Using Doubao Embedding Vision on Volcengine

Implementation guide · Doubao Embedding Vision · ByteDance

Serverless

Volcengine exposes Doubao Embedding Vision through model ID doubao-embedding-vision-251215. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-07-10. Next refresh: weekly.

Quick Start

  1. 1
    Create an account at Volcengine and generate an API key.
  2. 2
    Use the Volcengine SDK or REST API to call doubao-embedding-vision-251215 — see the documentation for request format.
API PortalDocumentationPricingModel Card

Code Examples

See Volcengine documentation for integration details.

Pricing on Volcengine

Capabilities

VisionMultimodal

About Doubao Embedding Vision

Doubao Embedding Vision is ByteDance's multimodal embedding model for text-image retrieval, semantic search and RAG. It maps text and visual inputs into a shared representation space and is not a generative vision model.

Full model details →

Model Specs

Released2025-12-15

Provider

Volcengine

ByteDance

Beijing, China