AI Models

Browse available AI models and their capabilities. Currently, only Google Gemini models are active and available to users.

Endpoints

Method	Path	Description	Auth	Rate Limit
GET	/ai/models	List available models	JWT + Entitlement	60/min
GET	/ai/models/:id	Get model details	JWT + Entitlement	60/min

---

Active Models

8 Gemini models are currently available:

Model	Input Cost/1K Tokens	Output Cost/1K Tokens
gemini-2.5-pro	$0.00125	$0.01000
gemini-2.5-flash	$0.00030	$0.00250
gemini-2.5-flash-lite	$0.00010	$0.00040
gemini-2.0-flash	$0.00010	$0.00040
gemini-3-pro-preview	$0.00200	$0.01200
gemini-3-flash-preview	$0.00050	$0.00300
gemini-3.1-pro-preview	$0.00200	$0.01200
gemini-3.1-flash-lite-preview	$0.00025	$0.00150

Switching between models requires a Bitter+ tier subscription or higher.

---

GET /ai/models

List all available AI models.

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

Request

Query Parameters

Parameter	Type	Required	Description
name	string	No	Filter by model name
provider	string	No	Filter by provider (e.g. google)
isActive	boolean	No	Filter by active status
minCostPer1kTokens	number	No	Minimum cost filter
maxCostPer1kTokens	number	No	Maximum cost filter
limit	number	No	Items per page
offset	number	No	Pagination offset

Response

Response Example

{
  "data": [
    {
      "modelKey": "gemini-2.5-pro",
      "name": "Gemini 2.5 Pro",
      "provider": "google",
      "capabilities": ["chat", "analysis", "reasoning", "vision"],
      "costPer1kTokens": 0.00125,
      "active": true
    },
    {
      "modelKey": "gemini-2.5-flash",
      "name": "Gemini 2.5 Flash",
      "provider": "google",
      "capabilities": ["chat", "analysis", "reasoning"],
      "costPer1kTokens": 0.00030,
      "active": true
    },
    {
      "modelKey": "gemini-2.5-flash-lite",
      "name": "Gemini 2.5 Flash Lite",
      "provider": "google",
      "capabilities": ["chat", "summarization"],
      "costPer1kTokens": 0.00010,
      "active": true
    },
    {
      "modelKey": "gemini-2.0-flash",
      "name": "Gemini 2.0 Flash",
      "provider": "google",
      "capabilities": ["chat", "summarization"],
      "costPer1kTokens": 0.00010,
      "active": true
    },
    {
      "modelKey": "gemini-3-pro-preview",
      "name": "Gemini 3 Pro (Preview)",
      "provider": "google",
      "capabilities": ["chat", "analysis", "reasoning", "vision"],
      "costPer1kTokens": 0.00200,
      "active": true
    },
    {
      "modelKey": "gemini-3-flash-preview",
      "name": "Gemini 3 Flash (Preview)",
      "provider": "google",
      "capabilities": ["chat", "analysis", "reasoning"],
      "costPer1kTokens": 0.00050,
      "active": true
    },
    {
      "modelKey": "gemini-3.1-pro-preview",
      "name": "Gemini 3.1 Pro (Preview)",
      "provider": "google",
      "capabilities": ["chat", "analysis", "reasoning", "vision"],
      "costPer1kTokens": 0.00200,
      "active": true
    },
    {
      "modelKey": "gemini-3.1-flash-lite-preview",
      "name": "Gemini 3.1 Flash Lite (Preview)",
      "provider": "google",
      "capabilities": ["chat", "summarization"],
      "costPer1kTokens": 0.00025,
      "active": true
    }
  ],
  "meta": {
    "total": 8,
    "limit": 20,
    "offset": 0
  }
}

Response Fields

Field	Type	Description
modelKey	string	Machine-readable model key
name	string	Display name
provider	string	Provider name
capabilities	string[]	Supported capabilities
costPer1kTokens	number	Cost in USD per 1,000 input tokens
active	boolean	Whether the model is currently available

Code Examples

cURL

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

JavaScript

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

Python

import requests

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

---

GET /ai/models/:id

Get detailed information about a specific model, including pricing.

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

Request

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

Response

Response Example

{
  "data": {
    "id": "cm8model01",
    "modelKey": "gemini-2.5-pro",
    "name": "Gemini 2.5 Pro",
    "provider": "google",
    "capabilities": ["chat", "analysis", "reasoning", "vision"],
    "maxTokens": 8192,
    "contextWindow": 1048576,
    "costPerInputToken": 0.00000125,
    "costPerOutputToken": 0.00001000,
    "active": true,
    "createdAt": "2026-03-01T00:00:00.000Z"
  }
}

Response Fields

Field	Type	Description
id	string	Model ID
modelKey	string	Machine-readable model key
name	string	Model name
provider	string	Underlying provider
capabilities	string[]	Supported capabilities
maxTokens	number	Maximum output tokens
contextWindow	number	Context window size in tokens
costPerInputToken	number	Cost per input token (USD)
costPerOutputToken	number	Cost per output token (USD)
active	boolean	Whether the model is currently available
createdAt	string	ISO 8601

Code Examples

cURL

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

JavaScript

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

Python

import requests

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

---

Notes

• Only active models are returned by default. Pass isActive=false to include inactive models (none currently exposed to users).
• Model switching between different capability tiers requires a Bitter+ subscription or higher.
• AI operations consume credits from your wallet. Credit costs are derived from the model's USD pricing with a platform margin applied.
• Preview models (*-preview) may be updated or replaced without notice.