Doubao Embedding Vision

Vision Embedding

doubao-embedding-vision · Doubao · embedding

Back to Models Back to Docs

Platform

Doubao

Visit Official Site

API Pricing

Input / 1M

$0.1/M

Output / 1M

$0/M

Overview

ByteDance Doubao Embedding Vision, multimodal embedding model supporting both image and text input.

Capabilities

Multimodal embedding (image + text); semantic search; RAG retrieval; clustering; classification.

Use Cases

Multimodal RAG; visual search; document clustering; image-text similarity matching.

Limitations

No text generation; no Function Calling; output dimension fixed; image input costs more.

Examples

Claude Code

Anthropic official CLI coding agent. Multi-file edits, tool use, long-context reasoning.

Terminal

export ANTHROPIC_AUTH_TOKEN="YOUR_API_KEY"
export ANTHROPIC_BASE_URL="https://api.robovai.com"
export ANTHROPIC_MODEL="doubao-embedding-vision"
claude

Context Window

8K ctx

Thinking Mode

Not supported

Overview

ByteDance Doubao Embedding Vision, multimodal embedding model supporting both image and text input.