GLM-4.6V-Flash

For local deployment and low-latency applications. GLM-4.6V series are Z.ai’s iterations in a multimodal large language model. GLM-4.6V scales its context window to 128k tokens in training, and achieves SoTA performance in visual understanding among models of similar parameter scales.

VisionReasoningFilesToolsCache

Context 128K·Max out 24K

Quickstart

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

const blackbox = createOpenAICompatible({
  name: 'blackbox',
  apiKey: process.env.BLACKBOX_API_KEY!,
  baseURL: 'https://api.blackbox.ai/v1',
});

const result = streamText({
  model: blackbox('blackboxai/zai/glm-4.6v-flash'),
  prompt: 'Why is the sky blue?',
});

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

Specs & pricing

Input $/M: —
Output $/M: —
Context window: 128K
Max output: 24K
Supported parameters: —

Related models

Model	Type	Context	Input $/M
GLM 4.5	Text	128K	0.6
GLM 4.5 Air	Text	128K	0.2
GLM 4.5V	Text	66K	0.6
GLM 4.6	Text	200K	0.6
GLM-4.6V	Text	128K	0.3