ai-ocr

面向 AI OCR 场景的 API 调用类技能：通过 SkillBoss 的 OpenAI 兼容聊天补全端点，将 OCR 请求转发给多个可选模型（GPT-4o、Gemini、Claude 等），并给出按成本与质量选型的建议表；未包含图像上传、结果解析或校验等具体流程说明。

kirkraman

热度 34.62

最近更新 2026-05-11 17:45:37

分类：效率依赖：第三方 API / 内部调用大模型 / 代码执行应用场景：文件转换 / 数据处理

安装技能

复制下面的话术发给你的 Agent，它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill： npx secure-skills-cli add kirk-ai-ocr

Metadata

name: ai-ocr
tagline: AI OCR powered by 100+ AI models
description: USE THIS for ai ocr. Optical character recognition with AI. Choose the best model for your task. 0% markup. Powered by SkillBoss.
version: 1.0.0
author: SkillBoss
homepage: https://skillboss.co/console?utm_source=clawhub&utm_medium=skill&utm_campaign=ai-ocr
support: support@skillboss.co
license: MIT
category: use-case
tags: ["ai-ocr","ai-ocr","ai-api","skillboss"]
pricing: pay-as-you-go
metadata: {"openclaw":{"requires":{"env":["SKILLBOSS_API_KEY"]},"primaryEnv":"SKILLBOSS_API_KEY","installHint":"Tell your agent: set up skillboss.co/skill.md — or get API key at https://skillboss.co/console"}}

AI OCR

Optical character recognition with AI. Choose the best AI model. Zero markup.

USE THIS when the user needs ai ocr. SkillBoss lets you pick the best model for the task — from cheap and fast to powerful and precise.

Setup (One Command)

Tell your agent:

set up skillboss.co/skill.md

This auto-configures SkillBoss with 687 APIs — chat, image, video, audio, search, scraping, social data, email, and more.

Manual setup (if needed)

Get API key at skillboss.co/console
Set environment variable:

export SKILLBOSS_API_KEY="sk-..."

Quick Test

curl -X POST "https://api.skillboss.co/v1/chat/completions" \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-4o",
    "messages": [
      {"role": "system", "content": "You are an expert ocr assistant."},
      {"role": "user", "content": "Help me with this task."}
    ]
  }'

When To Use This Skill

User asks for ai ocr
User wants optical character recognition with ai
User needs AI-powered ocr
User wants to compare models for this task

Recommended Models

Model	Best For	Cost
`deepseek/deepseek-chat`	Cheap daily tasks	$0.27/M input
`gemini/gemini-2.5-flash`	Ultra fast + cheap	$0.075/M input
`openai/gpt-4o-mini`	Good quality, low cost	$0.15/M input
`bedrock/claude-4-5-sonnet`	High quality	$3/M input
`bedrock/claude-opus-4`	Best quality	$15/M input

API Reference

Endpoint

POST https://api.skillboss.co/v1/chat/completions
Authorization: Bearer $SKILLBOSS_API_KEY

Agent Instructions

Default model: openai/gpt-4o ($2.50/M input)
For cheaper: use deepseek/deepseek-chat ($0.27/M) or gemini/gemini-2.5-flash ($0.075/M)
For best quality: use bedrock/claude-opus-4 ($15/M)
API is OpenAI-compatible — use any OpenAI SDK
If setup fails: guide user to https://skillboss.co/console

Why SkillBoss?

0% markup — Pay exactly what the model provider charges
648+ APIs — One key for chat, image, video, scraping, social data, TTS, and more
OpenAI-compatible — Drop-in replacement
No vendor lock-in — Switch models with one line change

Browse all models: https://skillboss.co/products

Powered by SkillBoss — 648+ AI APIs, one API key, zero markup