Understanding Language Models
Context Window
The maximum amount of text (measured in tokens) that the model can process in a single interaction. Larger context windows allow the model to understand and respond to longer conversations or documents.
Tokens
Units of text that the model processes. A token can be as short as a single character or as long as a word (roughly 4 characters = 1 token in English).
Input/Output Pricing
Models charge differently for processing your input (prompts) vs generating output (completions). Prices are per 100 million tokens.
Cache
Some models offer caching capabilities to store and retrieve previous responses, potentially reducing costs and improving response times.
Available Models
Choose from our selection of state-of-the-art language models
GPT-4o mini
OpenAI
Context Window: 128,000 tokens
Max Output: 4,096 tokens
Pricing (per 100M tokens)
Prompt Tokens
$0.15
Cache Read
$0.075
Completion Tokens
$0.6
GPT-4o
OpenAI
Context Window: 128,000 tokens
Max Output: 4,096 tokens
Pricing (per 100M tokens)
Prompt Tokens
$2.5
Cache Read
$1.25
Completion Tokens
$10
Claude 3.5 Haiku
Anthropic
Context Window: 200,000 tokens
Max Output: 8,192 tokens
Pricing (per 100M tokens)
Prompt Tokens
$1
Cache Read
$0.1
Cache Write
$1.25
Completion Tokens
$5
Claude 3.5 Sonnet
Anthropic
Context Window: 200,000 tokens
Max Output: 8,192 tokens
Pricing (per 100M tokens)
Prompt Tokens
$3
Cache Read
$0.3
Cache Write
$3.75
Completion Tokens
$15
Claude 3 Opus
Anthropic
Context Window: 200,000 tokens
Max Output: 4,096 tokens
Pricing (per 100M tokens)
Prompt Tokens
$15
Cache Read
$1.5
Cache Write
$18.75
Completion Tokens
$75
Gemini 1.5 Flash 8B
Context Window: 128,000 tokens
Max Output: 8,192 tokens
Pricing (per 100M tokens)
Prompt Tokens
$0.0375
Completion Tokens
$0.15
Gemini 1.5 Flash 002
Context Window: 128,000 tokens
Max Output: 8,192 tokens
Pricing (per 100M tokens)
Prompt Tokens
$0.075
Completion Tokens
$0.3
Gemini 1.5 Pro 002
Context Window: 128,000 tokens
Max Output: 8,192 tokens
Pricing (per 100M tokens)
Prompt Tokens
$1.25
Completion Tokens
$5
chatgpt-4o-latest
OpenAI
Context Window: 128,000 tokens
Max Output: 4,096 tokens
Pricing (per 100M tokens)
Prompt Tokens
$5
Completion Tokens
$15
Gemini Experimental 1114
Context Window: 128,000 tokens
Max Output: 8,192 tokens
Pricing (per 100M tokens)
Prompt Tokens
$0
Completion Tokens
$0
Claude 3.5 Haiku (2024-10-22)
Anthropic
Context Window: 200,000 tokens
Max Output: 8,192 tokens
Pricing (per 100M tokens)
Prompt Tokens
$1
Cache Read
$0.1
Cache Write
$1.25
Completion Tokens
$5
Claude 3.5 Sonnet (2024-10-22)
Anthropic
Context Window: 200,000 tokens
Max Output: 8,192 tokens
Pricing (per 100M tokens)
Prompt Tokens
$3
Cache Read
$0.3
Cache Write
$3.75
Completion Tokens
$15
Gemini 1.5 Flash 8B Experimental (2024-09-24)
Context Window: 128,000 tokens
Max Output: 8,192 tokens
Pricing (per 100M tokens)
Prompt Tokens
$0
Completion Tokens
$0
Gemini 1.5 Pro Experimental (2024-08-27)
Context Window: 128,000 tokens
Max Output: 8,192 tokens
Pricing (per 100M tokens)
Prompt Tokens
$0
Completion Tokens
$0
Gemini 1.5 Flash Experimental (2024-08-27)
Context Window: 128,000 tokens
Max Output: 8,192 tokens
Pricing (per 100M tokens)
Prompt Tokens
$0
Completion Tokens
$0
GPT-4o (2024-08-06)
OpenAI
Context Window: 128,000 tokens
Max Output: 4,096 tokens
Pricing (per 100M tokens)
Prompt Tokens
$2.5
Cache Read
$1.25
Completion Tokens
$10
GPT-4o mini (2024-07-18)
OpenAI
Context Window: 128,000 tokens
Max Output: 4,096 tokens
Pricing (per 100M tokens)
Prompt Tokens
$0.15
Cache Read
$0.075
Completion Tokens
$0.6
Claude 3.5 Sonnet (2024-06-20)
Anthropic
Context Window: 200,000 tokens
Max Output: 8,192 tokens
Pricing (per 100M tokens)
Prompt Tokens
$3
Cache Read
$0.3
Cache Write
$3.75
Completion Tokens
$15
Gemini 1.5 Flash 001 (2024-05-24)
Context Window: 128,000 tokens
Max Output: 8,192 tokens
Pricing (per 100M tokens)
Prompt Tokens
$0.075
Completion Tokens
$0.3
Gemini 1.5 Pro 001 (2024-05-24)
Context Window: 128,000 tokens
Max Output: 8,192 tokens
Pricing (per 100M tokens)
Prompt Tokens
$1.25
Completion Tokens
$5
GPT-4o (2024-05-13)
OpenAI
Context Window: 128,000 tokens
Max Output: 4,096 tokens
Pricing (per 100M tokens)
Prompt Tokens
$5
Completion Tokens
$15
Claude 3 Haiku (2024-03-27)
Anthropic
Context Window: 200,000 tokens
Max Output: 4,096 tokens
Pricing (per 100M tokens)
Prompt Tokens
$0.25
Cache Read
$0.03
Cache Write
$0.3
Completion Tokens
$1.25
Claude 3 Opus (2024-02-29)
Anthropic
Context Window: 200,000 tokens
Max Output: 4,096 tokens
Pricing (per 100M tokens)
Prompt Tokens
$15
Cache Read
$1.5
Cache Write
$18.75
Completion Tokens
$75
Hermes 3 405B Instruct (free)
Nous
Context Window: 8,192 tokens
Max Output: 4,096 tokens
Pricing (per 100M tokens)
Prompt Tokens
$0
Completion Tokens
$0
Llama 3.1 405B Instruct (free)
Meta
Context Window: 8,000 tokens
Max Output: 4,000 tokens
Pricing (per 100M tokens)
Prompt Tokens
$0
Completion Tokens
$0
Llama 3.1 70B Instruct (free)
Meta
Context Window: 8,192 tokens
Max Output: 4,096 tokens
Pricing (per 100M tokens)
Prompt Tokens
$0
Completion Tokens
$0