Skylark Embedding Vision

Embedding ByteDance Seed Partly verified Released Apr 2025

Skylark Embedding Vision is ByteDance’s multimodal embedding model for vector retrieval, converting images and Chinese or English text into dense vectors for search. Summary written by AI Index from ByteDance Seed’s own pages.

  • In Input modalities: TextImage

Prices

1 offering · prices as listed
BytePlus ModelArk (opens in a new tab) Official ap-southeast-1 · USD skylark-embedding-vision
Conditions/ 1M tokensInput
Text tokens Standard $0.125
Image tokens $0.325

Prices from Pricing--ModelArk-Byteplus (opens in a new tab) (checked Nov 8, 2026)

Standard: the price a request with no conditions pays (the headline price elsewhere on the site).

Details

Model ID

Not stated on ByteDance Seed’s pages: shortest vector, vector types, inputs per request, languages.

Cited scores

From third-party leaderboards, not measured by us

No cited leaderboard covers embedding models yet. MTEB’s results are open (CC0); we will cite them per benchmark, never as a combined score.

  1. Now priced on BytePlus ModelArk, ap-southeast-1 Input $0.325

Sources

ByteDance Seed’s official policies: data use, privacy, terms →

Some values on this page are still waiting to be checked against official pages: a filled dot is verified, a hollow one is not yet (with or without a source on file). How we verify data

ByteDance Seed · China · seed.bytedance.com

Snapshots, the same family and other models from this provider