Reference
GET /v1/models and /v1/status
Three reads that need no key: every model with its price and limits, one model by id, and how each model answered our hourly checks.
Checked 26 October 2026
GET /v1/models
curl https://nokeep.ai/v1/models{
"object": "list",
"data": [{
"id": "deepseek-v4.1-flash-uncensored",
"object": "model",
"owned_by": "nokeep",
"name": "DeepSeek V4.1 Flash Uncensored",
"context_length": 1000000,
"max_output_tokens": 131072,
"input_modalities": ["text", "image"],
"reasoning_efforts": ["none", "low", "high", "max"],
"pricing": {
"prompt": "0.00000045",
"completion": "0.00000175",
"credits_per_million": { "in": 450, "out": 1750 }
}
}]
}pricing.prompt and pricing.completion are US dollars per token, as OpenAI-style catalogs write them.
GET /v1/models/{id}
One model, in the same shape. An id that isn’t ours answers 404 model_not_found.
curl https://nokeep.ai/v1/models/deepseek-v4.1-flash-uncensoredGET /v1/status
Every hour we ask each model one short fixed question. This read says how the last check went and how each of the last 30 days did. The status page draws it.
{
"object": "status",
"checked_every_minutes": 60,
"models": [{
"id": "deepseek-v4.1-flash-uncensored",
"state": "up",
"last_checked_at": "2026-10-26T09:00:00.000Z",
"last_answered_at": "2026-10-26T09:00:00.000Z",
"last_ms": 1100,
"days": [{ "day": "2026-10-26", "checks": 9, "answered": 9, "ms_average": 1040 }]
}]
}state | Means |
|---|---|
up | The last check was answered. |
slow | Answered, but in over 15 seconds. |
busy | The model’s host had no room. Calls get 503 busy; retry. |
down | The last check failed another way. |
unknown | No check has run yet. |