OpenAI: o4 Mini is OpenAI's model. Its measured tokenizer sits with the GPT group, which is evidence that it builds on the GPT tokenizer. Tokenizer reuse is normal engineering, open vocabularies travel between labs, and this says nothing against OpenAI's authorship of the model itself.
| Signal | Result | Reference |
|---|---|---|
| Tokenizer signature | Exact match with 31 other models | tk_d1411c9d |
| API surface | Identical contract to 3 other entries | api_a2a7f2ca |
| Context and output | 200,000 context · 100,000 max output | declared |
| Reasoning contract | Optional | declared |
| Serving providers observed | OpenAI | measured 3 September 2026 |
Click a row to open the full comparison.
An x marks a row excluded as corrupt (caching or provider interference detected during measurement). Overhead subtracted: 6 prompt tokens.
OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning...
Supported parameters
include_reasoningmax_tokensreasoningresponse_formatseedstructured_outputstool_choicetools
defaults: {}
Cite this page as the evidence record for OpenAI: o4 Mini: the URL is stable, measurements are dated, and revisions append to the history above. Method: tokenizer fingerprinting, v1, 50 strings.
