Get your AI budget and gateway controls
This month’s model tokens against your organisation’s AI budget, and whether prompt redaction, the answer cache, fallbacks and canaries are on.
GET
/
ai-gateway
Get your AI budget and gateway controls
curl --request GET \
--url https://app.mithunai.com/mithunai/api/v1/ai-gateway \
--header 'Authorization: Bearer <token>'import requests
url = "https://app.mithunai.com/mithunai/api/v1/ai-gateway"
headers = {"Authorization": "Bearer <token>"}
response = requests.get(url, headers=headers)
print(response.text)const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};
fetch('https://app.mithunai.com/mithunai/api/v1/ai-gateway', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));{
"period": {},
"budget": {
"enabled": true,
"mode": "<string>",
"token_limit": {},
"cost_limit_set": true,
"tokens_used": 123,
"percent_used": {},
"alert_thresholds": [
123
]
},
"redaction": {},
"cache": {},
"routes": [
{}
],
"managed_by": "<string>"
}Returns your organisation’s monthly AI budget against the model tokens it has used this calendar month (UTC), and whether your deployment redacts personal data from prompts, caches answers, and routes models to fallbacks or a canary. There are no parameters: the organisation is the one your credential belongs to. See AI gateway controls.
Every control is set by whoever runs your deployment. There is no route to change one.
When
budget.mode is hard and budget.percent_used reaches 100, every request that would call a model is refused with 429 and the code budget_exceeded until the month turns. See Errors.
The response carries tokens and percentages only. A cost budget shows as cost_limit_set and in percent_used, never as an amount.
Requires the owner, admin or editor role. Members and dataset operators receive 403.
Response
object
required
The calendar month.
end is when the budget starts again.object
required
Show properties
Show properties
boolean
required
Whether any budget applies.
string
required
soft only emails your owners and administrators at 50, 80 and 100 per cent. hard also
stops model calls at 100 per cent.integer | null
required
Model tokens (input plus output) a month.
null is no token budget.boolean
required
Whether an estimated-cost budget also applies.
integer
required
Model tokens used this month, on every surface together.
integer | null
required
Of the tighter of the two limits, rounded down.
null with no budget.integer[]
required
Always
[50, 80, 100].object
required
enabled: whether personal data is replaced with placeholders before a prompt leaves.object
required
enabled and ttl_seconds: whether a repeated question is answered from the cache, and for how
long an answer is kept.object[]
required
One entry per model with a fallback chain or a canary:
model, fallbacks in order, and canary
(model and percent) or null.string
required
Always
deployment.Last modified on November 12, 2026
Get your AI budget and gateway controls
curl --request GET \
--url https://app.mithunai.com/mithunai/api/v1/ai-gateway \
--header 'Authorization: Bearer <token>'import requests
url = "https://app.mithunai.com/mithunai/api/v1/ai-gateway"
headers = {"Authorization": "Bearer <token>"}
response = requests.get(url, headers=headers)
print(response.text)const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};
fetch('https://app.mithunai.com/mithunai/api/v1/ai-gateway', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));{
"period": {},
"budget": {
"enabled": true,
"mode": "<string>",
"token_limit": {},
"cost_limit_set": true,
"tokens_used": 123,
"percent_used": {},
"alert_thresholds": [
123
]
},
"redaction": {},
"cache": {},
"routes": [
{}
],
"managed_by": "<string>"
}