DeepSeek V4 Flash API
About
Build advanced reasoning agents with DeepSeek V4 Flash, a specialized AI model optimized for complex logic and chain-of-thought tasks. This model delivers available completely free of charge, native tool calling support, open weights architecture. Access DeepSeek V4 Flash via the Umans AI Coding Plan API with up to 393K output tokens.
Capabilities
Input Modalities
text
Output Modalities
text
Reasoning
Yes
Structured Output
Yes
Tool Use
Yes
WeightsOpen
Temperature
Adjustable
Attachment
Not Supported
Limits
Context Window
1.0M
Tokens
Input Limit
1.0M
Tokens
Max Output
393K
Tokens
Pricing
Standard (per 1M tokens)
Input
Free
Output
Free
Caching (per 1M tokens)
Read
Free
Write
Free
Frequently Asked Questions
DeepSeek V4 Flash by Umans AI Coding Plan costs Free per 1M input tokens and Free per 1M output tokens. Cached reads cost Free per 1M tokens. Cache writes cost Free per 1M tokens.
Model Details
ID
umans-deepseek-v4-flash-0731
Provider
Umans AI Coding PlanFamily
deepseek-flash
Release Date
Jul 31, 2026
Knowledge Cutoff
May 1, 2025
API Integration
NPM Package
@ai-sdk/openai-compatible
Environment Variables
UMANS_AI_CODING_PLAN_API_KEY
API Base URL
https://api.code.umans.ai/v1