Deepseek V4 Flash
by DigitalOcean · family deepseek · listed May 2026T
Fast DeepSeek model for efficient chat, coding help, and agent loops
Current rates USD per 1M tokens
Input—
Output—
Cache read—
Cache write—
Against the market
On the record
- Model id
deepseek-4-flash- Context window
- 262K tokens
- Max output
- 8K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- no
- Tool calls
- yes
- Open weights
- no
- Knowledge cutoff
- —
- Released
- 2026-05-27
- Last updated
- 2026-05-29