AI Providers

AI providers are the underlying model vendors powering the platform. The provider is resolved automatically from the selected model — you do not need to specify a provider directly in most API calls.

Endpoints

Method	Path	Description	Auth	Rate Limit
GET	/ai/providers	List available providers	JWT + Entitlement	120/60s (shared global limit)
GET	/ai/providers/:id	Get provider details	JWT + Entitlement	120/60s (shared global limit)

---

Active Providers

Every registered provider is listed, whether or not your plan can use it — check isAccessible, not isActive, to know what you can actually call. isActive describes whether the provider is enabled on the platform at all (true for all of these); isAccessible describes whether your plan grants access to it.

Provider	Key	Accessible on Free plan
Google	google	Yes — always accessible on every plan
OpenAI	openai	No — requires a paid plan with the openai model entitlement
Anthropic	anthropic	No — requires a paid plan with the anthropic model entitlement
Mistral AI	mistral	No — requires a paid plan with the mistral model entitlement
DeepSeek	deepseek	No
Kimi (Moonshot)	kimi	No
Local / Ollama	local	No
SpaceXAI (xAI Grok)	spacexai	No
NVIDIA NIM	nvidia	No

Free plan: only google is accessible. Upgrading grants access to additional providers per your plan's entitlements.

---

GET /ai/providers

List all active AI providers.

Authentication: JWT Bearer token + active AI entitlement required.
Rate limit: 60/min

Request

Query Parameters

Parameter	Type	Required	Description
key	string	No	Filter by provider key (e.g. google)
limit	number	No	Items per page
offset	number	No	Pagination offset

Response

Response Example

{
  "data": [
    {
      "key": "google",
      "displayName": "Google",
      "isActive": true,
      "isAccessible": true,
      "baseUrl": "https://generativelanguage.googleapis.com",
      "docsUrl": "https://ai.google.dev/gemini-api/docs"
    },
    {
      "key": "openai",
      "displayName": "OpenAI",
      "isActive": true,
      "isAccessible": false,
      "baseUrl": "https://api.openai.com/v1",
      "docsUrl": "https://developers.openai.com/api/docs/"
    }
  ],
  "meta": {
    "total": 9,
    "limit": 20,
    "offset": 0,
    "hasNextPage": false
  }
}

Response Fields

Field	Type	Description
key	string	Machine-readable provider key
displayName	string	Display name
isActive	boolean	Whether the provider is enabled on the platform at all — not plan-dependent
isAccessible	boolean	Whether your plan grants access to this provider for chat/AI runs
baseUrl	string | null	The provider's own API base URL
docsUrl	string | null	Link to the provider's own API documentation

Code Examples

cURL

curl https://api.chainabit.com/api/v1/ai/providers \
  -H "Authorization: Bearer $TOKEN"

JavaScript

const res = await fetch(`${BASE_URL}/ai/providers`, {
  headers: { Authorization: `Bearer ${TOKEN}` },
});
const { data } = await res.json();

Python

import requests

res = requests.get(
    f"{BASE_URL}/ai/providers",
    headers={"Authorization": f"Bearer {TOKEN}"},
)
data = res.json()["data"]

---

GET /ai/providers/:id

Get details about a specific provider by its UUID.

Authentication: JWT Bearer token + active AI entitlement required.
Rate limit: 60/min

Request

Path params: id — from a GET /ai/providers response's data[].id. No query parameters.

Response

Response Example

{
  "data": {
    "id": "cm9provider01",
    "key": "google",
    "displayName": "Google",
    "isActive": true,
    "isAccessible": true,
    "baseUrl": "https://generativelanguage.googleapis.com",
    "docsUrl": "https://ai.google.dev/gemini-api/docs",
    "createdAt": "2026-01-01T00:00:00.000Z"
  }
}

Response Fields

Same fields as GET /ai/providers above, plus:

Field	Type	Description
id	string	Provider UUID
createdAt	string	ISO 8601

Code Examples

cURL

curl https://api.chainabit.com/api/v1/ai/providers/<provider-id> \
  -H "Authorization: Bearer $TOKEN"

JavaScript

const res = await fetch(`${BASE_URL}/ai/providers/${providerId}`, {
  headers: { Authorization: `Bearer ${TOKEN}` },
});
const { data } = await res.json();

Python

import requests

res = requests.get(
    f"{BASE_URL}/ai/providers/{provider_id}",
    headers={"Authorization": f"Bearer {TOKEN}"},
)
data = res.json()["data"]

---

Notes

• Every registered provider is returned regardless of your plan — filter by isAccessible on the client side if you only want to show providers the caller can actually use.
• Provider availability (isActive) is managed at the platform level and cannot be changed through the API. Your plan's accessibility (isAccessible) is managed through your subscription.
• To filter models by provider, use the provider query parameter on GET /ai/models.