| Signal | Result | Reference |
|---|---|---|
| Tokenizer signature | Not measured | – |
| API surface | Identical contract to 2 other entries | api_e1f8149d |
| Context and output | 400,000 context · 128,000 max output | declared |
| Reasoning contract | Mandatory · efforts high, medium, low, minimal · default medium | declared |
| Serving providers observed | OpenAI | measured 21 August 2026 |
An x marks a row excluded as corrupt (caching or provider interference detected during measurement). Overhead subtracted: 6 prompt tokens.
GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost....
Supported parameters
include_reasoningmax_completion_tokensmax_tokensreasoningreasoning_effortresponse_formatseedstructured_outputstool_choicetools
defaults: {"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null}
Cite this page as the evidence record for OpenAI: GPT-5 Mini: the URL is stable, measurements are dated, and revisions append to the history above. Method: tokenizer fingerprinting, v1, 50 strings. The raw data behind every figure is on the data page.
