List currently-effective per-model pricing

curl --request GET \
  --url https://tokens.flex.ai/v1/pricing

{
  "object": "list",
  "data": [
    {
      "model": "<string>",
      "currency": "USD",
      "effective_at": "2023-11-07T05:31:56Z",
      "input_per_mtok": 123,
      "output_per_mtok": 123,
      "cached_input_per_mtok": 123,
      "unit_price_usd": 123,
      "billing_unit": "<string>",
      "resolution_tier": "<string>",
      "quality_tier": "<string>"
    }
  ],
  "generated_at": "2023-11-07T05:31:56Z"
}

Models

List currently-effective per-model pricing

FlexAI extension. Returns the currently-effective pricing rows for every active model. Public, unauthenticated — pricing is global and identical for every caller. Cache-Control is public, max-age=60, stale-while-revalidate=120, so frequent polling is inexpensive.

Pricing lives on its own endpoint (not as a custom field on /v1/models) so packaging changes — credits, volume tiers, enterprise contracts — can extend the response without breaking SDK clients reading from /v1/models. Every entry carries pricing_type and effective_at for forward compatibility.

GET

pricing

curl --request GET \
  --url https://tokens.flex.ai/v1/pricing

{
  "object": "list",
  "data": [
    {
      "model": "<string>",
      "currency": "USD",
      "effective_at": "2023-11-07T05:31:56Z",
      "input_per_mtok": 123,
      "output_per_mtok": 123,
      "cached_input_per_mtok": 123,
      "unit_price_usd": 123,
      "billing_unit": "<string>",
      "resolution_tier": "<string>",
      "quality_tier": "<string>"
    }
  ],
  "generated_at": "2023-11-07T05:31:56Z"
}

Response

200 - application/json

Successful response

object

enum<string>

required

Available options:

list

data

object[]

required

Show child attributes

generated_at

string<date-time>

required

List available models Programmatic spend for the calling key

⌘I