Jina API - Access Jina Embedding and Rerank Models via AIsa - AIsa

AIsa gives you access to Jina’s embedding and reranker models with one AIsa API key. Embedding models use the OpenAI-compatible POST /v1/embeddings endpoint, and the reranker uses POST /v1/rerank. A common retrieval setup embeds and shortlists candidates first, then reranks them for the final order.

Supported Jina models

Model ID	Type	Endpoints
`jina-embeddings-v3`	Embedding	`/v1/embeddings`, `/v1/classify`
`jina-embeddings-v5-text-small`	Embedding	`/v1/embeddings`
`jina-reranker-v3`	Rerank	`/v1/rerank`

Current prices for these models are on aisa.one/models.

Quickstart

Embed text with the OpenAI SDK:

from openai import OpenAI

client = OpenAI(api_key="YOUR_AISA_API_KEY", base_url="https://api.aisa.one/v1")

response = client.embeddings.create(
    model="jina-embeddings-v5-text-small",
    input=["A fast, OpenAI-compatible embeddings endpoint."],
)
print(len(response.data[0].embedding))

Rerank documents against a query:

curl https://api.aisa.one/v1/rerank \
  -H "Authorization: Bearer $AISA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "jina-reranker-v3",
    "query": "What is the capital of France?",
    "documents": ["Paris is the capital of France.", "Berlin is the capital of Germany."]
  }'

Request and response fields are in Embeddings and Rerank Documents.

Next