List models

GET

/models

const url = 'https://api.staging.katara.com/v1/models';
const options = {method: 'GET'};

try {
  const response = await fetch(url, options);
  const data = await response.json();
  console.log(data);
} catch (error) {
  console.error(error);
}

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

Every model the marketplace can serve, with its capabilities and the lowest live price. pricing is absent while no provider is serving the model. The routing model katara/cortex@1 is listed with cortex: true, its candidates, the most conservative capabilities and context of those candidates, and its price ceiling (basis: ceiling).

Responses

200

The model list.

application/json

object

object

required

string

Allowed value: list

data

required

Array<object>

object

required

Model id, katara/<name>@<version>.

string

object

required

string

Allowed value: model

created

integer

owned_by

required

string

katara

required

object

contextLimit

required

Context window in tokens.

integer

capabilities

required

object

workload

string

Allowed values: chat embedding

tools

boolean

structuredOutputs

boolean

reasoning

boolean

streaming

boolean

maxOutputTokens

integer

tool_contract

Present when tools is true. What the model was certified for; a request outside it is refused with feature_not_supported.

object

tool_choice

Accepted tool_choice values.

Array<string>

Allowed values: auto none required named

parallel_tool_calls

boolean

strict_schemas

boolean

tool_streaming

How a call reaches a streaming client.

string

Allowed values: whole-call incremental

max_argument_bytes

Largest argument document certified; 0 = untested.

integer

certified_concurrency

integer

agentic_certified

boolean

metering_version

integer

certification_id

string

pricing

Lowest live offer, in USDC base units (6 decimals) per million tokens. Absent when no provider is serving.

object

input_price_per_mtok

string

output_price_per_mtok

string

Example

{
  "object": "list",
  "data": [
    {
      "id": "katara/llama-3.1-8b-instruct@1",
      "object": "model",
      "created": 0,
      "owned_by": "katara",
      "katara": {
        "contextLimit": 131072,
        "capabilities": {
          "workload": "chat",
          "tools": false,
          "structuredOutputs": false,
          "reasoning": false,
          "streaming": true,
          "maxOutputTokens": 8192
        },
        "pricing": {
          "input_price_per_mtok": "100000",
          "output_price_per_mtok": "300000"
        }
      }
    }
  ]
}