DeepSeek V4.1 FlashDeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, a refreshed generation of the V4 Flash line for coding, reasoning, and agent workflows. Served here at a quarter of OpenRouter's listed rate.

Input price: $0.0375 per 1M tokens

Output price: $0.15 per 1M tokens

Blended price: $0.065625 per 1M tokens

Max context: 1.0M

Max output tokens: 943K

Modalities: text

Reasoning efforts: low, high, max

Category: chat

curl -X POST https://ai.layercloud.ir/ollama/v1/chat/completions \ -H "Authorization: Bearer YOUR_TOKEN" \ -H "Content-Type: application/json" \ -d '{ "model": "deepseek/deepseek-v4.1-flash", "messages": [{"role": "user", "content": "Hello!"}] }'Related models

Get an API keyRead this page in plain markdown