DeepSeek V4.1 Flash token prices

DeepSeek V4.1 Flash is an open-weight model that takes text and images as input, with a context window of about a million tokens in its maker’s listing. Dated versions of it are listed separately, so match the full name when you compare.

On 12 Nov 2026, 28 hosts listed DeepSeek V4.1 Flash here. The lowest listed input price was $0.022 per million tokens. The lowest listed output price was $0.336 per million tokens.

Runcrate serves DeepSeek V4.1 Flash at $0.147 per million input tokens and $0.44 per million output tokens.

Hosts state several different precisions for this model. They also set very different limits on output: some cap a single answer at a small fraction of what others allow. Each of those choices changes what it costs a host to serve a token.

So the lowest row is not always the same product as the row above it. Read precision and output limit beside the price.

The hosts listed for this model state a cached input price. If your requests share a long opening, compare hosts on that figure too. For an agent that resends a long prompt on every step, it can outweigh the normal input price.

Count a day of your input and output tokens on this model. Multiply each, in millions, by one host’s two prices and add them. Repeat for the hosts whose limits and precision you accept.

Then test your own prompts on the two lowest-priced. A lower price is a saving only if the answers hold up.

This is one of a coordinated collection of Runcrate references. Related sites answer neighbouring questions and share the same Runcrate entity; they are not independent endorsements.