OpenRouterDeepSeek V4 Flash model ID, context window & pricing
deepseek-flash
Quick facts
Model ID deepseek/deepseek-v4-flash
Source OpenRouter
Context Window 1048575
Pricing $0.10 input / $0.20 output per 1M tokens
Capabilities tool calling, reasoning, structured output, temperature control, open weights
Model overview
DeepSeek V4 Flash is an AI model from OpenRouter with 1048575 token context window and text input support.
Published pricing is $0.10 input and $0.20 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/deepseek-v4-flash
Provider OpenRouter
Family deepseek-flash
Status -
Knowledge Cutoff 2025-05
Release Date 2026-04-24
Input Modalities text
Output Modalities text
Context Window 1048575
Input Limit -
Output Limit 65536
Tool Calling Yes
Reasoning Yes
Structured Output Yes
Temperature Control Yes
Open Weights Yes
Input Cost / 1M tokens $0.10
Output Cost / 1M tokens $0.20
Reasoning Cost / 1M tokens -
Cache Read Cost / 1M tokens $0.02
Cache Write Cost / 1M tokens -
Editorial take
DeepSeek V4 Flash is the speed-optimized sibling to the Pro model.
Accessed via OpenRouter, it's designed for high-throughput, low-latency tasks like real-time text processing, classification, and summarization. Choose this over Pro when speed and cost-efficiency outweigh the need for deep reasoning.