Models and pricing - AGICTO API

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

Type	Use it for	Common endpoint
Text	Chat, coding, summarization, translation, classification	`/v1/chat/completions`
Image	Image generation and editing	`/v1/images/generations`
Video	Video generation jobs	`/v1/videos` or official video endpoints
Embeddings	RAG, semantic search, recommendations	`/v1/embeddings`
Rerank	Search result reranking	`/v1/rerank`
Tools	Search, hot lists, video parsing, invoice OCR	`/v1/tool/*`

Fields to check

Field	How to use it
Model name	Copy it into the request body as `model`.
Type	Check whether it supports text, image, video, embedding, rerank, audio, or tools.
Provider	Filter by providers such as OpenAI, Google, Anthropic, DeepSeek, Doubao, Zhipu, Midjourney, Kling, Vidu, and Xiaomi.
Context length	Use it to decide whether the model can handle long documents, code, or conversations.
Input price	Estimate the cost of prompts, context, and retrieved content.
Output price	Estimate 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.