Delos API for Developers

Delos provides an OpenAI-compatible API allowing developers to integrate Delos AI models into their own applications.

Features

  • Chat completions: /v1/chat/completions compatible endpoint with parallel tool-calling support
  • Embeddings: /v1/embeddings endpoint for semantic search and RAG
  • Models: GET /v1/models endpoint listing all available models (chat and embeddings), tagged by capabilities
  • Granular scopes: distinct access rights (assistant:messages, assistant:embeddings) enforced per endpoint
  • Automation: automate workflows and query your data via the API

Authentication

The API uses API keys. To generate a key:

  1. Go to your Delos account settings
  2. API Keys section
  3. Create a new key by selecting the desired scopes
  4. Copy the generated key (it will not be displayed again)

Usage:

  • Endpoint: https://api.delos.so/v1
  • Authentication: header Authorization: Bearer YOUR_API_KEY
  • Full documentation: available in the Developers section of your workspace

Limits

  • Rate limit: 60 requests per minute per key
  • Maximum request size: 10 MB

Compatibility

The Delos API is compatible with the OpenAI SDK. You can use standard OpenAI client libraries by simply changing the base URL to the Delos endpoint.

Usage example

from openai import OpenAI

client = OpenAI(
    api_key="your-delos-api-key",
    base_url="https://api.delos.so/v1"
)

response = client.chat.completions.create(
    model="gpt-5",
    messages=[{"role": "user", "content": "Hello!"}]
)

Source: PR #8759 (cosmos-saas, merged 2026-06-18)