Skip to main content
GET
/
v1
/
model_apis
/
{model_api_name}
cURL
curl --request GET \
--url https://api.baseten.co/v1/model_apis/{model_api_name} \
--header "Authorization: Bearer $BASETEN_API_KEY"
{
  "name": "<string>",
  "display_name": "<string>",
  "description": "<string>",
  "release_date": "2023-12-25",
  "invoke_url": "<string>",
  "context_length": 123,
  "cost_per_million_input_tokens": "0.13",
  "cost_per_million_output_tokens": "0.50",
  "rate_limits": [
    {
      "threshold": 2
    }
  ],
  "model_family": "META",
  "org_details": {
    "added_at": "2023-11-07T05:31:56Z",
    "last_used_at": "2023-11-07T05:31:56Z"
  }
}

Authorizations

​
Authorization
string
header
required

Pass your Baseten API key. Clients automatically send Authorization: Bearer <key>. Direct callers can also use Authorization: Api-Key <key>; both schemes are accepted.

Path Parameters

​
model_api_name
string
required

Response

200 - application/json

A Model API catalog row, optionally enriched with workspace-specific state.

​
name
string
required

Identifier of the Model API. Stable, URL-safe slug used as the public identifier.

Example:

"llama-3-3-70b-instruct"

​
display_name
string
required

Human-readable name of the Model API.

Example:

"Llama 3.3 70B Instruct"

​
description
string
required

Description of the Model API.

​
release_date
string<date>
required

Date the Model API was made available.

​
invoke_url
string
required

Base URL for invoking the Model API. OpenAI-shaped routes (e.g. /v1/chat/completions) live underneath this host.

Example:

"https://inference.baseten.co"

​
context_length
integer
required

The model's context window length, in tokens.

Example:

8192

​
cost_per_million_input_tokens
required

Cost per million input tokens, in dollars.

Example:

"0.13"

​
cost_per_million_output_tokens
required

Cost per million output tokens, in dollars.

Example:

"0.50"

​
rate_limits
RateLimitV1 · object[]
required

Rate limits in effect for the workspace. Workspace-specific overrides are returned when the workspace has added this Model API and configured them; otherwise the catalog default rate limits are returned.

​
model_family
string | null

Family the underlying model belongs to.

Example:

"META"

​
org_details
ModelAPIOrgDetailsV1 · object

Workspace-specific state. Null when the workspace has not added this Model API.