​

Text Models Overview

​

Available Models

​

OpenAI Models

• GPT-4o: Latest multimodal model with advanced reasoning
• GPT-4o-mini: Fast and cost-effective version of GPT-4o
• GPT-4 Turbo: High-performance model with large context window
• GPT-3.5 Turbo: Reliable and efficient for most tasks

​

Anthropic Models

• Claude 3.5 Sonnet: Most capable model with excellent reasoning
• Claude 3.5 Haiku: Fast and economical for simple tasks
• Claude 3 Opus: Powerful model for complex analysis

​

Google Models

• Gemini 2.5 Pro: Advanced model with 2M token context
• Gemini 1.5 Pro: Multimodal with long context capabilities
• Gemini 1.5 Flash: Fast model optimized for speed

​

Meta Models

• Llama 3.3: Latest open-source model from Meta
• Llama 3.1: High-performance open model
• Code Llama: Specialized for code generation

​

Model Capabilities

​

Chat Completions API

POST /v1/chat/completions

​

Basic Example

curl -X POST "https://api.anyapi.ai/v1/chat/completions" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "messages": [
      {"role": "user", "content": "Explain quantum computing"}
    ]
  }'

​

Message Roles

• system: Sets the behavior and context for the assistant
• user: Messages from the human user
• assistant: Previous responses from the AI model

{
  "messages": [
    {"role": "system", "content": "You are a helpful coding assistant."},
    {"role": "user", "content": "Write a Python function to sort a list"},
    {"role": "assistant", "content": "Here's a Python function to sort a list..."},
    {"role": "user", "content": "Now make it work with custom comparisons"}
  ]
}

​

Advanced Features

​

Streaming Responses

const response = await fetch('/v1/chat/completions', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    model: 'gpt-4o',
    messages: [{role: 'user', content: 'Tell me a story'}],
    stream: true
  })
});

const reader = response.body.getReader();
const decoder = new TextDecoder();

while (true) {
  const {value, done} = await reader.read();
  if (done) break;
  
  const chunk = decoder.decode(value);
  console.log(chunk);
}

​

Function Calling

{
  "model": "gpt-4o",
  "messages": [
    {"role": "user", "content": "What's the weather in San Francisco?"}
  ],
  "functions": [
    {
      "name": "get_weather",
      "description": "Get the current weather in a location",
      "parameters": {
        "type": "object",
        "properties": {
          "location": {
            "type": "string",
            "description": "City and state, e.g. San Francisco, CA"
          }
        },
        "required": ["location"]
      }
    }
  ]
}

​

JSON Mode

{
  "model": "gpt-4o",
  "messages": [
    {"role": "user", "content": "Extract the key information from this text as JSON"}
  ],
  "response_format": {"type": "json_object"}
}

​

Model Comparison

​

Pricing

• Input tokens: Text you send to the model
• Output tokens: Text the model generates
• Different rates: Input vs output pricing varies by model

​

Best Practices

​

Performance Optimization

• Use system messages to set context once
• Keep conversations focused and relevant
• Choose the right model for your use case
• Implement proper error handling

​

Cost Optimization

• Use smaller models for simple tasks
• Implement response caching
• Set reasonable max_tokens limits
• Monitor usage with our dashboard

​

Quality Improvement

• Provide clear, specific instructions
• Use examples in your prompts
• Iterate on prompt design
• Test with different models

​

Rate Limits

​

Common Use Cases

​

Getting Started