Jina DeepSearch API

Jina DeepSearch (Grounded Search) provides high-level comprehension of search results. It's designed for complex queries that require deep reasoning over many sources.

Endpoint

POST https://llm.siraya.pro/v1/chat/completions

[!IMPORTANT] This model follows the standard Chat Completions interface but is powered by Jina's search and reasoning engine.

Request Parameters

Parameter	Type	Required	Description
model	string	Yes	Use jina-deepsearch-v1.
messages	array	Yes	Standard messages array containing the user query.
stream	boolean	No	Highly recommended to use true as deep reasoning takes time.
reasoning_effort	string	No	low, medium, or high (default: medium).

Example Request

cURLPython

curl https://llm.siraya.pro/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer <API_KEY>" \
  -d '{
    "model": "jina-deepsearch-v1",
    "messages": [{"role": "user", "content": "Explain the current state of Solid State Batteries."}],
    "stream": true
  }'

from openai import OpenAI

client = OpenAI(
    base_url="https://llm.siraya.pro/v1",
    api_key="<API_KEY>"
)

response = client.chat.completions.create(
    model="jina-deepsearch-v1",
    messages=[{"role": "user", "content": "Explain the current state of Solid State Batteries."}],
    stream=True
)

for chunk in response:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)

Response

The response follows the standard OpenAI Chat Completion format, delivering the reasoning and final answer as message content.