DeepSeek · DeepSeek V4
DeepSeek V4 Flash
deepseek/deepseek-v4-flash
Fast DeepSeek V4 lane for economical reasoning, coding and long-context work.
Open weightsReasoningTool callingStructured outputTemperature
Model specifications
- Context window
- 1M tokens
- Output limit
- 384K tokens
- Release date
- 2026-04-24
- Input modalities
- text
- Output modalities
- text
- Last updated
- 2026-04-24
Provider pricing
USD per 1M tokens. Limits may differ from the underlying model.
Checked 2026-08-06
OpenRouter
deepseek/deepseek-v4-flash
- Input
- $0.0882
- Output
- $0.18
- Context
- 1.05M
SiliconFlow
deepseek-ai/DeepSeek-V4-Flash
- Input
- $0.14
- Output
- $0.28
- Context
- 1M
Promotions, plan quotas, cache pricing and regional taxes are not included. Recheck the provider before purchase.