/v1/plan
Details of your active plan, including context length and model size limits.
/v1/plan
The plan endpoint returns the details of the plan your API key is subscribed to. The /v1/models endpoint reports each model's maximum context length on Featherless, which is not necessarily the limit your plan allows. Use this endpoint to learn your plan-level limits: your effective context ceiling for a model is the smaller of the model's context length and your plan's max_context_length.
HTTP request
GET https://api.featherless.ai/v1/plan
This endpoint requires authentication with your API key.
Response body
A successful request returns one plan object, based on the API key used. Examples for Chat and Developer are shown below. The Developer credit balance is illustrative; your balance will vary.
{
"id": "feather_pro_plus",
"name": "Feather Chat (formerly Premium)",
"max_context_length": 49152,
"max_model_size": null,
"concurrency": 4,
"api_access": true,
"credits": null
}{
"id": "feather_request_pricing",
"name": "Request Pricing",
"max_context_length": null,
"max_model_size": null,
"concurrency": 100,
"api_access": true,
"credits": "50.00"
}max_context_length is the maximum number of tokens (prompt plus completion) your plan allows per request, in tokens. A value of null means your plan imposes no cap of its own and each model's full context length applies.
max_model_size is the largest model your plan can access, in billions of parameters. A value of null means there is no model size limit.
concurrency is the number of concurrent requests your plan allows. See the concurrency article for how concurrent units are counted.