API · Models
Text
DeepSeek V4 Flash
DeepSeek V4 Flash is DeepSeek's fast and cost-efficient model with a 1M token context window, optimized for high-throughput tasks.
Context 1.0M·Max out 384K
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/deepseek/deepseek-v4-flash'),
prompt: 'Why is the sky blue?',
});
for await (const chunk of result.textStream) {
process.stdout.write(chunk);
}Specs & pricing
- Input $/M
- 0.089
- Output $/M
- 0.18
- Context window
- 1.0M
- Max output
- 384K
- Supported parameters
- tool-usejson-modestreaming
Related models
| Model | Type | Context | Input $/M |
|---|---|---|---|
| DeepSeek V4 Pro | Text | 1M | 0.435 |
| NVIDIA: Nemotron 3 Ultra | Text | 1M | 0.5 |
| Kimi K2.7 Code | Text | 262.1K | 0.74 |
| GLM 5.2 | Text | 1.0M | 0.93 |
| Gemma 4 31B | Text | 262.1K | 0.12 |