Skip to content
KataraKatara documentation

List models

GET
/models
curl --request GET \
  --url https://api.katara.com/v1/models

The model the API serves, katara/cortex, listed with cortex: true, the capabilities and context its models offer, and its price ceiling (basis: ceiling). Any model name in a request is accepted and served by it. Two more rows, katara/cortex-genius and katara/cortex-smart, are sold only per request with x402 (billing_methods: [x402]): each lists its first model’s price (basis: model) and its minimum_charge. Under /test/v1 those two rows carry no pricing.

Responses

Section titled “Responses”

200

Section titled “200”

The model list.

Media typeapplication/json
object
object
required
string
Allowed value: list
data
required
Array<object>
object
id
required

katara/cortex, or an x402-only model: katara/cortex-genius or katara/cortex-smart.

string
object
required
string
Allowed value: model
created
integer
owned_by
required
string
katara
required
object
cortex

True on a row Katara Cortex serves.

boolean
providerClass

routed on a Cortex row: whichever provider or vendor Cortex picks answers.

string
contextLimit
required

Context window in tokens.

integer
capabilities
required
object
workload
string
Allowed values: chat embedding image
tools
boolean
structuredOutputs
boolean
reasoning
boolean
streaming
boolean
vision

Reads image_url parts.

boolean
audio

Reads input_audio parts.

boolean
video

Reads file parts carrying a video.

boolean
documents

Reads file parts carrying a PDF.

boolean
image_generation

Serves /v1/images/generations.

boolean
image_editing

Serves /v1/images/edits.

boolean
maxOutputTokens
integer
tool_contract

Present when tools is true.

object
tool_choice

Accepted tool_choice values.

Array<string>
Allowed values: auto none required named
max_tool_name_length

The longest tool name a candidate takes.

integer
pricing

Cortex’s price ceiling (ceiling), or the price of an x402-only model’s own model (model), in USDC base units (6 decimals) per million tokens.

object
basis
string
Allowed values: ceiling model
input_price_per_mtok
string
output_price_per_mtok
string
currency
string
decimals

The token’s decimals, as a string.

string
image_price

One image at the default size.

string
image_prices

For a model priced by size, the price of one image at each image_size.

object
key
additional properties
string
default_image_size
string
input_image_price

Each picture sent to an edit.

string
max_input_images

The most pictures one edit takes.

integer
billing_methods

Present on the x402-only models: they are sold only per request with x402.

Array<string>
Allowed values: x402
minimum_charge

The least one paid request to an x402-only model costs, in USDC base units.

string
Example
{
  "object": "list",
  "data": [
    {
      "id": "katara/cortex",
      "object": "model",
      "created": 0,
      "owned_by": "katara",
      "katara": {
        "cortex": true,
        "providerClass": "routed",
        "contextLimit": 1048576,
        "capabilities": {
          "workload": "chat",
          "tools": true,
          "structuredOutputs": true,
          "reasoning": true,
          "streaming": true,
          "vision": true,
          "audio": true,
          "video": true,
          "documents": true,
          "maxOutputTokens": 65536,
          "tool_contract": {
            "tool_choice": [
              "auto",
              "none",
              "required",
              "named"
            ]
          }
        },
        "pricing": {
          "input_price_per_mtok": "2400000",
          "output_price_per_mtok": "12000000",
          "currency": "USDC",
          "decimals": "6",
          "basis": "ceiling"
        }
      }
    },
    {
      "id": "katara/cortex-genius",
      "object": "model",
      "created": 0,
      "owned_by": "katara",
      "katara": {
        "cortex": true,
        "providerClass": "routed",
        "contextLimit": 1048576,
        "capabilities": {
          "workload": "chat",
          "tools": true,
          "structuredOutputs": true,
          "reasoning": true,
          "streaming": true,
          "vision": true,
          "audio": true,
          "video": true,
          "documents": true,
          "maxOutputTokens": 65536,
          "tool_contract": {
            "tool_choice": [
              "auto",
              "none",
              "required",
              "named"
            ],
            "max_tool_name_length": 128
          }
        },
        "pricing": {
          "input_price_per_mtok": "2400000",
          "output_price_per_mtok": "12000000",
          "currency": "USDC",
          "decimals": "6",
          "basis": "model"
        },
        "billing_methods": [
          "x402"
        ],
        "minimum_charge": "50000"
      }
    },
    {
      "id": "katara/cortex-smart",
      "object": "model",
      "created": 0,
      "owned_by": "katara",
      "katara": {
        "cortex": true,
        "providerClass": "routed",
        "contextLimit": 1048576,
        "capabilities": {
          "workload": "chat",
          "tools": true,
          "structuredOutputs": true,
          "reasoning": true,
          "streaming": true,
          "vision": true,
          "audio": true,
          "video": true,
          "documents": true,
          "maxOutputTokens": 65536,
          "tool_contract": {
            "tool_choice": [
              "auto",
              "none",
              "required",
              "named"
            ],
            "max_tool_name_length": 128
          }
        },
        "pricing": {
          "input_price_per_mtok": "360000",
          "output_price_per_mtok": "3000000",
          "currency": "USDC",
          "decimals": "6",
          "basis": "model"
        },
        "billing_methods": [
          "x402"
        ],
        "minimum_charge": "10000"
      }
    }
  ]
}