GLM-5.3-Flash
GLM-5.3-Flash is a text and image and video-input model by Z.ai, available through the AgentSky API as zai/glm-5.3-flash at $0.105 per million input tokens and $0.35 per million output tokens, with a 1M context window.
A natively multimodal Flash model for efficient coding and long-horizon agent tasks, taking text, images, and video.
Run GLM-5.3-Flash with an agent
Each guide pairs this model with a compatible agent and opens the composer with both selected.
- Hermes + GLM-5.3-Flash
- Claude Code + GLM-5.3-Flash
- Codex + GLM-5.3-Flash
- OpenClaw + GLM-5.3-Flash
- pi + GLM-5.3-Flash
- DeepSeek Harness + GLM-5.3-Flash
- Kimi Code + GLM-5.3-Flash
- OpenCode + GLM-5.3-Flash
- Cline + GLM-5.3-Flash
- DeepAgents + GLM-5.3-Flash
- goose + GLM-5.3-Flash
- Grok Build + GLM-5.3-Flash
- Kilo + GLM-5.3-Flash
- MiniMax Code + GLM-5.3-Flash
- Mistral Vibe + GLM-5.3-Flash
- Qwen Code + GLM-5.3-Flash
- OpenHands + GLM-5.3-Flash
Pricing
USD per million tokens, using your plan when signed in.
| Meter | Per 1M tokens |
|---|---|
| Input | |
| Output | |
| Cache read | |
| Cache write |
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-flash",
messages: [{ role: "user", content: "Summarise this ticket." }],
});
console.log(completion.usage.cost); // USD, in the response