DeepSeek-V4.1-Flash vs DeepSeek-V4.1-Flash-1017

Specs, VRAM requirements and download trends — updated 24 October 2026.

deepseek-ai · A · Open weights

Params

763.2 B

Context

—

30d

1.5 M

mit · commercial OK

deepseek-ai · B · Open weights

Params

763.2 B

Context

—

30d

58 K

mit · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification	DeepSeek-V4.1-Flash	DeepSeek-V4.1-Flash-1017
Deployment	Open weights · also via API	Open weights · also via API
Parameters	763.2 B	763.2 B
Architecture	DeepseekV41ForCausalLM	DeepseekV41ForCausalLM
Context length	1,048,576	1,048,576
Licence	mit	mit
Commercial use	Allowed	Allowed
Languages	—	—
Downloads 30d	1,478,503	57,715
Downloads all time	2.1 M	58 K
Quantizations on the Hub	SAFETENSORS	SAFETENSORS
Gated	No	No
First seen on the Hub	2026-09-10	2026-10-17
API input price / 1M tokens	$0.02	$0.15
API output price / 1M tokens	$1.00	$0.60
Est. cost per 1M input + 1M output tokens	$1.02	$0.75
Cached input / 1M tokens	$0.015	$0.003
AA Intelligence Index	24.7	39.5
AA Coding Index	—	—
AA Agentic Index	—	—
Max output tokens	943,718	393,216
API providers	33	29
Tool calling	Yes	Yes
Reasoning mode	Yes	Yes