New version available

Refresh to update

Could not apply changes

GLM 5.3 Flash

zai
z-ai/glm-5.3-flash

Fast and cost-efficient multimodal GLM-5 model for coding, agentic workflows, vision, and general-purpose tasks. Supports reasoning and function calling with a large context window; hosted on Cloudflare Workers AI.

Quick start

TypeScript
cURL
import OpenAI from 'openai'

const openai = new OpenAI({
  apiKey: process.env.CODEPLATFORM_API_KEY,
  baseURL: 'https://ai.codeplatform.net/v1',
})

const response = await openai.chat.completions.create({
  model: 'z-ai/glm-5.3-flash',
  messages: [{
    role: 'user',
    content: 'Hello world',
  }],
})

API details

Send requests to the OpenAI-compatible /v1/chat/completions endpoint.

Capabilities

Pricing

Input tokens (per 1M)$0.15
Output tokens (per 1M)$0.50
Cached input (per 1M)$0.03

Limits

Context length1,048,576 tokens
Max output128,000 tokens