for details. - Authentication: AI Gateway authenticates requests using an [API key](https://vercel.com/docs/ai-gateway/authentication-and-byok#api-key-authentication) or [OIDC token](https://vercel.com/docs/ai-gateway/authentication-and-byok#oidc-token-authentication). You do not need to manage provider credentials directly. ## [Copy link to heading](#when-to-use-glm-5v-turbo)When to Use GLM 5V Turbo ### Best for - Design-to-code generation: Screenshots and mockups convert into responsive React components, HTML, and CSS - Visual debugging: The model examines rendered output, identifies layout issues, and generates fixes - GUI automation: Real screen environments navigated autonomously for testing and interaction workflows - Agentic visual coding pipelines: Image understanding combined with autonomous code planning and iteration - High-volume visual processing: The compact parameter size keeps inference fast and cost-effective ### Consider alternatives when - Maximum visual reasoning depth: GLM-4.6V (106B) provides the largest vision-language model in the lineup without speed constraints - Text-only workloads: GLM-5-Turbo offers the same generation's speed without vision overhead - Simple captioning or classification: A lighter vision model may be more cost-effective for basic image tasks - Deepest text reasoning: The full GLM-5 text-only variant provides multiple thinking modes without vision input ## [Copy link to heading](#conclusion)Conclusion GLM 5V Turbo bridges vision and code generation in a fast, compact package. For teams building design-to-code pipelines, visual debugging loops, or autonomous GUI agents, it delivers the GLM-5 generation's agentic capabilities with multimodal input at a practical speed and cost profile.