API Overview

The External AI API is a single endpoint that handles discovery (GET) and generation (POST).

Endpoint

https://abzar-ai.com/api/external/ai

Method	Purpose
GET	Return account info, providers, models, token stats, and key limits
POST	Generate text or images
OPTIONS	CORS preflight

CORS

By default, browser CORS is disabled. API keys are intended for server-side use only.

To allow specific browser origins (or all origins), set:

EXTERNAL_AI_CORS_ORIGINS=https://app.example.com,https://admin.example.com
# or
EXTERNAL_AI_CORS_ORIGINS=*

When enabled, responses include:

Access-Control-Allow-Origin: <matched-origin-or-*>
Access-Control-Allow-Methods: GET, POST, OPTIONS
Access-Control-Allow-Headers: Content-Type, Authorization, X-API-Key

Never put pk_ API keys in frontend JavaScript.

Response convention

Successful responses:

{
  "success": true,
  "data": { }
}

Error responses:

{
  "success": false,
  "error": "Human-readable message",
  "details": { }
}

Always check success before reading data.

GET — discover capabilities

curl -X GET "https://abzar-ai.com/api/external/ai" \
  -H "X-API-Key: $ABZAR_AI_API_KEY"

The payload includes:

• user — id, username, display name
• subscription — active plan details
• token_stats — usage, remaining tokens, usage by service
• api_key_info — name, expiry, allowed providers/models, rate limits
• available_providers — providers and chat-capable models, each with an estimated pricing block
• image_generation_providers — providers and image models, each with an estimated pricing block
• pricing_meta — when the estimates above were last refreshed
• supported_features — text_generation, image_generation

Use this endpoint to build dynamic model pickers and to verify remaining quota before expensive jobs.

Per-model pricing

Every model returned under available_providers[].models[] and image_generation_providers[].models[] includes a pricing object so you can show users an approximate Toman cost before they spend tokens:

{
  "id": "clx...",
  "name": "GPT-5",
  "capabilities": { "chat": true, "imageGeneration": false, "imageAnalysis": false, "streaming": false },
  "maxTokens": 8000,
  "pricing": {
    "estimated_cost_toman": 6292,
    "chat_cost_scenarios_toman": { "light": 1200, "typical": 6292, "heavy": 22370 },
    "image_quality_costs_toman": null,
    "price_tier": "expensive"
  }
}

For chat models, chat_cost_scenarios_toman gives three sample costs (light = short message, typical, heavy = long context + max-length answer such as code) — a single number is misleading because cost scales with output length. Image models instead get image_quality_costs_toman (low / medium / high). price_tier (cheap | moderate | expensive) ranks the model relative to other active models of the same type.

These numbers are estimates, not exact bills — the exact amount depends on actual token usage and shifts with the exchange rate over time (see pricing_meta.rate_updated_at). The underlying dollar rate itself is not exposed. pricing is null when the platform’s pricing configuration is incomplete.

POST — generate content

Send a JSON body with at least:

Field	Required	Description
prompt	Yes	Text prompt for generation
model	Yes	Model id or model name
provider	No	Defaults to deepseek
type	No	text (default) or image

See Text Generation, Image Generation, and Parameters & Models for full details.