Models

GET /v1/models

Returns all available models with pricing and metadata.

Example

curl https://api.aiand.com/v1/models \
  -H "Authorization: Bearer sk-your-api-key"

Response

{
  "object": "list",
  "data": [
    {
      "id": "openai/gpt-oss-120b",
      "object": "model",
      "created": 1700000000,
      "owned_by": "ai&",
      "provider": "openai",
      "context_window": 128000,
      "description": "Fast, affordable small model for lightweight tasks",
      "currency": "usd",
      "input_per_1m": "0.150000",
      "output_per_1m": "0.600000"
    }
  ]
}

Model object

Field	Type	Description
id	string	Model identifier — use this as the model parameter in requests
object	string	Always "model"
created	integer	Unix timestamp
owned_by	string	Always "ai&"
provider	string	Upstream provider name
context_window	integer	Maximum context length in tokens
description	string	Short model description
currency	string	Your organization’s billing currency (usd or jpy)
input_per_1m	string	Cost per 1M input tokens, in your billing currency. Numeric value returned as a string for precision (e.g. "0.150000")
output_per_1m	string	Cost per 1M output tokens, in your billing currency

Example

curl https://api.aiand.com/v1/models \
  -H "Authorization: Bearer sk-your-api-key"

Model name resolution

The model parameter you send on an inference request (/v1/chat/completions, /v1/completions, /v1/responses, /v1/messages) is resolved as follows:

1. Exact match (case-insensitive) against a model id always wins.
2. Otherwise, the value is treated as a prefix: the request resolves to the highest-priority model whose id starts with it.

This lets you pin to a model family without naming an exact version. For example, with kimi-2.6 and kimi-2.7 both available, sending "model": "kimi" resolves to whichever the catalog lists first (the higher-priority version). Sending "model": "kimi-2.6" still resolves to that exact version. If nothing matches, the request returns a 400 listing GET /v1/models as the source of valid names.

Usage is always recorded and billed against the resolved model’s canonical id, regardless of which prefix you sent.

Cost calculation

cost = (input_tokens / 1_000_000 * input_per_1m) + (output_tokens / 1_000_000 * output_per_1m)

Credits are deducted after each successful request. Failed requests (4xx/5xx) are not billed.