DeepSeek Chat

by DeepSeek · chat

Alias for DeepSeek V4 Flash non-thinking mode. Efficient model for general chat, coding, analysis, and high-throughput workloads. 1M context, up to 384K output, supports JSON output and tool calls.

Pricing

Input: $0.1358/M tokens · Output: $0.2716/M tokens

Capabilities

Function Calling, JSON Mode, Streaming

Context: 1000K tokens

Max output: 384K tokens

Routes: 6/6 healthy

Performance

TTFT: 8360ms · Latency: 18582ms · Throughput: 136.4 tok/s