Jina AIEmbedding

Jina Embeddings V3

jina-embeddings-v3

Jina Embeddings V3 by Jina AI.

Context: 8.2K tokens
Endpoint

Pricing

Input$0.05 / 1M

Output—

Cache Write (5m)$0.05 / 1M

Cache Write (1h)$0.05 / 1M

Cache Read$0.05 / 1M

Quick Start

Select an endpoint and copy a working example for this model.

Endpoint

python

from openai import OpenAI client = OpenAI(    api_key="YOUR_API_KEY",    base_url="https://api.apertis.ai/v1") response = client.chat.completions.create(    model="jina-embeddings-v3",    messages=[        {"role": "user", "content": "Hello!"}    ],    max_tokens=1024,    temperature=0.7) print(response.choices[0].message.content) # Optional: Enable context compression to reduce token usage# response = client.chat.completions.create(#     model="jina-embeddings-v3",#     messages=[{"role": "user", "content": "Hello!"}],#     extra_body={"compression": {"enabled": True, "model": "gpt-4.1-mini"}}# )

Supported Parameters

API docs

Common4 params

modelinputencoding_formatdimensions

Extended1 param

user

Cursor IDE Model IDs

Use these namespaced identifiers in Cursor IDE to avoid conflicts with built-in models.

jina-embeddings-v3

Questions about Jina Embeddings V3

How much does Jina Embeddings V3 cost on Apertis?

Jina Embeddings V3 costs $0.05 per 1M input tokens on Apertis.

What is Jina Embeddings V3's context window?

Jina Embeddings V3 has a context window of 8.2K tokens.

Which company develops Jina Embeddings V3?

Jina Embeddings V3 is developed by Jina AI.

Which model ID do I use to call Jina Embeddings V3?

Use the model ID jina-embeddings-v3 to call Jina Embeddings V3.

Compare with Other Models

See how this model compares to others from the same provider.

Jina Embeddings V5 Text Small

Context: 8.2K
Input: $0.05/M
Output: — (Not priced per output token)

Jina Embeddings V5 Text Nano

Context: 8.2K
Input: $0.05/M
Output: — (Not priced per output token)

Jina Embeddings V2 Base ES

Context: 8.2K
Input: $0.05/M
Output: — (Not priced per output token)

Jina Embeddings V2 Base DE

Context: 8.2K
Input: $0.05/M
Output: — (Not priced per output token)