Models

Use the models endpoint to discover account-visible model IDs before configuring application traffic.

List models

GET /models

curl https://gw.r9s.ai/v1/models \
  -H "Authorization: Bearer $R9S_API_KEY"

Example response:

{
  "object": "list",
  "data": [
    {
      "id": "gpt-4o-mini",
      "object": "model",
      "created": 1626777600,
      "owned_by": "openai"
    },
    {
      "id": "qwen-plus",
      "object": "model",
      "created": 1626777600,
      "owned_by": "ali"
    }
  ]
}

Retrieve model details

GET /models/{model}

curl https://gw.r9s.ai/v1/models/gpt-4o-mini \
  -H "Authorization: Bearer $R9S_API_KEY"

Typical model fields:

Model selection guidance

• Confirm availability with GET /models instead of hard-coding a provider assumption.
• Keep separate model choices for chat, reasoning, audio, and image workflows.
• Test response compatibility before using fallback across different model families.
• Track cost and token usage per model during rollout.