API Reference — SkillBoss OpenAI-Compatible API

Base URL

All API requests should be made to:

https://api.skillboss.co/v1

Authentication

SkillBoss uses API keys for authentication. Include your key in the Authorization header:

Authorization: Bearer YOUR_SKILLBOSS_KEY

Two API Endpoints

OpenAI-Compatible Chat API

SkillBoss implements the OpenAI-compatible chat completions API, making it a drop-in replacement for OpenAI's SDK.

Basic Example

curl https://api.skillboss.co/v1/chat/completions \
  -H "Authorization: Bearer YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-4-5-sonnet",
    "messages": [
      {"role": "user", "content": "Hello, how are you?"}
    ],
    "max_tokens": 100
  }'

import requests

response = requests.post(
    "https://api.skillboss.co/v1/chat/completions",
    headers={
        "Authorization": f"Bearer {YOUR_KEY}",
        "Content-Type": "application/json"
    },
    json={
        "model": "claude-4-5-sonnet",
        "messages": [{"role": "user", "content": "Hello"}],
        "max_tokens": 100
    }
)
print(response.json())

import OpenAI from 'openai'

const client = new OpenAI({
  baseURL: 'https://api.skillboss.co/v1',
  apiKey: process.env.SKILLBOSS_KEY
})

const response = await client.chat.completions.create({
  model: 'claude-4-5-sonnet',
  messages: [{role: 'user', content: 'Hello'}],
  max_tokens: 100
})

console.log(response.choices[0].message.content)

Available Models

SkillBoss provides access to 679+ AI endpoints across multiple providers:

Claude (Anthropic)

// Claude 4.5 Sonnet (Latest, most capable)
model: "claude-4-5-sonnet"

// Claude 3.7 Sonnet (Fast, cost-effective)
model: "claude-4-5-sonnet"

// Claude 3.5 Haiku (Ultra-fast, affordable)
model: "claude-3-5-haiku"

GPT (OpenAI)

// GPT-5 (Latest flagship)
model: "gpt-5"

// GPT-4 Turbo
model: "gpt-4-turbo"

// GPT-4o (Optimized)
model: "gpt-4o"

// GPT-4o Mini (Fast & cheap)
model: "gpt-4o-mini"

Gemini (Google)

// Gemini 2.5 Flash (Latest, fast)
model: "gemini-2.5-flash"

// Gemini 2.0 Pro
model: "gemini-2.0-pro"

Other Providers

// DeepSeek V3 (Chinese, excellent for code)
model: "deepseek/deepseek-v3"

// Qwen (Alibaba)
model: "qwen/qwen-max"

// Full list: https://api.skillboss.co/v1/models

curl https://api.skillboss.co/v1/models \
  -H "Authorization: Bearer YOUR_KEY"

Request Parameters

Required

Optional

Advanced Parameters

const stream = await client.chat.completions.create({
  model: 'claude-4-5-sonnet',
  messages: [{role: 'user', content: 'Write a story'}],
  stream: true
})

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content || '')
}

{
  "messages": [
    {"role": "system", "content": "You are a helpful coding assistant."},
    {"role": "user", "content": "Write a Python function"}
  ]
}

{
  "messages": [
    {"role": "user", "content": "What's the capital of France?"},
    {"role": "assistant", "content": "Paris."},
    {"role": "user", "content": "What's its population?"}
  ]
}

Response Format

Standard Response

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1677652288,
  "model": "claude-4-5-sonnet",
  "choices": [{
    "index": 0,
    "message": {
      "role": "assistant",
      "content": "Hello! I'm doing well, thank you for asking."
    },
    "finish_reason": "stop"
  }],
  "usage": {
    "prompt_tokens": 10,
    "completion_tokens": 12,
    "total_tokens": 22
  },
  "_balance_warning": false,
  "_remaining_credits": 1523.45
}

Balance Warning

When your balance drops below 10 credits, responses include a warning:

{
  ...
  "_balance_warning": true,
  "_remaining_credits": 7.23
}

Rate Limits

Error Handling

See the Error Reference for complete error codes and handling strategies.

Common errors:

{
  "error": {
    "message": "Insufficient credits",
    "type": "insufficient_balance",
    "code": "insufficient_balance"
  }
}

SDKs & Libraries

from openai import OpenAI

client = OpenAI(
    base_url="https://api.skillboss.co/v1",
    api_key="YOUR_SKILLBOSS_KEY"
)

Next Steps

/v1/run Endpoint (Non-Chat)

For all non-chat endpoints (images, video, audio, scraping, email, payments):

import requests

response = requests.post(
    "https://api.skillboss.co/v1/run",
    headers={"Authorization": "Bearer YOUR_KEY"},
    json={
        "model": "flux-1.1-pro",          # Model identifier
        "inputs": {                         # Model-specific inputs
            "prompt": "A sunset over mountains"
        }
    }
)
result = response.json()

Popular /v1/run Models

See the public discovery hub for all 679+ endpoints.

Agent-Readable API Summary:

{
  "base_url": "https://api.skillboss.co/v1",
  "auth": "Bearer <api_key>",
  "endpoints": {
    "/v1/chat/completions": {"method": "POST", "use_for": "chat_and_llm_models"},
    "/v1/run": {"method": "POST", "use_for": "images_video_audio_scraping_email_payments"},
    "/v1/models": {"method": "GET", "use_for": "list_all_available_models"}
  },
  "compatibility": "OpenAI SDK",
  "streaming": true,
  "function_calling": true,
  "total_endpoints": 679
}