AI Rate Card

deepseek-v4-1-flash-fast vs Kimi K3: API price and specs

Kimi K3 is 37% cheaper than deepseek-v4-1-flash-fast on input price.

Kimi K3 is 33% cheaper than deepseek-v4-1-flash-fast on output price.

Kimi K3 is 35% cheaper than deepseek-v4-1-flash-fast on a 1M-in / 200k-out workload.

Fielddeepseek-v4-1-flash-fastKimi K3
Lowest input, per 1M$0.60 +58%$0.38
Median input, per 1M$0.60$3.00 +400%
Lowest output, per 1M$2.40 +48.8%$1.61
Median output, per 1M$2.40$15.00 +525%
Lowest unit price——
Cost of 1M in + 200k out$1.08 +53.7%$0.70
Context1M1M
Max output384K +63.4%1M
Providers5 +91.9%62
RegionsUSAPAC, EU, GLOBAL, US
Acceptsimage, textapplication/pdf, file, image, image/bmp, image/gif, image/heic, image/heif, image/jpeg, image/png, image/webp, pdf, text, video, video/3gpp, video/avi, video/mov, video/mp4, video/mpeg, video/mpg, video/webm, video/wmv, video/x-flv
Returnstexttext
TypeText modelsText models
Free optionnoyes
Cheapest providerbasetentrustedrouter

Your own workload: how many tokens the model gets (input) and gives back (output) - for example, in a month. The "Cost" row of the table above is recalculated for these numbers, for each model.

Computed from current offers each time the page opens; the best value of a row is bold, the percent is how far behind the best.

Providers selling both

baseten, inco, kilo, trustedrouter, vercel

Frequently asked questions

Which is cheaper, deepseek-v4-1-flash-fast or Kimi K3?

Kimi K3 is 37% cheaper than deepseek-v4-1-flash-fast on input price. Kimi K3 is 33% cheaper than deepseek-v4-1-flash-fast on output price. Kimi K3 is 35% cheaper than deepseek-v4-1-flash-fast on a 1M-in / 200k-out workload.

Which has the larger context, deepseek-v4-1-flash-fast or Kimi K3?

deepseek-v4-1-flash-fast: 1M tokens; Kimi K3: 1M tokens.

Where can I use both deepseek-v4-1-flash-fast and Kimi K3?

baseten, inco, kilo, trustedrouter, vercel