Using GLM-5V-Turbo on Vercel AI Gateway

Implementation guide · GLM-5 · Zhipu AI

ServerlessOpen Source

Vercel AI Gateway exposes GLM-5V-Turbo through model ID zai/glm-5v-turbo. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-06-29. Next refresh: weekly.

Quick Start

1
Create an account at Vercel AI Gateway and generate an API key.
2
Use the Vercel AI Gateway SDK or REST API to call zai/glm-5v-turbo — see the documentation for request format.
3
You'll be billed $1.20/1M input, $4.00/1M output tokens. See full pricing.

API Portal Documentation Pricing Model Card

Code Examples

Install

pip install openai

API key

AI_GATEWAY_API_KEY

Model ID

zai/glm-5v-turbo

creator/model-name e.g. kwaipilot/kat-coder-pro-v2

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["AI_GATEWAY_API_KEY"],
    base_url="https://ai-gateway.vercel.sh/v1"
)
response = client.chat.completions.create(
    model="zai/glm-5v-turbo",
    messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)

Pricing on Vercel AI Gateway

Type	Price (per 1M)
Input tokens	$1.20
Output tokens	$4.00

Capabilities

VisionMultimodalReasoningJSON / Tool useStructured Outputs

About GLM-5V-Turbo

First native multimodal variant of GLM-5 with CogViT visual encoder. Specialized for design-to-code tasks—converts mockups, screenshots, Figma exports, and hand-drawn sketches into HTML, CSS, and JavaScript. Trained with reinforcement learning across 30+ task types with INT8 quantization. Achieved 94.8 on Design2Code benchmark (vs Claude Opus 4.6: 77.3). Supports image, video, and text inputs natively.

Full model details →

Model Specs

Released2026-04-01

Parameters744B total, 40B active

Context200k

ArchitectureMixture of Experts

Knowledge cutoff2025-11

Vercel