API · Models
Text
Hy3
Built for real-world business scenarios, Hy3 features a 295B/21B active MoE architecture, native 256K context support, and three reasoning modes. It enhances coding, long-form comprehension, multi-turn dialogue, and agentic task execution, balancing reliability, efficiency, and cost across both high-frequency interactions and complex workflows.
ReasoningToolsCache
Context 262.1K·Max out 262.1K
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/tencent/hy3'),
prompt: 'Why is the sky blue?',
});
for await (const chunk of result.textStream) {
process.stdout.write(chunk);
}Specs & pricing
- Input $/M
- 0.14
- Output $/M
- 0.58
- Context window
- 262.1K
- Max output
- 262.1K
- Supported parameters
- —
Related models
| Model | Type | Context | Input $/M |
|---|---|---|---|
| NVIDIA: Nemotron 3 Ultra | Text | 1M | 0.6 |
| Kimi K2.7 Code | Text | 262.1K | 0.95 |
| GLM 5.2 | Text | 1.0M | 1.40 |
| Gemma 4 31B | Text | 262.1K | 0.14 |
| GPT-OSS 120B | Text | 131K | 0.1 |