DeepSeek V4.1 Flash

HOTNEW

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 on...

1M context·$0.30 in·$1.20 out·Sep 2026 release·Vision, Reasoning, Tools / functions, Web search

Available on

OpenRouter Together AI Alibaba

Providers

Where DeepSeek V4.1 Flash runs in Big-AGI, with each service's own model ID and USD-per-1M-token rates. The summary above prefers the creator's claim; rates below are each service's own.

ServiceModel IDContextInputOutputCache read

OpenRouter

deepseek/deepseek-v4.1-flash

$0.30

$1.20

$0.01

Together AI

deepseek-ai/DeepSeek-V4.1-Flash

$0.30

$1.20

$0.01

Alibaba

deepseek-v4.1-flash

$0.30

$1.20

$0.03

Usage mix in Big-AGI: OpenRouter 68% · Community 32%Specs as reported by each service · usage over the last 2 days · refreshed hourly

Run DeepSeek V4.1 Flash in Big-AGI.

Connect your own key on any of the services above, at their rates, no markup - and run it side by side with every other model.

Launch Big-AGI

BIG-AGI

Product

Features Models Controls What's new BEAM Technology

Resources

Documentation Discord GitHub

Company

Email Us Privacy Terms