GLM 4.5V
GLM 4.5V is Z.AI's vision-language model built on GLM-4.5-Air. It supports image reasoning, long video understanding, GUI task handling, and visual grounding. Your use is subject to Z.AI's Terms & Privacy Policies.
View API reference- Input and output price
- Prices from: Input $0.60, Output $1.80, Per 1M tokens
- 24h uptime
- Loading AI Gateway uptime
import { streamText } from 'ai'
const result = streamText({ model: 'zai/glm-4.5v', prompt: 'Why is the sky blue?'})Copy link to headingPlayground
Try out GLM 4.5V 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.
GLM 4.5V
GLM 4.5V
Copy link to headingProviders
Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.
Copy link to headingUptime24 hours
Direct request success rate on AI Gateway and per-provider. Visit the docs for more info.
Copy link to headingThroughput24 hours
P50 throughput on live AI Gateway traffic, in tokens per second (TPS). Visit the docs for more info.
Copy link to headingLatency24 hours
P50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds. View the docs for more info.
Getting started
Call GLM 4.5V through AI Gateway with the AI SDK generateText and streamText functions, or through the OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages APIs by changing the base URL. AI Gateway authenticates the request and routes it to an available provider.
Install the AI SDK (pnpm add ai dotenv), create an API key from the API Keys page, and set it as AI_GATEWAY_API_KEY in your environment. Full setup is covered in the text generation quickstart.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'zai/glm-4.5v', prompt: 'Why is the sky blue?', });
console.log(result.text);}
main().catch(console.error);Top-level parameters
The same GLM 4.5V request in each API format AI Gateway supports.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'zai/glm-4.5v', system: 'You are a concise technical assistant.', prompt: 'Summarize the tradeoffs between static generation and SSR.', maxOutputTokens: 1024, });
console.log(result.text);}
main().catch(console.error);Standard parameters like prompt, messages, temperature, and tools work as documented in the AI SDK docs. These are the parameters with model-specific behavior.
| Parameter | Type | Required | Description |
|---|---|---|---|
model | string | Yes | Model ID in the form creator/model, e.g. zai/glm-4.5v. AI Gateway routes the request to an available provider. |
maxOutputTokens | number | No | Hard cap on generated tokens. GLM 4.5V supports up to 16,384 output tokens. Reasoning tokens count toward this limit. |
reasoning | 'provider-default' | 'none' | 'minimal' | 'low' | 'medium' | 'high' | 'xhigh' | No | Provider-agnostic reasoning effort, available in AI SDK 7 or later. Maps to the provider’s native reasoning configuration; reasoning settings under providerOptions take precedence when both are set. See the Reasoning section below. |
providerOptions | Record<string, JSONValue> | No | AI Gateway routing options under gateway, plus any provider-native options under the provider’s own namespace — see the table below. |
Input limits
| Input | Formats | Sources | Max count | Max size | Limits |
|---|---|---|---|---|---|
| Text | — | — | — | — | Prompt and response share the 66K-token context window |
| Image | — | URL, base64, Uint8Array | — | — | Sent as image parts in messages; counts as input tokens |
Provider options
Set AI Gateway routing options under providerOptions.gateway. For provider-specific options, pass them under the provider’s namespace as documented by the AI SDK.
Learn more in the AI SDK provider docs.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'zai/glm-4.5v', prompt: 'Why is the sky blue?', providerOptions: { gateway: { only: ['novita', 'zai'], }, }, });
console.log(result.text);}
main().catch(console.error);These AI Gateway routing options apply to every model. Provider-specific options pass through under the provider’s own namespace (for example providerOptions.anthropic) exactly as documented by the AI SDK.
| Parameter | Type | Required | Description |
|---|---|---|---|
providerOptions.gateway.only | string[] | No | Restrict routing to these provider slugs. Requests fail over only within the listed providers. |
providerOptions.gateway.order | string[] | No | Preferred provider order. Listed providers are tried first; unlisted providers remain available as fallbacks. |
providerOptions.gateway.sort | 'cost' | 'ttft' | 'tps' | No | Rank candidate providers by price, time to first token, or tokens per second instead of the default routing order. |
providerOptions.gateway.zeroDataRetention | boolean | No | Route only to providers with a zero-data-retention policy for this model. |
Routing across providers
AI Gateway serves the same model through multiple providers and fails over automatically. order expresses a preference while keeping every provider eligible; only is a hard allowlist — if none of the listed providers are available the request fails instead of falling back.
Options under a provider's own namespace (for example providerOptions.anthropic) are forwarded to that provider with the request. Providers ignore option namespaces that don't apply to them, so it is safe to set provider options alongside gateway routing options.
Reasoning
AI Gateway bridges reasoning across every API format. The AI SDK exposes a provider-agnostic top-level reasoning level (none, minimal, low, medium, high, or xhigh); the Chat Completions and Responses formats take the same effort under reasoning.effort; and the Anthropic Messages format uses a native thinking token budget. Whichever you send, the gateway maps it to the target model’s native configuration, converting between effort levels and token budgets as needed. Reasoning-related settings under providerOptions take full precedence over the top-level reasoning value and are never merged. Reasoning tokens typically count toward your output-token usage, though how they’re reported and billed varies by provider.
Learn more in the AI Gateway reasoning guide.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'zai/glm-4.5v', prompt: 'Explain the Monty Hall problem step by step.', reasoning: 'high', });
console.log(result.text);}
main().catch(console.error);Image input
Send images alongside text as message parts. Images count as input tokens.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'zai/glm-4.5v', messages: [ { role: 'user', content: [ { type: 'text', text: 'Describe this image.' }, { type: 'image', image: 'https://example.com/photo.jpg' }, ], }, ], });
console.log(result.text);}
main().catch(console.error);Tool calling
Expose tools the model can call. Define each tool’s inputs with a Zod schema.
import { generateText, tool } from 'ai';import { z } from 'zod';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'zai/glm-4.5v', prompt: 'What is the weather in San Francisco?', tools: { getWeather: tool({ description: 'Get the current weather for a location', inputSchema: z.object({ location: z.string() }), execute: async ({ location }) => ({ location, temperatureC: 18 }), }), }, });
console.log(result.text);}
main().catch(console.error);Copy link to headingMore models by Z.AI
| Model |
|---|
| 1M | 3.6 s | 157 tps | $0.37/M | $1.25/M | Read$0.08/M | — | +1 | | 09/18/2026 | |||||
| 1M | 0.4 s | 213 tps | $0.08/M | $0.25/M | Read$0.01/M | — | +1 |    +17 | 08/26/2026 | |||||
| 1M | 0.1 s | 352 tps | $0.70/M+1 more | $2.20/M+1 more | Read$0.12/M | — |   +17 | 08/18/2026 | ||||||
| 1M | 0.3 s | 505 tps | $2.10/M | $6.60/M | Read$0.21/M | — |  | 06/23/2026 | ||||||
| 1M | 0.2 s | 368 tps | $0.49/M+1 more | $1.56/M+1 more | Read$0.09/M | — | +14 | 06/16/2026 | ||||||
| 200K | 0.8 s | 161 tps | $0.06/M | $0.40/M | Read$0.01/M | — | | 01/19/2026 |
Copy link to headingAbout GLM 4.5V
GLM 4.5V extends the GLM-4.5-Air foundation with multimodal vision capabilities. Built by Z.AI, it targets image reasoning, document understanding, and visual grounding tasks at a comparable scale to other models in its class.
The model supports a broad range of visual input types: single images, multi-image analysis, long video understanding with event recognition, complex chart and document parsing, and GUI task handling including screen reading and icon recognition. A distinctive feature is visual grounding, where the model localizes specific elements in images with bounding box coordinates, enabling applications that need to point at or interact with visual content programmatically.
GLM 4.5V includes a thinking mode switch that balances quick responses against deeper reasoning. For straightforward visual questions, disable thinking for fast responses. For complex multi-image analysis or document interpretation, enable thinking to improve accuracy. The model operates within a context window of 66K tokens.
Copy link to headingWhat To Consider When Choosing a Provider
- Configuration: High-resolution images consume more input tokens. Consider resizing images to the minimum resolution your task requires to control costs.
- Configuration: Enable thinking for complex visual reasoning tasks (chart analysis, multi-image comparison). Disable it for simple captioning or classification to reduce latency.
- Configuration: When using visual grounding, the model returns bounding box coordinates normalized by image dimensions. Your application needs to handle this coordinate format for downstream processing.
- Zero Data Retention: Zero Data Retention is offered on a per-provider and model basis. See the documentation for details.
- Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.
Copy link to headingWhen to Use GLM 4.5V
Best for
- Document and chart understanding: Parsing complex layouts with mixed text, tables, and figures requires joint visual-textual reasoning
- GUI automation and testing: Screen reading, icon recognition, and visual element localization in one model
- Multi-image analysis: Multiple images or image sequences processed in a single request
- Long video understanding: Event recognition and temporal reasoning across extended video content
- Visual grounding tasks: Bounding box coordinates for detected elements are returned natively
Consider alternatives when
- Text-only capabilities: GLM-4.5 or GLM-4.5-Air provides the same language foundation without the vision overhead
- Image generation needed: GLM 4.5V is input-multimodal only and produces text output
- Advanced vision features: GLM-4.6V offers an upgraded 128K context window and native multimodal function calling
- Pixel-accurate frontend replication: GLM-4.6V includes targeted improvements for HTML/CSS reconstruction from screenshots
Copy link to headingConclusion
GLM 4.5V brings vision-language capability to the GLM-4.5 generation, with a focus on document understanding, GUI interaction, and visual grounding. The thinking mode switch gives you control over the accuracy-latency tradeoff on a per-request basis.
Copy link to headingFrequently Asked Questions
What visual inputs does GLM 4.5V support?
Single images, multiple images, long videos, screenshots, charts, documents, and GUI interfaces. It processes these alongside text prompts in a single request.
What is visual grounding in GLM 4.5V?
Visual grounding lets the model identify and localize specific elements in images by returning bounding box coordinates. Coordinates are normalized by image dimensions, enabling programmatic interaction with detected visual elements.
Does GLM 4.5V support video input?
Yes. It handles long video understanding with event recognition and temporal reasoning, processing extended video content within the context window.
How does the thinking mode work?
You can toggle thinking on or off per request. Thinking mode enables deeper chain-of-thought reasoning for complex visual tasks. Disabling it provides faster, more direct responses for simpler queries.
How do I authenticate with GLM 4.5V through AI Gateway?
AI Gateway provides a unified API key. No separate Z.AI account is needed. Configure your API key and use the model identifier to route requests. BYOK is also supported for direct provider accounts.
How does GLM 4.5V compare to GLM-4.6V?
GLM 4.5V builds on GLM-4.5-Air and targets vision-language tasks at its scale. GLM-4.6V is the next generation with a 128K context window, native multimodal function calling, and improved frontend replication capabilities.
Can GLM 4.5V generate images?
No. GLM 4.5V accepts visual inputs and produces text output only. For image generation, use a dedicated image generation model.