ModelRushText
DeepSeek V4 Flash 0731 API
DeepSeek V4 Flash 0731 generates text from chat messages through the ModelRush API and returns generated text. Requests run synchronously and can stream tokens. It is callable in 6 execution regions, from $0.4664 per 1M input tokens.Hybrid reasoningText generationOpenAI-compatible Chat Completions
Current rate
$0.4664/ 1M tokens
Output preview

token5s
Model information
Capabilities and limits
Best for
Fast reasoningChat applicationsBatch text processing
Current customer pricing
Each row identifies the Operation, Region, price variant, and immutable price version used for execution.| Model | Capability | Execution Region | Price variant | Customer price |
|---|---|---|---|---|
| DeepSeek V4 Flash 0731 · modelrush/deepseek-v4-flash-0731 | Chat completions | cn-beijing | Standard | Input $0.4664 · Output $1.3992 / 1M tokens |
| DeepSeek V4 Flash 0731 · modelrush/deepseek-v4-flash-0731 | Chat completions | cn-hong-kong | Standard | Input $0.4664 · Output $1.3992 / 1M tokens |
| DeepSeek V4 Flash 0731 · modelrush/deepseek-v4-flash-0731 | Chat completions | eu-frankfurt | Standard | Input $0.4664 · Output $1.3992 / 1M tokens |
| DeepSeek V4 Flash 0731 · modelrush/deepseek-v4-flash-0731 | Chat completions | jp-tokyo | Standard | Input $0.4664 · Output $1.3992 / 1M tokens |
| DeepSeek V4 Flash 0731 · modelrush/deepseek-v4-flash-0731 | Chat completions | sg-singapore | Standard | Input $0.484 · Output $1.452 / 1M tokens |
| DeepSeek V4 Flash 0731 · modelrush/deepseek-v4-flash-0731 | Chat completions | us-virginia | Standard | Input $0.4664 · Output $1.3992 / 1M tokens |
Other recommended models



ModelRushOne integration, intelligent routing, transparent billing. Model infrastructure for developers and agents.© 2026 ModelRushAll systems operational