OpenAI: o3 Mini (batch)

openai/o3-mini:batch · OpenAIDeclared and measured agree

Tokenizer lineage (measured): GPT
Evidence confidence: High
Declared tokenizer tag: GPT
Entered catalogue: 31 January 2025
Last tested: Not yet measured
Measurement: Variant: inherits its base model’s measurement

Evidence

✓ inherited from openai/o3-mini: a serving variant shares its base model's tokenizer

This entry is a serving variant of OpenAI: o3 Mini. A variant shares its base model's tokenizer by construction, so the measurement lives on the base record and this page inherits it.

Identity statement

OpenAI: o3 Mini (batch) 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.

Evidence stack

Signals of different kinds, weighed together

Signal	Result	Reference
Tokenizer signature	Not measured	–
API surface	Identical contract to 3 other entries	api_3da68b21
Context and output	200,000 context · 100,000 max output	declared
Reasoning contract	Optional	declared
Serving providers observed	None recorded yet	–

Declared record

What the catalogue claims about this model

OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding. This model supports the `reasoning_effort` parameter, which can be set to...

Modalities: text+file->text
Declared tokenizer: GPT
Prompt price: $0.55 / M tokens
Completion price: $2.20 / M tokens

Supported parameters

include_reasoningmax_tokensreasoningresponse_formatseedstructured_outputstool_choicetools

defaults: {"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null}

Catalogue entry

History

Every observation, kept as taken

31 January 2025Enters the OpenRouter catalogue declared as GPT.

Cite this page as the evidence record for OpenAI: o3 Mini (batch): the URL is stable, measurements are dated, and revisions append to the history above. Method: tokenizer fingerprinting, v1, 50 strings.