Skip to main content

​
Live Models Data

The models catalog is dynamically updated. Visit our dashboard for real-time pricing and availability.

​
Model Selection Guide

​
By Use Case

Fast Responses

gpt-5-mini, gpt-4o-mini, gemini-2.0-flash-001, gpt-3.5-turbo

Complex Reasoning

gpt-5, claude-opus-4-1-20250805, gemini-2.5-pro

Cost-Effective

gpt-4o-mini, gemini-2.0-flash-001

Large Context

gpt-4.1 (1M+), gemini-2.5-pro (1M+)

Vision Tasks

gpt-5, gpt-4o, claude-sonnet-4, gemini models

Code Generation

gpt-5, claude-3.7-sonnet, gpt-4o

​
By Budget

Economy

Models: gpt-4o-mini, gemini-2.0-flash-001Use Cases: Prototyping, simple tasks, testingCost: Most affordable option for high-volume usage

Standard

Models: gpt-5-mini, claude-3.5-sonnetUse Cases: Production apps, chatbots, customer serviceCost: Balanced performance and pricing

Premium

Models: gpt-5, claude-sonnet-4Use Cases: Advanced reasoning, complex analysis, researchCost: Higher tier for demanding applications

Enterprise

Models: claude-opus-4-1-20250805, gpt-4.1Use Cases: Critical applications, advanced research, maximum capabilityCost: Premium pricing for best-in-class performance

​
Using Models in Code

Always use the model ID when making API calls: 
from openai import OpenAI

client = OpenAI(
    base_url="https://ai.megallm.io/v1",
    api_key="your-api-key"
)

# Use model ID, not display name
response = client.chat.completions.create(
    model="gpt-5",  # Model ID
    messages=[{"role": "user", "content": "Hello!"}]
)

# Switch to Claude using model ID
response = client.chat.completions.create(
    model="claude-opus-4-1-20250805",  # Model ID
    messages=[{"role": "user", "content": "Hello!"}]
)

# Try Gemini using model ID
response = client.chat.completions.create(
    model="gemini-2.5-pro",  # Model ID
    messages=[{"role": "user", "content": "Hello!"}]
)

​
Automatic Fallback

Configure automatic fallback using model IDs: 
response = client.chat.completions.create(
    model="gpt-5",
    messages=messages,
    fallback_models=["claude-opus-4-1-20250805", "gemini-2.5-pro"],
    fallback_on_rate_limit=True,
    fallback_on_error=True
)

​
Pricing Calculator

Estimate your costs across different models:
Usage LevelTokens/Monthgpt-5-miniclaude-3.5-sonnetgemini-2.0-flash-001
Hobby1M$2.25$18$0.75
Startup10M$22.50$180$7.50
Business100M$225$1,800$75
Enterprise1B+CustomCustomCustom
Important: Model IDs are case-sensitive. Always use the exact model ID as shown in the tables above.

​
Next Steps

  • Read the FAQ for common questions about model selection
  • Check out the API Reference for detailed endpoint documentation
  • View Developer Docs for integration guides