DeepSeek V4 Flash (Reasoning, High Effort)
Available
2026-04-24
32,000 tokens
DeepSeek 开发的 AI 模型，适合多种 AI 应用场景。
Supported modalities:TextCode
Quick Overview
Text Generation4/10
Code Generation4/10
Reasoning6/10
Multimodal4/10
Benchmark Results
Scores from leading benchmark suites.
44.9%
artificial-analysis-intelligence
39.8%
artificial-analysis-coding
%
artificial-analysis-math
Performance Metrics
Latency and throughput performance.
1000ms
P50 Latency
Dive Deeper
Explore detailed analyses by topic.
Pricing Info
Input (1K tokens)$0.00014000000000000001
Output (1K tokens)$0.00028000000000000003
View detailed pricingFeature support
Streaming
Tool calling
JSON mode