DeepSeekdeepseek-v4.1-flash2026 Frontier

DeepSeek: DeepSeek V4.1 Flash API Pricing

DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B o...

Base Input Price$0.022/ 1M tokens

Base Output Price$0.40/ 1M tokens

Prompt Cache Read$0.004-81.82% discount

Batch API RateN/A24h async offload

Inference Hosts & Aggregator Providers

Compare rates and latency across direct APIs, OpenRouter, and hyperscale cloud providers

Live verified rates

Provider Name	Input / 1M	Output / 1M	Prompt Caching	Access Endpoint
DeepSeek Direct	$0.022	$0.40	Supported	Connect
OpenRouter	$0.022	$0.40	Supported	Connect

Head-to-Head Comparisons for DeepSeek: DeepSeek V4.1 Flash

DeepSeek: DeepSeek V4.1 Flash vs OpenAI: GPT-6.1 Sol$0.022/M vs $2/M

DeepSeek: DeepSeek V4.1 Flash vs GPT-4o (Omni)$0.022/M vs $2.5/M

DeepSeek: DeepSeek V4.1 Flash vs Claude 3.5 Sonnet$0.022/M vs $3/M

DeepSeek: DeepSeek V4.1 Flash vs DeepSeek-V3 (deepseek-chat)$0.022/M vs $0.27/M