DeepSeek V4.1 Flash 1017

deepseek-v4p1-flash-1017

Multimodal open-weight MoE model for long-context reasoning and agentic work

Intelligence: 45.1
Context: 1.04M
Training cutoff: --
Added: 2026-10-19
Inputs: Vision

Providers

One route serves DeepSeek V4.1 Flash 1017, and every figure below is measured on it. Where the selected window has too little traffic, the figure names what it is based on instead.

Fireworks AI only route

accounts/fireworks/models/deepseek-v4p1-flash-1017

Uptime

100.0%

Input / 1M: $0.30
Output / 1M: $1.20
TTFT: -- no requests yet
Output rate: -- needs live traffic

1.04M context 131,072 max output cache $0.006 read / $0.30 write per 1M Vision ZDR Retention None Training No Provider terms, reviewed 2026-10-13warming · 30m

Prompt caching Automatic reuse Eligible Cache key Affinity hint Caller breakpoints None advertised

TTFT is the median time to the first visible answer token over real ModelRelay requests, with a fixed prompt standing in for models that have no traffic yet. Speed ranks by it. Intelligence is the Artificial Analysis Intelligence Index.