# DeepSeek V4 Flash: AI model fact sheet

- **Provider:** deepseek
- **Released:** 2026-04-24
- **Context window:** 1,048,576 tokens
- **API pricing:** $0.14 / 1M input, $0.28 / 1M output
- **OpenRouter ID:** deepseek/deepseek-v4-flash
- **Capabilities:** conversation, reasoning, code-generation, analysis, agentic-tool-use

DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. Designed for fast inference and high-throughput workloads, with hybrid attention for long-context processing and configurable reasoning modes. Well suited for coding assistants, chat systems, and agent workflows where responsiveness and cost efficiency are important.

Source: real side-by-side outputs, pricing and specs at https://rival.tips/models/deepseek-v4-flash