DeepSeek R1 0528

by DeepSeek · chat

Upgraded reasoning model with improved benchmark performance, enhanced front-end development capabilities, and reduced hallucinations. Supports JSON output and function calling for structured reasoning tasks and tool-integrated workflows.

Pricing

Input: $0.5115/M tokens · Output: $2.0367/M tokens

Capabilities

Function Calling, JSON Mode, Streaming, Reasoning

Context: 128K tokens

Max output: 66K tokens

Routes: 4/4 healthy

Performance

TTFT: 6311ms · Latency: 46199ms · Throughput: 31.2 tok/s