​

Text Models Overview

​

Available Models

​

OpenAI Models

• GPT-5.4: Most capable flagship model with advanced reasoning and agentic capabilities
• GPT-5.2: High-performance model for knowledge work and complex projects
• GPT-4o: Reliable multimodal model for general-purpose tasks
• GPT-4o mini: Fast and cost-effective for lightweight tasks

​

Anthropic Models

• Claude Opus 4.6: Most powerful model for deep reasoning and complex multi-step tasks (1M context)
• Claude Sonnet 4.6: Balanced performance for coding, design, and knowledge work
• Claude Haiku 4.5: Fast and cost-effective for high-volume requests

​

Google Models

• Gemini 3.1 Pro: Advanced reasoning with double the performance of previous generation
• Gemini 3.1 Flash Lite: Ultra-fast and cost-efficient for high-volume workloads
• Gemini 2.5 Pro: Multimodal with 2M token context window

​

Meta Models

• Llama 4 Maverick: Best-in-class open-source multimodal model (128 experts)
• Llama 4 Scout: Efficient model with industry-leading 10M token context window
• Llama 3.3: Proven open-source model for custom deployments

​

DeepSeek Models

• DeepSeek V3: High-performance open-source model for coding and conversation
• DeepSeek R1: Advanced reasoning capabilities on par with top proprietary models

​

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

​

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

​

Common Use Cases

​

Getting Started