deepseek-v4.1-flash

Name: deepseek-v4.1-flash
Author: Ollama

open-weight8B

Designed for greater capability, faster inference, higher throughput, and scaling to larger models.

Capabilities

Show unsupported (4)

Reasoning & Interaction

Reasoning

Tool Calling

Infrastructure

Streaming

Fine-tuning

ProviderOllama

Licenseopen-weight

Status—

Typechat

Input modalitiestext, image

Output modalitiestext

Open weightYes

Parameters8B

Architecture—

Context window—

Max input—

Max output—

Reasoning tokensYes

Knowledge cutoff—

Release date2026-10-17

Sourceofficial

Function Callingfunction_calling

Call external functions and APIs

Model	Caps	Perf	Speed	Context	Max out
deepseek-v3.1	SF	—	—	164K	—
deepseek-v3.2	RTSF	—	—	164K	—
deepseek-v4-flash	RTJMSF	—	—	1M	384K
deepseek-v4-pro	RTJMSF	—	—	1M	384K
deepseek-v4.1-flash	RTSF	—	—	—	—

GET/v1/models/ollama/deepseek-v4.1-flash

Designed for greater capability, faster inference, higher throughput, and scaling to larger models.

Changes · 4 entries

deepseek-v4.1-flashcreateca7a400Nov 2, 2026, 03:02 AM

deepseek-v4.1-flashupdate42a9895Oct 20, 2026, 06:39 AM

release_date2026-09-10→2026-10-17

deepseek-v4.1-flashupdate63ba2aaOct 18, 2026, 06:34 AM

descriptionDeepSeek-V4.1-Flash is an advanced tool designed to enhan...→Designed for greater capability, faster inference, higher...

deepseek-v4.1-flashcreate17bcfbfSep 11, 2026, 06:36 AM