Jina Embeddings v5 Omni Nano
Compact multimodal embedding model (~1.0B parameters) for text, image, video, audio, and PDF in a shared 768-dimensional space.
Specs
- Context
- 8.2K
- Max output
- —
- Input price
- $0.02/ 1M tokens
- Output price
- —
- Released
- 2026-05-07
Context
- Context window
- 8.2K
- Max input
- 8.2K
- Max output
- —
Pricing · USD / 1M tokens
- Input
- $0.02
- Output
- —
- Cache read
- —
- Cache write
- —
Modalities
- Input
- TextImageVideoAudioDocument
- Output
- Embedding
API
- API types
Reasoning
- Not published
Info
- Status
- Active
- Released
- 2026-05-07
- Knowledge cutoff
- —
Features
- Not published
How to call
1 provider
jinamodel = jina-embeddings-v5-omni-nano
embeddings
POSThttps://api.jina.ai/v1/embeddings
JSON
Standard format
{
"id": "jina-embeddings-v5-omni-nano",
"object": "model",
"created": 1778112000,
"owned_by": "jina",
"name": "Jina Embeddings v5 Omni Nano",
"api": {
"types": [
"embeddings"
]
},
"limits": {
"context": 8192,
"input": 8192,
"output": null
},
"modalities": {
"input": [
"text",
"image",
"video",
"audio",
"document"
],
"output": [
"embedding"
]
},
"reasoning": {
"supported": null,
"efforts": []
},
"pricing": {
"currency": "USD",
"unit": "1M_tokens",
"input": 0.02,
"output": null,
"cache_read": null,
"cache_write": null
},
"features": [],
"info": {
"status": "active",
"release_date": "2026-05-07",
"knowledge_cutoff": null,
"description": "Compact multimodal embedding model (~1.0B parameters) for text, image, video, audio, and PDF in a shared 768-dimensional space.",
"docs": "https://jina.ai/models/jina-embeddings-v5-omni-nano",
"verified_at": "2026-10-11"
}
}Official sources
3