curl --request PUT \
--url https://app.thinnest.ai/api/v1/byok/credentials \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"kind": "llm",
"provider": "openai",
"credentials": {
"apiKey": "sk-proj-4fT9xQ2mLr8Vw1Zc7Kb3Nh6Yd0Pe5Gs9Qw7m",
"model": "gpt-5.4-mini"
}
}
'{
"kind": "llm",
"provider": "openai",
"label": "OpenAI",
"key": "…Qw7m",
"fields": {
"model": "gpt-5.4-mini"
},
"model": "gpt-5.4-mini",
"models": [
"gpt-5.4",
"gpt-5.4-mini",
"gpt-5.4-nano",
"gpt-4.1-mini"
],
"verifiedAt": "2026-10-06T10:01:40.902Z",
"updatedAt": "2026-10-06T10:01:40.902Z"
}Add BYOK Key
Adds or replaces your key for one job. The key is checked with the provider before anything is stored — a key the provider rejects is not saved — then stored encrypted and only ever shown by its last four characters. The provider’s model list is pulled at the same time. Without credentials.model, a speech key starts on the provider’s usual model and an LLM key on its usual one where it has one; replacing a key with one for the same provider keeps the model already chosen. Needs a full key.
curl --request PUT \
--url https://app.thinnest.ai/api/v1/byok/credentials \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"kind": "llm",
"provider": "openai",
"credentials": {
"apiKey": "sk-proj-4fT9xQ2mLr8Vw1Zc7Kb3Nh6Yd0Pe5Gs9Qw7m",
"model": "gpt-5.4-mini"
}
}
'{
"kind": "llm",
"provider": "openai",
"label": "OpenAI",
"key": "…Qw7m",
"fields": {
"model": "gpt-5.4-mini"
},
"model": "gpt-5.4-mini",
"models": [
"gpt-5.4",
"gpt-5.4-mini",
"gpt-5.4-nano",
"gpt-4.1-mini"
],
"verifiedAt": "2026-10-06T10:01:40.902Z",
"updatedAt": "2026-10-06T10:01:40.902Z"
}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
Who does the job. Speech-to-text: deepgram, assemblyai, soniox, speechmatics, gladia, sarvam, elevenlabs, cartesia, openai, groq, mistral, azure. LLM: openai, anthropic, google, groq, mistral, sarvam, deepseek, xai, together, fireworks, cerebras, openrouter, openai_compatible. Voice: deepgram, elevenlabs, cartesia, openai, sarvam, soniox, mistral, azure, rime, inworld, hume, murf, speechify. A provider that does not do the job is refused with the list that does.
deepgram, assemblyai, soniox, speechmatics, gladia, sarvam, elevenlabs, cartesia, openai, groq, mistral, azure, rime, inworld, hume, murf, speechify, anthropic, google, deepseek, xai, together, fireworks, cerebras, openrouter, openai_compatible Response
The key as stored, masked.
One of your own provider keys, masked.