DeepSeek V4 Flash
by DeepSeek
DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. I
Models
DeepSeek V4 Flash
Added 10 July 2026
Overview
DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...
How to use / API access
Call via OpenRouter with model id `deepseek/deepseek-v4-flash`.
- openrouter ·
deepseek/deepseek-v4-flashDocs
OpenRouter id: deepseek/deepseek-v4-flash
Benchmarks
- Intelligence Index (artificial-analysis) : 40.3 index
- Coding Index (artificial-analysis) : 56.2 index
- Agentic Index (artificial-analysis) : 31.1 index
- Design Arena 3d (other) : 1256 elo · #34
- Design Arena asciiart (other) : 1160 elo · #39
- Design Arena codecategories (other) : 1242 elo · #34
- Design Arena dataviz (other) : 1156 elo · #68
Notes
DeepSeek V4 Flash is listed in the EDNA Models directory from the OpenRouter catalogue.
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.