GPT-5.4 is a flagship model for complex professional work. Learn more in our GPT-5.4 model guidance. Reasoning.effort supports: none (default), low, medium, high and xhigh.
function_callingweb_searchfile_searchtool_searchimage_generationcode_interpreterhosted_shellapply_patchskillscomputer_usemcphttps://api.openai.com/v1/chat/completionshttps://api.openai.com/v1/responseshttps://api.openai.com/v1/batches| Input | Output | Cached input | 30m write | 12h write | |
|---|---|---|---|---|---|
| Standard | $2.5 | $15 | $0.25 | — | — |
| Batch | $1.25 | $7.5 | $0.13 | — | — |
| Fast | $5 | $30 | $0.5 | — | — |
For models with a 1.05M context window (GPT-5.4 and GPT-5.4 Pro), prompts with >272K input tokens are priced at 2x input and 1.5x output for the full session for standard, batch, and flex.
Regional processing (data residency) endpoints are charged a 10% uplift for GPT-5.4 and GPT-5.4 Pro.
| Model | Context | Max out | Pricing |
|---|---|---|---|
| GPT-5.4 nano | 400K | 128K | $0.2$1.25 |
| GPT-5.4 Mini | 400K | 128K | $0.75$4.5 |
| GPT-5.4 | 1.1M | 128K | $2.5$15 |
| GPT-5.4 Pro | 1.1M | 128K | $30$180 |
/v1/models/openai/gpt-5.4