DeepSeek: DeepSeek V4 Flash Latest API
About
Build advanced reasoning agents with DeepSeek: DeepSeek V4 Flash Latest, a specialized AI model optimized for complex logic and chain-of-thought tasks. This model delivers cost-effective pricing at $0.0069/1M input and $0.14/1M output tokens, native tool calling support. Access DeepSeek: DeepSeek V4 Flash Latest via the Kilo Gateway API with up to 944K output tokens.
Capabilities
Input Modalities
text
Output Modalities
text
Reasoning
Yes
Structured Output
Yes
Tool Use
Yes
WeightsClosed
Limits
Context Window
1.0M
Tokens
Input Limit
1.0M
Tokens
Max Output
944K
Tokens
Pricing
Standard (per 1M tokens)
Input
$0.0069
Output
$0.14
Caching (per 1M tokens)
Read
$0.0015
Frequently Asked Questions
DeepSeek: DeepSeek V4 Flash Latest by Kilo Gateway costs $0.0069 per 1M input tokens and $0.14 per 1M output tokens. Cached reads cost $0.0015 per 1M tokens.
Model Details
ID
~deepseek/deepseek-v4-flash-latest
Provider
Kilo GatewayFamily
deepseek
Release Date
Aug 1, 2026
Knowledge Cutoff
N/A
API Integration
NPM Package
@ai-sdk/openai-compatible
Environment Variables
KILO_API_KEY
API Base URL
https://api.kilo.ai/api/gateway