LLM Gateway
DeepSeek V4 Flash
deepseek-flash
Model overview
DeepSeek V4 Flash is an AI model from LLM Gateway with 1000000 token context window and text input support.
Published pricing is $0.14 input and $0.28 output per 1M tokens.
- Workloads that use text inputs with text outputs.
- Agent and tool workflows that need function calling.
- Reasoning-heavy prompts where stepwise problem solving matters.
Model ID deepseek-v4-flash
Provider LLM Gateway
Family deepseek-flash
Status -
Knowledge Cutoff 2025-05
Release Date 2026-04-24
Input Modalities text
Output Modalities text
Context Window 1000000
Input Limit -
Output Limit 384000
Tool Calling Yes
Reasoning Yes
Structured Output Yes
Temperature Control Yes
Open Weights Yes
Input Cost / 1M tokens $0.14
Output Cost / 1M tokens $0.28
Reasoning Cost / 1M tokens -
Cache Read Cost / 1M tokens $0.03
Cache Write Cost / 1M tokens -