Switch a model
Switch a model’s own switch, by its number such as router@4. On, it answers calls to
that number, loaded and probed first, which takes a place unless it answers already:
past the account’s limit, 409 live_limit lists what answers, and switch_off switches
families or models off in the same step. Off, calls to its number stop, and so does its
own keep warm. With adapter, only while the number names the model the caller saw: 409
model_changed, which also answers when the model, read as on, was switched off before the
switch took hold.
curl --request POST \
--url https://console.sqwish.ai/v1/models/{model}/switch \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"on": true,
"switch_off": [
"<string>"
],
"adapter": "<string>"
}
'import requests
url = "https://console.sqwish.ai/v1/models/{model}/switch"
payload = {
"on": True,
"switch_off": ["<string>"],
"adapter": "<string>"
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({on: true, switch_off: ['<string>'], adapter: '<string>'})
};
fetch('https://console.sqwish.ai/v1/models/{model}/switch', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));{
"id": "<string>",
"status": "<string>",
"evaluation_key": "<string>",
"name": "<string>",
"description": "<string>",
"family": "<string>",
"size_order": 123,
"kind": "<string>",
"lora": "<string>",
"metrics": {},
"max_prompt_tokens": 123,
"max_questions": 123,
"calibration": "<string>",
"availability_reason": "<string>",
"available": true,
"access_requested": true,
"adapter_capacity": {
"max_rank": 123,
"slots": 123
},
"created_at": 123,
"deleted_at": 123,
"discarded_at": 123,
"on_at": 123,
"keep_warm": true,
"keep_warm_window": {
"started_at": 123,
"ends_at": 123,
"reserved_usd": "<string>"
},
"keep_warm_stopped_at": 123,
"used_at": 123,
"switches_off_at": 123,
"off_reason": "owner",
"off_at": 123,
"job_id": "<string>",
"model_name": "<string>",
"version": 123,
"parent": "<string>",
"residency": {
"state": "hot",
"pinned": true
},
"state": "loaded",
"decision_price_nano": "<string>",
"base": "<string>",
"evaluation_set": {
"dataset": {
"id": "<string>",
"name": "<string>",
"archived_at": 123,
"deleted": true
},
"training_examples": 123,
"validation_examples": 123,
"remembered_examples": 123
},
"request_latency": {
"median_ms": 123,
"samples": 123,
"median_is_lower_bound": true,
"start": "<string>",
"end": "<string>"
}
}{
"error": {
"code": "<string>",
"message": "<string>",
"retryable": true,
"request_id": "<string>",
"details": [
{
"path": [
"<string>"
],
"message": "<string>",
"type": "<string>"
}
]
}
}{
"error": {
"code": "<string>",
"message": "<string>",
"retryable": true,
"request_id": "<string>",
"details": [
{
"path": [
"<string>"
],
"message": "<string>",
"type": "<string>"
}
]
}
}Authorizations
Create an API key in the console. Required when accounts are enabled.
Path Parameters
Body
Families, such as router, and models, such as router@2, to switch off in the same step, to make room when switching on would pass the account's limit (live_limit).
20The id of the model the caller saw: refused unless the model called is still that one.
140Response
Successful Response
A base, an early-access catalogue entry, or a trained adapter.
Why it can't answer now: no_engine (its pool has no engine right now), not_served (this server doesn't serve it), or, for an adapter, base_mismatch, engine_unconfigured or engine_changed.
Show child attributes
Show child attributes
When its owner deleted it. A deleted model answers and runs nothing.
When a rollback of its family discarded it. A discarded model answers and runs nothing.
When its own switch went on: it answers calls to its number, such as router@4. Null while it is off.
Whether it is kept warm on its own switch. A family's keep warm doesn't set it: see keep_warm_window.
The hour of keep warm being billed for it, through its family or its own switch, or null when nothing is billed.
Show child attributes
Show child attributes
When its own keep warm switched off because the next hour couldn't be reserved, while it stays off. Otherwise null.
Its idle clock: the latest of its last production call by an API key that named it, its last evaluation that named it, and when it was switched on.
When idling switches it off unless it's used. Null while it is off or kept warm on its own switch, and when idling never switches anything off. A family's is also null while it serves no model.
Why it is off: owner when it was switched off by hand, idle when nothing used it for too long. Null otherwise.
owner, idle When it went off, with off_reason. Null otherwise.
Show child attributes
Show child attributes
loaded, loading, asleep Exact integer string of nano-USD per billed input token from the current billing policy. Zero means free; null means unpriced.
An adapter's base model id: the base whose prices it pays.
Show child attributes
Show child attributes
Show child attributes
Show child attributes
curl --request POST \
--url https://console.sqwish.ai/v1/models/{model}/switch \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"on": true,
"switch_off": [
"<string>"
],
"adapter": "<string>"
}
'import requests
url = "https://console.sqwish.ai/v1/models/{model}/switch"
payload = {
"on": True,
"switch_off": ["<string>"],
"adapter": "<string>"
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({on: true, switch_off: ['<string>'], adapter: '<string>'})
};
fetch('https://console.sqwish.ai/v1/models/{model}/switch', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));{
"id": "<string>",
"status": "<string>",
"evaluation_key": "<string>",
"name": "<string>",
"description": "<string>",
"family": "<string>",
"size_order": 123,
"kind": "<string>",
"lora": "<string>",
"metrics": {},
"max_prompt_tokens": 123,
"max_questions": 123,
"calibration": "<string>",
"availability_reason": "<string>",
"available": true,
"access_requested": true,
"adapter_capacity": {
"max_rank": 123,
"slots": 123
},
"created_at": 123,
"deleted_at": 123,
"discarded_at": 123,
"on_at": 123,
"keep_warm": true,
"keep_warm_window": {
"started_at": 123,
"ends_at": 123,
"reserved_usd": "<string>"
},
"keep_warm_stopped_at": 123,
"used_at": 123,
"switches_off_at": 123,
"off_reason": "owner",
"off_at": 123,
"job_id": "<string>",
"model_name": "<string>",
"version": 123,
"parent": "<string>",
"residency": {
"state": "hot",
"pinned": true
},
"state": "loaded",
"decision_price_nano": "<string>",
"base": "<string>",
"evaluation_set": {
"dataset": {
"id": "<string>",
"name": "<string>",
"archived_at": 123,
"deleted": true
},
"training_examples": 123,
"validation_examples": 123,
"remembered_examples": 123
},
"request_latency": {
"median_ms": 123,
"samples": 123,
"median_is_lower_bound": true,
"start": "<string>",
"end": "<string>"
}
}{
"error": {
"code": "<string>",
"message": "<string>",
"retryable": true,
"request_id": "<string>",
"details": [
{
"path": [
"<string>"
],
"message": "<string>",
"type": "<string>"
}
]
}
}{
"error": {
"code": "<string>",
"message": "<string>",
"retryable": true,
"request_id": "<string>",
"details": [
{
"path": [
"<string>"
],
"message": "<string>",
"type": "<string>"
}
]
}
}