Model · Z.ai

GLM 5.3 Flash

zai/glm-5.3-flash

Try in Agents

Z.ai's native multimodal coding model — 320B/18B active, visual coding and tool use at 1M context

reasoningvisioncaching

Specs

Context

Max output

131K

Provider

Z.ai

Input

$0.150/ 1M tokens

Output

$0.500/ 1M tokens

Cache read

$0.030/ 1M tokens

Try it

Chat with GLM 5.3 FlashTerramind API

⌘+Enter to run

Code

import { streamText } from "ai";
import { createOpenAICompatible } from "@ai-sdk/openai-compatible";

const terramind = createOpenAICompatible({
  name: "terramind",
  baseURL: "https://terramind.com/api/v1",
  apiKey: process.env.TERRAMIND_API_KEY!,
});

const result = streamText({
  model: terramind("glm-5.3-flash"),
  prompt: "Why is the sky blue?",
});

for await (const chunk of result.textStream) {
  process.stdout.write(chunk);
}

Want to run this in your app? Grab an API key · Full chat reference

More by Z.ai

Model	Context	In	Out	Capabilities
zai/glm-5.1	203K	$1.40	$4.40	reasoningcaching
zai/glm-5.2	1M	$0.800	$2.55	reasoningcaching
zai/glm-5.3	1M	$1.40	$4.40	reasoningcaching
zai/glm-5.3-flashx	1M	$0.370	$1.25	reasoningvisioncaching
zai/glm-5.3-fast	1.0M	$2.10	$6.60	reasoningcaching
zai/glm-5.2-fast	1M	$2.80	$8.80	reasoningcaching
zai/glm-5v-turbo	200K	$1.20	$4.00	reasoningvisionvideo
zai/glm-5	197K	$1.00	$3.20