We provide free access to our APIs at sufficient levels for most research and development purposes. For large-scale deployment, our APIs are priced based on usage. We also offer enterprise plans to organizations looking to deploy their applications at scale. To update your billing information or inquire about commercial use of our SDKs or datasets, please message support or email [email protected].

Video & Audio (Transcription Included)

Audiovisual files or streams processed by our facial expression, vocal burst, speech prosody, and/or emotional language models will be subject to the following prices per minute. For videos with many faces, additional costs may apply (capped at price/min x number of faces).

TierVolume (min/mo)Price per minute
Free0-100 minFree
T1100-10,000 min$0.0276
T210,000-100,000 min$0.0176
T3100,000-1 million min$0.012
T4> 1 million min$0.0092

Audio Only (Transcription Included)

Audio files or streams processed by our vocal expression, speech prosody, and emotional language models will be subject to the following prices per minute.

TierVolume (min/mo)Price per minute
Free0-100 minFree
T1100-10,000 min$0.0212
T210,000-100,000 min$0.0132
T3100,000-1 million min$0.0088
T4> 1 million min$0.0068

Video Only

Video files or streams processed by our facial expression models only will be subject to the following prices per minute. For videos with many faces, additional costs may apply (capped at price/min x number of faces).

TierVolume (min/mo)Price per minute
Free0-100 minFree
T1100-10,000 min$0.014
T210,000-100,000 min$0.0088
T3100,000-1 million min$0.006
T4> 1 million min$0.0044

Images

Images processed by our facial expression models (batch or streaming) will be subject to the following prices per annotation (i.e., per face, but with a minimum of one annotation per image).

TierVolume (annotations/mo)Price per annotation
Free0-4,000 annotationsFree
T14,001-10,000 annotations$0.00068
T210,001-100,000 annotations$0.00044
T3100,001-1 million annotations$0.000284
T41-10 million annotations$0.00022
T5> 10 million annotations$0.000132

Face Mesh

Mediapipe facial landmark locations processed by our face mesh model (batch or streaming) will be subject to the following prices per face

TierVolume (annotations/mo)Price per annotation
Free0-4,000 annotationsFree
T14,001-10,000 annotations$0.00068
T210,001-100,000 annotations$0.00044
T3100,001-1 million annotations$0.000284
T41-10 million annotations$0.00022
T5> 10 million annotations$0.000132

Text Only

Text processed by our emotional language models (batch or streaming) will be subject to the following prices per word.

TierVolume (words/mo)Price per word
Free0-10,000 wordsFree
T110,001 to 1 million words$0.00008
T21-10 million words$0.000056
T310-100 million words$0.00004
T4> 100 million words$0.000028