DeepSeek V4 Flash
DeepSeek's fast, cost-efficient V4 mixture-of-experts model (MIT) with long context and native tool calling.
DeepSeek V4 Flash is a cloud text model from DeepSeek. It takes a text prompt and replies with generated text. Its context window handles up to 1M input tokens and up to 66K output tokens, and it supports adjustable reasoning effort for harder problems. Generation can be tuned with system instructions, temperature, and top-p sampling. It runs through Runware using your own API key, from $0.20 per million input tokens.
- Pricing
- $0.20 / 1M in · $0.80 / 1M out
- Context window
- 1M in · 66K out
- Reasoning
- Adjustable effort
- Controls
- System prompt, Temperature, Top-p
DeepSeek
DeepSeek is a Chinese AI lab whose open-weight models — from the R1 reasoning distills to the V4 mixture-of-experts family — bring frontier-grade reasoning under permissive (MIT) licensing.
www.deepseek.com ↗Examples
Sample outputs generated with DeepSeek V4 Flash will appear here.