DeepSeek V4 Flash 0731 Fast
Fast DeepSeek model for efficient chat, coding help, and agent loops
Model facts
- Context window
- 1M tokens
- Maximum output
- 33K tokens
- Cheapest paid input
- $0.35 per 1M tokens
- Cheapest paid output
- $0.7 per 1M tokens
- Open weights
- yes
- Providers
- 1
Capabilities and modalities
reasoning, tool calling, structured output, temperature control, open weights, text.
Observed price history
- 2026-08-24: $0.35 input / $0.7 output per 1M tokens
API providers
- Venice AI — model id deepseek-v4-flash-0731-fast; $0.35 input / $0.7 output per 1M tokens; provider documentation