AI Rate Card

MiniMax-M3 vs Hy3: API price and specs

Hy3 is 35% cheaper than MiniMax-M3 on input price.

MiniMax-M3 is 62% cheaper than Hy3 on output price.

Hy3 is 2% cheaper than MiniMax-M3 on a 1M-in / 200k-out workload.

MiniMax-M3 has a 300% larger context than Hy3.

FieldMiniMax-M3Hy3
Lowest input, per 1M$0.20 +53.8%$0.13
Median input, per 1M$0.30 +114.9%$0.14
Lowest output, per 1M$0.20$0.53 +164%
Median output, per 1M$1.20 +111.1%$0.57
Lowest unit price——
Cost of 1M in + 200k out$0.24 +1.9%$0.24
Context1M262K +75%
Max output1M262K +75%
Providers4619 +58.7%
RegionsAPAC, EU, GLOBAL, USAPAC, US
Acceptsfile, image, image/gif, image/jpeg, image/png, image/webp, pdf, text, video, video/mp4, video/quicktime, video/x-matroska, video/x-msvideofile, text
Returnstexttext
TypeText modelsText models
Free optionyesyes
Cheapest provideraihubmixdeepinfra

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

aihubmix, aiml, deepinfra, edenai, huggingface, impossibl, kenari, kilo, novita, opencode, opencode-go, openrouter, orcarouter, poe, requesty, siliconflow, trustedrouter, vercel, zenmux

Frequently asked questions

Which is cheaper, MiniMax-M3 or Hy3?

Hy3 is 35% cheaper than MiniMax-M3 on input price. MiniMax-M3 is 62% cheaper than Hy3 on output price. Hy3 is 2% cheaper than MiniMax-M3 on a 1M-in / 200k-out workload.

Which has the larger context, MiniMax-M3 or Hy3?

MiniMax-M3: 1M tokens; Hy3: 262K tokens.

Where can I use both MiniMax-M3 and Hy3?

aihubmix, aiml, deepinfra, edenai, huggingface, impossibl, kenari, kilo, novita, opencode, opencode-go, openrouter, orcarouter, poe, requesty, siliconflow, trustedrouter, vercel, zenmux