Documentation/Pricing & Models/Model Pricing Table

Model Pricing Table

Official pricing rates, cache discounts, and reasoning token rates across 50+ models.


Model Pricing Table

Rates are updated per **1 Million Tokens** with automatic prompt cache discounts:

Model ProviderModel IDInput / 1MOutput / 1MCached Input / 1M
**OpenAI**`gpt-4o-mini`$0.150$0.600$0.075
**OpenAI**`gpt-4o`$2.500$10.000$1.250
**OpenAI**`o3-mini` / `o1`$1.100$4.400$0.550
**OpenAI**`gpt-5.6-sol`$4.000$20.000$0.400
**Anthropic**`claude-3-7-sonnet`$0.590$2.930$0.300
**Anthropic**`claude-3-5-sonnet`$3.000$15.000$0.300
**Anthropic**`claude-3-5-haiku`$0.800$4.000$0.080
**Google**`gemini-2.0-flash`$0.100$0.400$0.025
**Google**`gemini-1.5-pro`$1.250$5.000$0.313
**DeepSeek**`deepseek-chat`$0.220$0.660$0.050
**DeepSeek**`deepseek-reasoner`$0.660$1.980$0.150

Interactive Model Cost Calculator

Live USD inference cost estimation across 50+ models

Live Math
Input Tokens (Prompt)1,500 tokens
Output Tokens (Completion)600 tokens
Reasoning / Thinking Tokens300 tokens
Markup Multiplier (Profit Margin)1x (0% margin)
Computed Inference Cost
$0.000585USD
Input Prompt Cost:$0.000225
Output & Thinking Cost:$0.000360
Raw Base Cost:$0.000585
Calculated synchronously in 0.00ms with zero external API calls.