DeepSeek V4 Flash Hits OpenRouter with 1M Context at $0.14 Input Pricing

michellechen · x · 2026-08-01

OpenRouter has officially listed the DeepSeek V4 Flash 0731 model. According to the platform, this model utilizes a sparse mixture-of-experts (MoE) architecture with 13B active parameters out of 284B total, optimized for coding, reasoning, and agent workflows.

Pricing is set at $0.14 per 1M input tokens and $0.28 per 1M output tokens, featuring a massive 1M context window. OpenRouter offers various routing modes, including Balanced, Nitro (fastest), and Exacto (highest tool-calling accuracy).

Original post →

More from Models

Models channel →