Parameters & Models

Complete reference for request fields and model selection.

Common parameters

| Parameter | Required | Type | Default | Description | | — | — | — | — | | prompt | Yes | string | — | Generation prompt | | model | Yes | string | — | Model id or model name | | provider | No | string | deepseek | Provider identifier | | type | No | string | text | text or image |

The API resolves model by name first, then by id. Prefer the exact names returned by GET /api/external/ai.

Text parameters

| Parameter | Type | Default | Description | | — | — | — | | max_tokens | number | 2000 | Maximum tokens to generate | | temperature | number | 0.7 | Creativity / randomness (0.0–2.0) |

Image parameters

| Parameter | Type | Default | Description | | — | — | — | | size | string | 1024x1024 | 1024x1024, 1792x1024, 1024x1792 | | quality | string | standard | standard or hd | | style | string | — | vivid or natural when supported |

Supported model families

Available models depend on your plan, API key restrictions, and live provider configuration. Always discover the current list with:

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

Typical families include:

Text / chat

Provider	Example models	Best for
DeepSeek	deepseek-chat, deepseek-coder	General chat, coding
OpenAI	gpt-4, gpt-4-turbo, gpt-3.5-turbo	Complex reasoning, versatile tasks
Other configured providers	See GET response	Depends on account setup

Image

Provider	Example models	Notes
OpenAI	dall-e-3, dall-e-2	Size / quality / style options
Other image providers	See image_generation_providers	Capability flags in GET response

Capability flags

Each model in the GET response includes:

{
  "id": "...",
  "name": "...",
  "capabilities": {
    "chat": true,
    "imageGeneration": false,
    "imageAnalysis": false,
    "streaming": true
  },
  "maxTokens": 8192
}

Use these flags to filter UI options instead of hard-coding model lists.

Token costs

Token deduction is calculated from the selected model and request type:

• Text requests use input/output token pricing
• Image requests use the model’s image cost configuration

If pricing configuration is unavailable, the API returns 503 rather than guessing a cost.

Choosing a model

1. Call GET /api/external/ai
2. Filter by capabilities.chat or capabilities.imageGeneration
3. Respect api_key_info.allowed_providers and allowed_models
4. Pass the chosen model (and provider) on POST