Custom integration¶

Compatibility boundary¶

A custom integration is compatible with Nexus when it can set:

https://api.nexus-hub.ru/v1 for OpenAI Chat or Responses;
https://api.nexus-hub.ru for Anthropic Messages;
https://api.nexus-hub.ru/v1beta for Gemini-compatible routes;
Bearer or another supported API-key header;
a model from GET /v1/models;
JSON and, when needed, SSE streaming.

OpenAI Python SDK¶

The official SDK accepts base_url and api_key:

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["NEXUS_API_KEY"],
    base_url="https://api.nexus-hub.ru/v1",
)
response = client.responses.create(
    model=os.environ["NEXUS_MODEL"],
    input="Reply exactly OK.",
    max_output_tokens=16,
)
print(response.output_text)

Set NEXUS_MODEL to a value from GET /v1/models. For Chat Completions, use client.chat.completions.create and its matching output limit.

Anthropic Python SDK¶

For Messages, set base_url without /v1:

import os
from anthropic import Anthropic

client = Anthropic(
    api_key=os.environ["NEXUS_API_KEY"],
    base_url="https://api.nexus-hub.ru",
)
message = client.messages.create(
    model=os.environ["NEXUS_MODEL"],
    max_tokens=16,
    messages=[{"role": "user", "content": "Reply exactly OK."}],
)
print(message.content)

Retries, timeouts, and streaming¶

Set a timeout explicitly and retry only errors that are safe to retry in your business logic. Do not retry with the same x-request-id. For streaming, consume SSE through its terminal event and close the connection on error; do not write bodies to logs.

Key hygiene and operations¶

Keep the key in an environment variable or secret manager.
Do not commit it or include it in exceptions, traces, screenshots, or prompts.
Revoke a compromised key and create a new one.
Send support only the method, route, error code, SDK version, and x-request-id.

Official SDKs: openai-python and anthropic-sdk-python. Route fields are documented in the Nexus API reference.