Skillget

apiko-ai-api-examples

skill
$ git clone https://github.com/tong0619453646-dev/apiko-ai-api-examples && mkdir -p ~/.claude/skills && cp -r apiko-ai-api-examples/skills/apiko-media ~/.claude/skills/
Guvenlik Denetimi
Basarisiz
Health Uyari
  • No license — Repository has no license file
  • Description — Repository has a description
  • Active repo — Last push 1 days ago
  • Low visibility — Only 0 GitHub stars
Code Basarisiz
  • process.env — Environment variable access in chat.mjs
  • network request — Outbound network request in mcp/src/catalog.ts
  • process.env — Environment variable access in mcp/src/config.ts
  • process.env — Environment variable access in mcp/src/http.ts
  • network request — Outbound network request in mcp/src/http.ts
  • exec() — Shell command execution in mcp/src/pricing.ts
Permissions Gecti
  • Permissions — No dangerous permissions requested

Bu listing icin henuz AI raporu yok.

SUMMARY

Claude Code skill that creates and edits images and videos through APIKO, an OpenAI-compatible AI API (Nano Banana, GPT Image, Seedream, Wan 3.0, Seedance). It submits the async job, polls it, checks the cost first and saves the file.

Set APIKO_API_KEY (create a key at https://apiko.app/), then ask Claude Code for an image or a video. Needs python3; the bundled script uses only the standard library. Model list and prices: https://apiko.app/models
README.md

APIKO: quickstart examples

APIKO is one OpenAI-compatible endpoint for text, image and video models from OpenAI, Anthropic, Google, DeepSeek and more. Create one key, point any OpenAI SDK at https://api.apiko.app/v1, and switch models by changing the model id.

Setup

  1. Create an API key at https://apiko.app/ (pay as you go, credit packs from $5, no subscription).
  2. Export it: export APIKO_API_KEY=sk-...

Examples

  • chat.py: Python, official openai package
  • chat.mjs: Node.js, official openai package
  • chat.sh: plain HTTP with curl

Any model id listed on https://apiko.app/models works, for example gpt-6-astra, claude-sonnet-5-5, gemini-3.5-flash or deepseek-v4-pro.

MCP server for Claude Code, Codex and Cursor

mcp/ is the APIKO MCP server (npm package apiko-mcp). It lets Claude Code, Codex, Cursor, Claude Desktop and other MCP clients find image and video models, quote the cost, generate, and follow the task, all from the chat. Which clients it works with and how to add it to each: mcp/README.md. Overview and prices: APIKO MCP server.

claude mcp add apiko --scope user -e APIKO_API_KEY=sk-... -- npx -y apiko-mcp
codex mcp add apiko --env APIKO_API_KEY=sk-... -- npx -y apiko-mcp

Claude Code skill for images and video

skills/apiko-media/ teaches Claude Code (and other agents that read SKILL.md) to generate images and videos through APIKO: async submit and poll, cost checks before paid jobs, and the billing rules that surprise people, such as Wan reference clips being billed with the output.

mkdir -p ~/.claude/skills && cp -r skills/apiko-media ~/.claude/skills/

LangChain and LlamaIndex

from langchain_openai import ChatOpenAI
llm = ChatOpenAI(model="claude-sonnet-5-5", base_url="https://api.apiko.app/v1", api_key=os.environ["APIKO_API_KEY"])

from llama_index.llms.openai_like import OpenAILike
llm = OpenAILike(model="gemini-3.5-flash", api_base="https://api.apiko.app/v1", api_key=os.environ["APIKO_API_KEY"], is_chat_model=True)

Yorumlar (0)

Sonuc bulunamadi