API · Models
Text
Qwen3 VL 32B
Qwen3-VL-32B-Instruct is a large-scale multimodal vision-language model for high-precision image understanding and document analysis.
Context 262.1K·Max out 8.2K
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/qwen3-vl-32b'),
prompt: 'Why is the sky blue?',
});
for await (const chunk of result.textStream) {
process.stdout.write(chunk);
}Specs & pricing
- Input $/M
- $0.50
- Output $/M
- $1.50
- Context window
- 262.1K
- Max output
- 8.2K
- Supported parameters
- vision
Related models
| Model | Type | Context | Input $/M |
|---|---|---|---|
| Qwen3 Max | Text | 256K | $1.20 |
| Qwen3 Coder | Text | 128K | $1 |
| Qwen3 VL 235B | Text | 262.1K | $0.20 |
| Blackbox Pro | Text | 400K | $1.75 |
| GPT-5.3 Codex | Text | 400K | $1.75 |