Text Generation

Generate text completions and extract brand styles with AI models.

POST/api/v1/text/generate

Request Body

Parameter	Type	Required	Description
model	string	Yes	Model key (see models below)
prompt	string	No	Text prompt (required for openrouter-completion)
params	object	No	Model-specific parameters
attachmentMediaIds	string[]	No	Positional media attachment IDs

Response

{
  "inferenceJobId": "ij_..."
}

Example

POST/api/v1/text/generate

{
  "model": "openrouter-completion",
  "prompt": "Write a tagline for a sustainable fashion brand",
  "params": {
    "llm": "anthropic/claude-sonnet-4.6",
    "systemPrompt": "You are a creative copywriter specializing in fashion.",
    "reasoningEnabled": true,
    "reasoningEffort": "medium",
    "maxOutputTokens": 4096
  }
}

Models

openrouter-completion

LLM text completion via OpenRouter. Prompt required.

Parameter	Type	Required	Description
llm	string	No	openai/gpt-5.2, openai/gpt-5.1, openai/gpt-5-chat, google/gemini-3-pro-preview, google/gemini-3-flash-preview, anthropic/claude-opus-4.5, anthropic/claude-sonnet-4.5, anthropic/claude-sonnet-4.6, x-ai/grok-4, x-ai/grok-4-fast (default x-ai/grok-4-fast)
systemPrompt	string	No	System prompt to set the LLM persona and behavior
reasoningEnabled	boolean	No	Enable reasoning/chain-of-thought mode
reasoningEffort	string	No	minimal, low, medium, high, xhigh
reasoningMaxTokens	number	No	1024 to 32000
maxOutputTokens	number	No	1024 to 128000

Attachments: Up to 4 optional media attachments.

Available LLMs

Provider	Model
OpenAI	`openai/gpt-5.2`
OpenAI	`openai/gpt-5.1`
OpenAI	`openai/gpt-5-chat`
Google	`google/gemini-3-pro-preview`
Google	`google/gemini-3-flash-preview`
Anthropic	`anthropic/claude-opus-4.5`
Anthropic	`anthropic/claude-sonnet-4.5`
Anthropic	`anthropic/claude-sonnet-4.6`
xAI	`x-ai/grok-4`
xAI	`x-ai/grok-4-fast`

extract-brand-style

Extract brand style attributes from images. Prompt is hardcoded internally.

Params: None.

Attachments: 1 to 8 brand images (first is required).