GLM-5.3 — AgentSky

GLM-5.3

zai/glm-5.3

The current GLM flagship for software engineering and agent workloads, with configurable reasoning effort.

Overview

The current GLM flagship for software engineering and agent workloads, with configurable reasoning effort. It is billed from the same balance as every other model and tool here, and the price of each call comes back in the response.

Run GLM-5.3 with an agent

Each guide pairs this model with a currently compatible agent, explains their separate roles, and opens the shared Composer with both selections ready.

Pricing

Prices in USD per million tokens, using your plan when signed in.

Meter Per 1M tokens
Input Price: $1.40
Output Price: $4.40
Cache read Price: $0.26
Cache write Price: $1.40

Your balance and per-call records come from /v1/credits and/v1/generation.

Use it

Point your client at the gateway and pass this model id. Nothing else changes.

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://gateway.agentsky.dev/v1",
  apiKey: process.env.AGENTSKY_API_KEY, // ast_…
});

const completion = await client.chat.completions.create({
  model: "zai/glm-5.3",
  messages: [{ role: "user", content: "Summarise this ticket." }],
});
console.log(completion.usage.cost); // USD, in the response

Questions

What is GLM-5.3?

How much does GLM-5.3 cost?

What is the context length of GLM-5.3?

Which clients can call GLM-5.3?

How do I name GLM-5.3 in a request?

Can GLM-5.3 read images?

What output can GLM-5.3 produce?

How should I plan a long prompt for GLM-5.3?

What would 10,000 input tokens and 2,000 output tokens cost with GLM-5.3?

How is cached input priced for GLM-5.3?

Does the GLM-5.3 token price cover an entire agent task?

How do I use GLM-5.3 on AgentSky?