curl "https://api.telzino.com/v1/llm-models" \
-H "Authorization: Bearer YOUR_ACCESS_TOKEN"
curl "https://api.telzino.com/v1/llm-models?organization_id=ORG_UUID" \
-H "Authorization: Bearer YOUR_ACCESS_TOKEN"
const response = await fetch('https://api.telzino.com/v1/llm-models', {
headers: { 'Authorization': 'Bearer YOUR_ACCESS_TOKEN' }
});
const { data } = await response.json();
console.log(data); // [{ id: 'gpt-4.1', name: 'GPT-4.1', ... }]
import requests
response = requests.get(
'https://api.telzino.com/v1/llm-models',
headers={'Authorization': 'Bearer YOUR_ACCESS_TOKEN'}
)
models = response.json()['data']
{
"data": [
{
"id": "gpt-4.1",
"name": "GPT-4.1",
"description": "OpenAI's recommended default model",
"provider": "openai"
},
{
"id": "gpt-4o",
"name": "GPT-4o",
"description": "OpenAI's multimodal model",
"provider": "openai"
},
{
"id": "gpt-4o-mini",
"name": "GPT-4o Mini",
"description": "Fast, cost-effective OpenAI model",
"provider": "openai"
},
{
"id": "gpt-4.1-mini",
"name": "GPT-4.1 Mini",
"description": "Faster, more cost-effective OpenAI model",
"provider": "openai"
},
{
"id": "gpt-4.1-nano",
"name": "GPT-4.1 Nano",
"description": "OpenAI's smallest, fastest model",
"provider": "openai"
},
{
"id": "grok-3-fast",
"name": "Grok-3 Fast",
"description": "xAI's Grok-3 Fast model",
"provider": "xai"
},
{
"id": "moonshotai/Kimi-K2.6",
"name": "Kimi K2.6",
"description": "Moonshot AI's Kimi model, served via Telnyx",
"provider": "moonshot"
},
{
"id": "claude-sonnet-4-6",
"name": "Claude Sonnet",
"description": "Anthropic's Claude Sonnet model",
"provider": "anthropic"
},
{
"id": "google/gemma-4-31b-it",
"name": "Gemma 4 31B",
"description": "Google's Gemma 4, served via LiveKit Inference",
"provider": "livekit"
}
]
}
{
"error": "unauthorized",
"error_description": "User payload not found"
}
{
"error": "not_found",
"error_description": "Resource not found or access denied"
}
LLM Models
List LLM Models
Returns a list of available LLM models that can be used when creating or updating agents
GET
/
v1
/
llm-models
curl "https://api.telzino.com/v1/llm-models" \
-H "Authorization: Bearer YOUR_ACCESS_TOKEN"
curl "https://api.telzino.com/v1/llm-models?organization_id=ORG_UUID" \
-H "Authorization: Bearer YOUR_ACCESS_TOKEN"
const response = await fetch('https://api.telzino.com/v1/llm-models', {
headers: { 'Authorization': 'Bearer YOUR_ACCESS_TOKEN' }
});
const { data } = await response.json();
console.log(data); // [{ id: 'gpt-4.1', name: 'GPT-4.1', ... }]
import requests
response = requests.get(
'https://api.telzino.com/v1/llm-models',
headers={'Authorization': 'Bearer YOUR_ACCESS_TOKEN'}
)
models = response.json()['data']
{
"data": [
{
"id": "gpt-4.1",
"name": "GPT-4.1",
"description": "OpenAI's recommended default model",
"provider": "openai"
},
{
"id": "gpt-4o",
"name": "GPT-4o",
"description": "OpenAI's multimodal model",
"provider": "openai"
},
{
"id": "gpt-4o-mini",
"name": "GPT-4o Mini",
"description": "Fast, cost-effective OpenAI model",
"provider": "openai"
},
{
"id": "gpt-4.1-mini",
"name": "GPT-4.1 Mini",
"description": "Faster, more cost-effective OpenAI model",
"provider": "openai"
},
{
"id": "gpt-4.1-nano",
"name": "GPT-4.1 Nano",
"description": "OpenAI's smallest, fastest model",
"provider": "openai"
},
{
"id": "grok-3-fast",
"name": "Grok-3 Fast",
"description": "xAI's Grok-3 Fast model",
"provider": "xai"
},
{
"id": "moonshotai/Kimi-K2.6",
"name": "Kimi K2.6",
"description": "Moonshot AI's Kimi model, served via Telnyx",
"provider": "moonshot"
},
{
"id": "claude-sonnet-4-6",
"name": "Claude Sonnet",
"description": "Anthropic's Claude Sonnet model",
"provider": "anthropic"
},
{
"id": "google/gemma-4-31b-it",
"name": "Gemma 4 31B",
"description": "Google's Gemma 4, served via LiveKit Inference",
"provider": "livekit"
}
]
}
{
"error": "unauthorized",
"error_description": "User payload not found"
}
{
"error": "not_found",
"error_description": "Resource not found or access denied"
}
Use this endpoint to discover valid values for the
model field when creating or updating agents.
The list returned is filtered by Feature Administration:
a Partner or Reseller can lock individual models for the organizations beneath them, and a
locked model is omitted. gpt-4.1 — the default model for a newly created agent — is the one model that
can never be locked, so it is always present in the response.
Query Parameters
string
Optional. Scope the catalogue to exactly what this organization may use, applying its
account, reseller and org-level Feature Administration locks. Without this parameter the
response reflects only account-level locks — the coarsest honest answer, since the token
identifies an account, not an organization — so a model locked for one organization
under the account may still appear here.The organization must belong to the authenticated account, or the request is rejected
with
404.curl "https://api.telzino.com/v1/llm-models" \
-H "Authorization: Bearer YOUR_ACCESS_TOKEN"
curl "https://api.telzino.com/v1/llm-models?organization_id=ORG_UUID" \
-H "Authorization: Bearer YOUR_ACCESS_TOKEN"
const response = await fetch('https://api.telzino.com/v1/llm-models', {
headers: { 'Authorization': 'Bearer YOUR_ACCESS_TOKEN' }
});
const { data } = await response.json();
console.log(data); // [{ id: 'gpt-4.1', name: 'GPT-4.1', ... }]
import requests
response = requests.get(
'https://api.telzino.com/v1/llm-models',
headers={'Authorization': 'Bearer YOUR_ACCESS_TOKEN'}
)
models = response.json()['data']
{
"data": [
{
"id": "gpt-4.1",
"name": "GPT-4.1",
"description": "OpenAI's recommended default model",
"provider": "openai"
},
{
"id": "gpt-4o",
"name": "GPT-4o",
"description": "OpenAI's multimodal model",
"provider": "openai"
},
{
"id": "gpt-4o-mini",
"name": "GPT-4o Mini",
"description": "Fast, cost-effective OpenAI model",
"provider": "openai"
},
{
"id": "gpt-4.1-mini",
"name": "GPT-4.1 Mini",
"description": "Faster, more cost-effective OpenAI model",
"provider": "openai"
},
{
"id": "gpt-4.1-nano",
"name": "GPT-4.1 Nano",
"description": "OpenAI's smallest, fastest model",
"provider": "openai"
},
{
"id": "grok-3-fast",
"name": "Grok-3 Fast",
"description": "xAI's Grok-3 Fast model",
"provider": "xai"
},
{
"id": "moonshotai/Kimi-K2.6",
"name": "Kimi K2.6",
"description": "Moonshot AI's Kimi model, served via Telnyx",
"provider": "moonshot"
},
{
"id": "claude-sonnet-4-6",
"name": "Claude Sonnet",
"description": "Anthropic's Claude Sonnet model",
"provider": "anthropic"
},
{
"id": "google/gemma-4-31b-it",
"name": "Gemma 4 31B",
"description": "Google's Gemma 4, served via LiveKit Inference",
"provider": "livekit"
}
]
}
{
"error": "unauthorized",
"error_description": "User payload not found"
}
{
"error": "not_found",
"error_description": "Resource not found or access denied"
}
Response Fields
| Field | Type | Description |
|---|---|---|
id | string | Model identifier — use this as the model value when creating or updating agents |
name | string | Display name of the model |
description | string | Brief description of the model |
provider | string | Underlying provider: openai, xai, moonshot, anthropic, or livekit |
Errors
| Status | Meaning |
|---|---|
401 | Missing or invalid access token |
404 | organization_id was supplied but does not belong to the authenticated account |
