Static fallback rates
Sent with every call — instructions, RAG chunks, tool definitions.
1 = single-shot request. Above 1, history is resent each turn — input grows every turn.
No custom models yet — add one to include it in the comparison table.
Enable Prompt Caching
Applies each model's cache discount to input cost, above that provider's minimum cacheable prompt length
Share of input tokens that hit the cache. RAG apps typically cache the fixed context/system prompt while fresh user input stays full-price — try a lower ratio to model that.
Use Batch API
Applies each model's batch discount, ~50% off
Safety Buffer Margin
Adds +15% contingency for retries & errors
Reasoning Token Overhead
Bills hidden "thinking" tokens on reasoning models (o-series, R1, extended thinking) as extra output
Extra hidden output tokens as a % of your visible output, on reasoning-capable models only (badge in the table below). 100% roughly doubles billed output on those models.
Live Summary
Per request
$0.00000
Daily cost
$0.00
Monthly cost
$0.00
Model Comparison
Sorted cheapest → most expensive| # | Model | Per Request | Monthly | Relative Cost |
|---|
Prices are editable estimates stored in the MODEL_PRICES array and may not reflect live provider pricing.
Always confirm current rates on each provider's official pricing page before budgeting.