DeepSeek V4 Flash
Fast, very low-cost DeepSeek with 1M context and thinking mode.
- Reasoning
- Coding
- Tool calling
- Structured output
- Extended thinking
- Streaming
Specifications
| Provider | DeepSeek |
|---|---|
| API model ID | deepseek-v4-flash |
| Released | July 2026 |
| Context window | 1,000,000 tokens |
| Max output | 384,000 tokens |
| Reasoning model | Yes |
| Price per 1M tokens (input / output) | See provider |
Specs as published by DeepSeek. Prices are standard list prices before caching or batch discounts.
Compare DeepSeek V4 Flash
More DeepSeek models
FAQ
- What is the context window of DeepSeek V4 Flash?
- DeepSeek V4 Flash accepts up to 1,000,000 tokens of context and can return up to 384,000 output tokens per reply.
- When was DeepSeek V4 Flash released?
- DeepSeek released DeepSeek V4 Flash in July 2026.
- How do I use DeepSeek V4 Flash?
- Add your DeepSeek API key in DapperGPT, pick DeepSeek V4 Flash in the model picker, and start chatting. You pay DeepSeek directly for usage.