Zhipu GLM · audio

GLM Realtime

glm-realtime

End-to-end voice + video understanding with singing + 2-min memory. Function calls supported.

Try in Chat Docs

Pricing

Input$2.00 / MTok

Output$8.00 / MTok

Context

128k tokens

Provider

Zhipu GLM

Capabilities

Chat completions

Multi-turn dialogue, system prompts.

Streaming

SSE chunks for incremental output.

Tool / function calling

Structured arguments via JSON schemas.

Image input

Pass images alongside the prompt.

Video generation

Text and image to short video, async.

JSON mode

Coming soon.

Make your first call.

Drop your sk-maas-… key in and you're done.

chat.ts

import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://api.miavo.xyz/v1',
  apiKey: process.env.MACAW_API_KEY!,
});

const res = await client.chat.completions.create({
  model: 'glm-realtime',
  messages: [
    { role: 'user', content: 'Write me a haiku about gateways.' },
  ],
});

console.log(res.choices[0].message.content);

More from Zhipu GLM