DeepSeek-V4.1-Flash

DeepSeek-V4.1-Flash

deepseek-ai/DeepSeek-V4.1-Flash

About DeepSeek-V4.1-Flash

DeepSeek-V4.1-Flash is DeepSeek's latest multimodal MoE model with 552B backbone parameters. Built on a Causal Encoder-Decoder architecture, it activates only ~8B parameters during prefill and ~16B during decode, delivering flagship-level intelligence at significantly lower inference cost. The model natively understands images, supports a 1M-token context window. It outperforms DeepSeek-V4-Pro across coding, agentic and automation benchmarks, while reducing the KV cache footprint by roughly 4x versus its predecessor.

Available Serverless

Run queries immediately, pay only for usage

Input Price

$

0.15

/ M Tokens

Cache Read

$

0.003

/ M Tokens

Output Price

$

0.6

/ M Tokens

Metadata

Create on

License

MIT

Provider

DeepSeek

Specification

State

Available

Architecture

Causal Encoder-Decoder MoE

Calibrated

No

Mixture of Experts

Yes

Total Parameters

552B

Activated Parameters

8B / 16B

Reasoning

No

Precision

FP8

Context length

1049K

Max Tokens

393K

Supported Functionality

Serverless

Supported

Serverless LoRA

Not supported

Fine-tuning

Not supported

Embeddings

Not supported

Rerankers

Not supported

Support image input

Supported

JSON Mode

Supported

Structured Outputs

Not supported

Tools

Supported

Fim Completion

Not supported

Chat Prefix Completion

Supported

Ready to accelerate your AI development?

Ready to accelerate your AI development?

Ready to accelerate your AI development?