curl --request PATCH \
--url https://app.thinnest.ai/api/v1/byok \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"enabled": true,
"scope": "voice"
}
'const options = {
method: 'PATCH',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({enabled: true, scope: 'voice'})
};
fetch('https://app.thinnest.ai/api/v1/byok', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));import requests
url = "https://app.thinnest.ai/api/v1/byok"
payload = {
"enabled": True,
"scope": "voice"
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.patch(url, json=payload, headers=headers)
print(response.text){
"enabled": true,
"scope": "all",
"usingScope": "all",
"using": "own",
"complete": true,
"credentials": [
{
"kind": "stt",
"provider": "deepgram",
"label": "Deepgram",
"key": "…k9z2",
"fields": {
"model": "nova-3-general"
},
"model": "nova-3-general",
"models": [
"flux-general-en",
"nova-3-general",
"nova-2-general"
],
"verifiedAt": "2026-10-06T10:00:12.441Z",
"updatedAt": "2026-10-06T10:00:12.441Z"
},
{
"kind": "llm",
"provider": "openai",
"label": "OpenAI",
"key": "…Qw7m",
"fields": {
"model": "gpt-5.4-nano"
},
"model": "gpt-5.4-nano",
"models": [
"gpt-5.4",
"gpt-5.4-mini",
"gpt-5.4-nano"
],
"verifiedAt": "2026-10-06T10:01:40.902Z",
"updatedAt": "2026-10-06T10:01:40.902Z"
},
{
"kind": "tts",
"provider": "elevenlabs",
"label": "ElevenLabs",
"key": "…3c1d",
"fields": {
"model": "eleven_flash_v2_5"
},
"model": "eleven_flash_v2_5",
"models": [
"eleven_flash_v2_5",
"eleven_multilingual_v2"
],
"verifiedAt": "2026-10-06T10:02:05.117Z",
"updatedAt": "2026-10-06T10:02:05.117Z"
}
]
}Turn BYOK On or Off
Switches your workspace onto your own keys, or back onto ours, and/or chooses what you bring (scope). Scope all needs all three keys — speech-to-text, LLM and voice — added, verified and each with a model chosen; scope voice needs only the voice key, and speech-to-text, the LLM and telephony stay ours; scope llm needs only the LLM key, and speech-to-text and the voice stay ours (calls are billed on the normal voice plan, whatever your model); scope llm_voice needs the LLM key and the voice key, and our speech recogniser stays (a call is a flat ₹1/min like all). scope is the default for your agents: any agent may follow it, be switched off, or choose another scope your keys allow (Update Agent byok). Any plan may turn it on. On a developer’s workspace, turning it off turns it off for every customer using your keys, and a customer inherits your scope. Needs a full key.
curl --request PATCH \
--url https://app.thinnest.ai/api/v1/byok \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"enabled": true,
"scope": "voice"
}
'const options = {
method: 'PATCH',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({enabled: true, scope: 'voice'})
};
fetch('https://app.thinnest.ai/api/v1/byok', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));import requests
url = "https://app.thinnest.ai/api/v1/byok"
payload = {
"enabled": True,
"scope": "voice"
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.patch(url, json=payload, headers=headers)
print(response.text){
"enabled": true,
"scope": "all",
"usingScope": "all",
"using": "own",
"complete": true,
"credentials": [
{
"kind": "stt",
"provider": "deepgram",
"label": "Deepgram",
"key": "…k9z2",
"fields": {
"model": "nova-3-general"
},
"model": "nova-3-general",
"models": [
"flux-general-en",
"nova-3-general",
"nova-2-general"
],
"verifiedAt": "2026-10-06T10:00:12.441Z",
"updatedAt": "2026-10-06T10:00:12.441Z"
},
{
"kind": "llm",
"provider": "openai",
"label": "OpenAI",
"key": "…Qw7m",
"fields": {
"model": "gpt-5.4-nano"
},
"model": "gpt-5.4-nano",
"models": [
"gpt-5.4",
"gpt-5.4-mini",
"gpt-5.4-nano"
],
"verifiedAt": "2026-10-06T10:01:40.902Z",
"updatedAt": "2026-10-06T10:01:40.902Z"
},
{
"kind": "tts",
"provider": "elevenlabs",
"label": "ElevenLabs",
"key": "…3c1d",
"fields": {
"model": "eleven_flash_v2_5"
},
"model": "eleven_flash_v2_5",
"models": [
"eleven_flash_v2_5",
"eleven_multilingual_v2"
],
"verifiedAt": "2026-10-06T10:02:05.117Z",
"updatedAt": "2026-10-06T10:02:05.117Z"
}
]
}Authorizations
Headers
Developers only: the customer workspace this request acts in — its org_… id from POST /customers. Leave it out to act in your own workspace. Refused with 404 (Workspace not found.) when the id is unknown, is not one of your customers, or is not an org_… id; 410 when that customer was deleted (restore it with POST /customers/{id}/restore until it is erased); 403 when the key belongs to one customer workspace (it cannot act as another); 400 when your workspace is not a developer workspace. /customers/* and GET /customers/usage are your own workspace's and refuse the header with 400: call them without it.
"org_3fKq9TzQ1mN8vB2xR7cLpA"
Body
Send enabled, scope, or both.
all — all three of your keys; voice — only your voice key; llm — only your language-model key (we keep the speech recogniser and the voice, and calls stay on the normal voice plan); llm_voice — your language-model key and your voice key (we keep the speech recogniser; a flat ₹1/min). Changing it while on needs the new scope's keys complete.
all, voice, llm, llm_voice Response
The workspace's BYOK state after the change.
What this workspace brings: all — speech-to-text, LLM and voice keys (a call is ₹1/min all-in, a chat reply ₹0.02); voice — only the voice key, with our speech-to-text, model and telephony (a call is billed at the voice-only BYOK rate, replies as usual); llm — only the language-model key, with our speech-to-text and voice (a call is billed on the same Premium or Studio voice plan as any call, a chat reply at ₹0.02); llm_voice — the language-model key and the voice key, with our speech recogniser (a call is a flat ₹1/min like all, no model limit, a chat reply at ₹0.02). It is the default for your agents; an agent may choose its own (byok on the agent). all unless changed.
all, voice, llm, llm_voice