Pricing

How Pricing Works

OpenModex uses pay-as-you-go pricing. You’re billed only for the tokens you consume, at transparent pass-through rates.

OpenModex charges the same per-token rate as the underlying provider. There are no hidden markups on model costs.

Subscription Tiers

	Free	Pro	Enterprise
Price	$0/mo	$29/mo	Custom
Requests/min	30	120	300+
Tokens/min	60,000	500,000	Custom
Models	All	All	All + Custom
Smart Routing	Basic	Full	Full + Custom
Prompt Caching	—	Included	Included
Fallbacks	1 level	Unlimited	Unlimited
BYOK	—	Included	Included
Support	Community	Email	Dedicated
Analytics	Basic	Full	Full + Export
Team Management	—	Up to 5	Unlimited

Token Pricing

Model costs are passed through at provider rates. Check real-time pricing via the Models API or the Dashboard.

Popular Models

Model	Input (per 1M tokens)	Output (per 1M tokens)
`gpt-4o`	$2.50	$10.00
`gpt-4o-mini`	$0.15	$0.60
`claude-3.5-sonnet`	$3.00	$15.00
`claude-3-haiku`	$0.25	$1.25
`gemini-2.0-flash`	$0.10	$0.40
`gemini-1.5-pro`	$1.25	$5.00
`deepseek-chat`	$0.14	$0.28
`mistral-large`	$2.00	$6.00
`text-embedding-3-small`	$0.02	—

Cached Responses

Prompt caching reduces costs significantly:

	Standard	Cached
Input tokens	100%	~50%
Output tokens	100%	$0
Latency	Normal	<10ms

Cost Tracking

Every API response includes cost data:

{
  "usage": {
    "prompt_tokens": 150,
    "completion_tokens": 50,
    "total_tokens": 200,
    "cost_usd": 0.001
  }
}

Balance & Payments

Add funds via credit card (Stripe) or cryptocurrency
View balance and transaction history in the Dashboard
Set alerts for low-balance notifications
Auto-recharge available on Pro and Enterprise tiers

Cost Optimization Tips

Use Smart Routing

Let OpenModex pick the cheapest model that meets your quality threshold.

Enable Caching

Cache repeated prompts to eliminate redundant API calls.

Right-size Models

Use smaller models for simple tasks — gpt-4o-mini is 15x cheaper than gpt-4o.

Bring Your Own Key

Use your own provider keys for volume discounts.

Getting Started

Platform

Core Features

Guides

How Pricing Works

Subscription Tiers

Token Pricing

Popular Models

Cached Responses

Cost Tracking

Balance & Payments

Cost Optimization Tips

Use Smart Routing

Enable Caching

Right-size Models

Bring Your Own Key

​How Pricing Works

​Subscription Tiers

​Token Pricing

​Popular Models

​Cached Responses

​Cost Tracking

​Balance & Payments

​Cost Optimization Tips

Use Smart Routing

Enable Caching

Right-size Models

Bring Your Own Key

How Pricing Works

Subscription Tiers

Token Pricing

Popular Models

Cached Responses

Cost Tracking

Balance & Payments

Cost Optimization Tips