AxcessAI - One API. Every AI Model.

Quick Start

Getting Your API Key

1Visit the dashboard to create your API key
2Copy your API key and store it safely
3Set the base URL to https://api.axcessai.dev/v1
4Start making requests just like you would with OpenAI

Supported Models & Pricing

AxcessAI supports all major AI models with transparent pricing. Browse the Models page to see all 200+ available models.

Popular Models

GPT-4 Turbo: $10 input / $30 output

Claude 3 Opus: $15 input / $75 output

Gemini Flash: $0.075 input / $0.30 output

GPT-4o Mini: $0.15 input / $0.60 output

Find More

Visit the Models page to filter by provider, pricing, and context length.

Browse All Models

Code Examples

Shell

curl https://api.axcessai.dev/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-4-turbo",
    "messages": [
      {"role": "user", "content": "Hello!"}
    ]
  }'

Base URL Configuration

To use AxcessAI with your existing OpenAI SDK, simply change the base URL:

Default OpenAI

https://api.openai.com/v1

AxcessAI (OpenAI Compatible API)

https://api.axcessai.dev/v1

API Endpoints

Chat Completions

Generate text responses from language models.

POST /v1/chat/completions

{
  "model": "openai/gpt-4-turbo",
  "messages": [
    {"role": "user", "content": "Hello!"}
  ],
  "temperature": 0.7,
  "max_tokens": 2048
}

Image Generation

Generate images from text prompts using DALL-E, Flux, and other models.

POST /v1/images/generations

{
  "model": "openai/dall-e-3",
  "prompt": "A serene landscape with mountains",
  "size": "1024x1024",
  "quality": "standard",
  "n": 1
}

Embeddings

Convert text into embeddings for semantic search and similarity comparison.

POST /v1/embeddings

{
  "model": "openai/text-embedding-3-small",
  "input": "The quick brown fox jumps over the lazy dog"
}

Text-to-Speech

Convert text to audio using various voices and models.

POST /v1/audio/speech

{
  "model": "openai/tts-1",
  "input": "Hello, welcome to AxcessAI!",
  "voice": "nova",
  "response_format": "mp3"
}

API Response Format

AxcessAI returns responses in the exact same format as OpenAI:

{
  "id": "chatcmpl-8mq3m1",
  "object": "chat.completion",
  "created": 1699638019,
  "model": "openai/gpt-4-turbo",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! I'm ready to help."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 10,
    "completion_tokens": 12,
    "total_tokens": 22
  }
}

Authentication & Security

API Key Management

Keep your API key secret and never commit it to version control
Use environment variables to store your API key
Rotate your keys periodically for enhanced security
You can revoke keys anytime from the dashboard
API keys are only shown once at creation—save it immediately

Environment Variable Setup

Node.js / JavaScript

AXCESSAI_API_KEY=sk_your_key_here

Python

export OPENAI_API_KEY=sk_your_key_here

Rate Limiting

Rate Limit Tiers

Limit Type	Value	Description
Hard Limit	60 requests/minute	Maximum requests per minute per API key
Soft Limit	1M tokens/day	Warning issued when approaching this
Timeout	60 seconds	Maximum request duration

Rate Limit Headers: Response headers include X-RateLimit-Limit-Requests and X-RateLimit-Limit-Tokens. Check these to monitor your usage in real-time.

Error Handling

Common Error Codes

Code	Status	Description
invalid_api_key	401	API key is missing or invalid
rate_limit_exceeded	429	Too many requests. Retry after delay
invalid_request_error	400	Request format is invalid
model_not_found	404	Requested model is not available
insufficient_quota	429	Daily token limit exceeded
server_error	500	Internal server error. Retry with backoff

Error Response Format

{
  "error": {
    "type": "invalid_request_error",
    "message": "model parameter is required",
    "param": "model"
  }
}

Usage Tracking & Monitoring

Dashboard Metrics

Your dashboard tracks several key metrics for each API key:

Requests: Total number of API requests made
Tokens: Total input and output tokens used
Last Used: Timestamp of the most recent request
Created: When the API key was generated
Daily Usage: Tracked tokens for the current day

Accessing Usage Info Programmatically

Response headers contain usage information:

X-RateLimit-Limit-Requests: 60
X-RateLimit-Limit-Tokens: 1000000
X-RateLimit-Remaining-Requests: 59
X-RateLimit-Remaining-Tokens: 999988

Best Practices

Request Optimization

Use batch requests when processing multiple inputs to reduce overhead
Choose appropriate models for your use case (cheaper models for simple tasks)
Implement request caching to avoid duplicate API calls
Use streaming for long responses to reduce latency
Set reasonable timeout values (30-60 seconds typical)

Error Recovery

Implement exponential backoff for rate limit errors (429)
Retry failed requests with increased delay between attempts
Log errors for debugging and monitoring purposes
Use circuit breakers to avoid cascading failures
Monitor rate limit headers to proactively manage traffic

Cost Management

Monitor daily token usage to stay within limits
Use the Models page to compare pricing before choosing a model
Create separate API keys for different projects to track costs per project
Set up alerts when approaching daily token limits
Review usage patterns in the dashboard regularly

Troubleshooting

Common Issues & Solutions

401 Unauthorized

Check that you're using the correct API key and it's being passed in the Authorization header as "Bearer YOUR_KEY"

429 Rate Limited

You've exceeded the 60 requests per minute limit. Implement exponential backoff and retry after 1-5 seconds

Invalid Model Error

Check the Models page to see available models and use the exact model name (e.g., "openai/gpt-4-turbo")

Timeout Errors

Requests that take longer than 60 seconds will timeout. Break large requests into smaller chunks or use streaming

CORS Issues

Make requests from the backend, not directly from browser JavaScript. Use a server-side proxy if needed

Documentation