API pricing
Source of record for model, file search, web search, and container pricing rows.
OpenAI calculator
OpenAI API pricing calculator for tokens, hosted tools, and runtime.
This page is a real lightweight calculator, not a static explainer. It estimates model-token spend, file search, web search, and container runtime in one source-linked breakdown so the biggest line item is visible before a team commits to a model path.
Line-item breakdown
Keep the big lines visible before debating model swaps.
The calculator keeps request-driven costs and standing monthly costs separate so storage and runtime do not disappear behind one number.
| Line item | Per request | Monthly | Note |
|---|---|---|---|
| Model input tokens | $2.50 | $2500 | Calculated from the selected OpenAI model row. |
| Cached input tokens | $0.00 | $0.00 | Calculated from the selected row's cached-input rate. |
| Model output tokens | $1.50 | $1500 | Calculated from the selected OpenAI output-token rate. |
| File search tool calls | $0.00 | $0.00 | Calculated from file-search call count. Token exposure from retrieved context is not included. |
| File search storage | $0.00 | $0.00 | Standing monthly cost for 0 GB over 30 days after the first 1 free GB. |
| Web search calls | $0.00 | $0.00 | No web search path selected. |
| Web search content tokens | $0.00 | $0.00 | No web-search token exposure in the current estimate. |
| Container runtime | $0.00 | $0.00 | Calculated from code interpreter container count. Runtime cost is separate from the model row. |
Source-linked assumptions
The calculator stays honest by showing what it does not guess.
- Applied model row: gpt-5.4 / Short / standard.
- File-search storage is treated as a standing 30-day monthly cost rather than a request-driven line item.
- File-search token exposure from retrieved context is not estimated in this v1 calculator.
- For standard and preview reasoning web search on models without a published fixed token block, the calculator prices the call meter but excludes variable search-content token usage.
- Monthly multiplier scales request-driven line items. Standing storage remains its own monthly line.
Open official page
File search guide
Explains the hosted retrieval path that makes file-search cost a multi-meter estimate.
Web search guide
Explains the tool path behind web-search pricing and why path selection matters.
Code interpreter guide
Explains the runtime path that turns code execution into a container-cost decision.
Continue the site
Keep moving through the decision from here.
Use the groups below to move laterally through the decision, not back out into another doc hunt.
Related pages
Stay in the same decision neighborhood instead of backing out to search.
Calculators
Interactive estimate pages that price token usage, hosted tools, and runtime together.
Open pageOpenAI file search pricing
Tool-cost brief for file search pricing across storage, tool calls, and model-token exposure.
Open pageOpenAI container pricing
Tool-cost brief for code interpreter container runtime and how it stacks with model spend.
Open pageCompare pages
Open the pages that turn this topic into a side-by-side decision.
Replacement pages
Use the likely substitutes, migration targets, or fallback choices as the next click.
Source category pages
Trace the source families behind this page instead of opening random docs in isolation.