Available Models & Pricing

Complete list of AI models available through Tokenlio with transparent pricing.

INFO

Prices shown are in USD per 1 million tokens. Actual pricing may vary. Check the public API endpoint for current rates.

Model Categories

Models available through Tokenlio span multiple providers and use cases.

Chat Completion Models

Conversational AI for text generation:

OpenAI: GPT-4 Turbo, GPT-4, GPT-3.5 Turbo
Anthropic: Claude 3.5 Sonnet, Claude 3 Opus, Claude 3 Sonnet, Claude 3 Haiku
Google: Gemini 1.5 Pro, Gemini 1.5 Flash, Gemini 1.0 Pro

Pricing Structure

Tokenlio uses transparent per-token pricing:

Input tokens: Your prompts and conversation context
Output tokens: Generated responses
No hidden fees: What you see is what you pay
Real-time tracking: Monitor usage in the console

Example Pricing

Typical models pricing (reference only, check API for current rates):

GPT-4 Turbo:

Input: ~$10 per 1M tokens
Output: ~$30 per 1M tokens

GPT-3.5 Turbo:

Input: ~$0.50 per 1M tokens
Output: ~$1.50 per 1M tokens

Claude 3.5 Sonnet:

Input: ~$3 per 1M tokens
Output: ~$15 per 1M tokens

Claude 3 Haiku:

Input: ~$0.25 per 1M tokens
Output: ~$1.25 per 1M tokens

Gemini 1.5 Pro:

Input: ~$1.25 per 1M tokens
Output: ~$5 per 1M tokens

Gemini 1.5 Flash:

Input: ~$0.075 per 1M tokens
Output: ~$0.30 per 1M tokens

WARNING

Prices shown are approximate and for reference only. Use the public models API endpoint to fetch current pricing programmatically, or check the console for the latest rates.

Model Selection Guide

By Use Case

Creative Writing: GPT-4, Claude 3 Opus

High-quality, nuanced content
Character consistency
Complex narratives

Code Generation: GPT-4 Turbo, Claude 3.5 Sonnet

Accurate syntax
Good at debugging
Multi-language support

Data Analysis: GPT-4 Turbo, Claude 3.5 Sonnet

Complex reasoning
Pattern recognition
Detailed explanations

Customer Support: GPT-3.5 Turbo, Claude 3 Haiku

Fast responses
Cost-effective at scale
Handles common queries

Document Processing: Gemini 1.5 Pro, Claude 3 models

Long context windows
Comprehensive analysis
Multi-format support

Rapid Prototyping: GPT-3.5 Turbo, Gemini 1.5 Flash

Quick iterations
Low cost per request
Good for testing

By Context Length

Huge (200K+ tokens):

Claude 3 models (200K)
Gemini 1.5 models (1M)

Large (32K-128K tokens):

GPT-4 Turbo (128K)
GPT-4-32K (32K)

Standard (8K-16K tokens):

GPT-4 (8K)
GPT-3.5 Turbo (16K)

Getting Current Pricing

Via Public API

Fetch live pricing without authentication:

bash

curl https://api.tokenlio.ai/api/v1/public/models

Returns JSON with current pricing, savings percentages, and model capabilities.

Via Console

Current pricing for all models
Your workspace's available models
Usage costs and projections

Model Identifiers

Use these identifiers in API requests:

OpenAI

gpt-4-turbo
gpt-4
gpt-3.5-turbo

Anthropic

claude-3-5-sonnet
claude-3-opus
claude-3-sonnet
claude-3-haiku

Google

gemini-1.5-pro
gemini-1.5-flash
gemini-1.0-pro

Usage Examples

Choose by Task Complexity

python

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.tokenlio.ai/v1"
)

# Simple task - use cheaper model
response = client.chat.completions.create(
    model="gpt-3.5-turbo",
    messages=[{"role": "user", "content": "Summarize in one sentence"}]
)

# Complex task - use powerful model
response = client.chat.completions.create(
    model="gpt-4-turbo",
    messages=[{"role": "user", "content": "Analyze this legal document..."}]
)

Dynamic Model Selection

python

def select_model(task_complexity: str) -> str:
    if task_complexity == "simple":
        return "gpt-3.5-turbo"
    elif task_complexity == "moderate":
        return "claude-3-haiku"
    elif task_complexity == "complex":
        return "gpt-4-turbo"
    else:
        return "claude-3-5-sonnet"

FAQ

Q: Can I request access to a specific model?
A: Yes, email support@tokenlio.ai with your use case.

Q: Are prices guaranteed?
A: Prices may change with notice. Current usage is always charged at current rates.

Q: Do you offer volume discounts?
A: Contact sales@tokenlio.ai for enterprise pricing.

Q: How do I know which model to use?
A: Start with GPT-3.5 Turbo for testing, then upgrade to GPT-4 or Claude for better quality if needed.

Available Models & Pricing

Model Categories

Chat Completion Models

Pricing Structure

Example Pricing

Model Selection Guide

By Use Case

By Context Length

Getting Current Pricing

Via Public API

Via Console

Model Identifiers

OpenAI

Anthropic

Google

Usage Examples

Choose by Task Complexity

Dynamic Model Selection

FAQ

Next Steps

Need Help?

Available Models & Pricing ​

Model Categories ​

Chat Completion Models ​

Pricing Structure ​

Example Pricing ​

Model Selection Guide ​

By Use Case ​

By Context Length ​

Getting Current Pricing ​

Via Public API ​

Via Console ​

Model Identifiers ​

OpenAI ​

Anthropic ​

Google ​

Usage Examples ​

Choose by Task Complexity ​

Dynamic Model Selection ​

FAQ ​

Next Steps ​

Need Help? ​

Available Models & Pricing

Model Categories

Chat Completion Models

Pricing Structure

Example Pricing

Model Selection Guide

By Use Case

By Context Length

Getting Current Pricing

Via Public API

Via Console

Model Identifiers

OpenAI

Anthropic

Google

Usage Examples

Choose by Task Complexity

Dynamic Model Selection

FAQ

Next Steps

Need Help?