Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.agicto.com/llms.txt

Use this file to discover all available pages before exploring further.

AGICTO API supports text, image, video, audio, embedding, rerank, multimodal, and tool capabilities. Use the live model list to filter models, review pricing, check context length, and copy the model name for API requests.
Use the model list as the source of truth for live models and prices. This page explains how to read the fields and use model names in requests.

​
Model types

TypeUse it forCommon endpoint
TextChat, coding, summarization, translation, classification/v1/chat/completions
ImageImage generation and editing/v1/images/generations
VideoVideo generation jobs/v1/videos or official video endpoints
EmbeddingsRAG, semantic search, recommendations/v1/embeddings
RerankSearch result reranking/v1/rerank
ToolsSearch, hot lists, video parsing, invoice OCR/v1/tool/*

​
Fields to check

FieldHow to use it
Model nameCopy it into the request body as model.
TypeCheck whether it supports text, image, video, embedding, rerank, audio, or tools.
ProviderFilter by providers such as OpenAI, Google, Anthropic, DeepSeek, Doubao, Zhipu, Midjourney, Kling, Vidu, and Xiaomi.
Context lengthUse it to decide whether the model can handle long documents, code, or conversations.
Input priceEstimate the cost of prompts, context, and retrieved content.
Output priceEstimate the cost of generated text, code, or media output.

​
Use a model name

curl https://api.agicto.cn/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "MODEL_NAME",
    "messages": [
      {
        "role": "user",
        "content": "Hello"
      }
    ]
  }'
If a request fails, first check whether the model type matches the endpoint. For example, do not send an image model to /v1/chat/completions.