Embedding Models

Venice embedding models like BGE-M3 and Qwen3 Embedding with per-token pricing, privacy tiers, and OpenAI-compatible /embeddings usage.

Use the id value as the model parameter in API requests. 9 models currently available.

Model	ID	Input (per 1M tokens)	Privacy
BGE-EN-ICL	text-embedding-bge-en-icl	$0.01	Private
BGE-M3	text-embedding-bge-m3	$0.15	Private
Gemini Embedding 2 Preview	gemini-embedding-2-preview	$0.25	Anonymized
Multilingual E5 Large Instruct	text-embedding-multilingual-e5-large-instruct	$0.01	Private
Nemotron Embed VL 1B v2	text-embedding-nemotron-embed-vl-1b-v2	$0.01	Private
Qwen3 Embedding 0.6B	text-embedding-qwen3-0-6b	$0.01	Private
Qwen3 Embedding 8B	text-embedding-qwen3-8b	$0.01	Private
Text Embedding 3 Large	text-embedding-3-large	$0.16	Anonymized
Text Embedding 3 Small	text-embedding-3-small	$0.03	Anonymized

---

See the Embeddings API for usage examples.