DeepSeek V4.1 Flash 1017 API pricing

What it costs on a real workload

Per 1M tokens processed, at the rates above. How the four profiles are defined.

Compare every model on these profiles →

Observed rate history

No repricing observed since this model entered our archive on 2026-10-29. When a rate moves, the change appears here and on the sitewide ticker.

What the record shows

DeepSeek V4.1 Flash 1017 has not repriced once since it entered our archive on 2026-10-29. That is the ordinary case rather than the exception: providers ship new models at lower rates far more often than they cut the price of one already in service, which is why a cheaper option usually arrives as a new name rather than as a smaller number on this page.

Against the 44 models we price, it is the 13th cheapest for retrieval-shaped work, which reads a great deal and writes little, and the 13th cheapest for content-shaped work, which does the reverse. The two are close, so it holds its position whichever way your workload leans.

It charges 4.0 times more for output than for input, against a median of 5.0 times across the set. That is narrower than most, so it punishes long answers less than the typical model does.

Inside Mistral's own lineup it is the 7th cheapest of the 10 models we track on this workload, so 6 cheaper and 3 more expensive options sit on the same account behind the same key.

One other model we price charges exactly $0.300 in and $1.20 out: DeepSeek Flash. Where a rate ties exactly, price has stopped being the deciding factor and this site has nothing further to tell you: that choice comes down to your own evaluations, which we do not run and do not score.

Cached input reads at $0.007 against a standard input rate of $0.300, a 98% discount on the part of your prompt that repeats.

Whether it accepts image input is not stated in the source we capture, and we do not guess at it.

Its 1.05M token context window holds roughly 786,000 words of English text in a single request. A workload that does not fit cannot run here at any price, which is a capability limit rather than a cost one.

Priced near this one

Closest to DeepSeek V4.1 Flash 1017 on a retrieval workload, cheaper and more expensive alike. Cost only; we publish no quality score.

Retrieval profile: 800k in, 200k out, 70% cached where offered.