OpenAI: GPT-4o-mini (batch)

openai/gpt-4o-mini:batch · OpenAIDeclared and measured agree

Tokenizer lineage (measured): GPT
Evidence confidence: High
Declared tokenizer tag: GPT
Entered catalogue: 18 July 2024
Last tested: Not yet measured
Measurement: Variant: inherits its base model’s measurement

Evidence

✓ inherited from openai/gpt-4o-mini: a serving variant shares its base model's tokenizer

This entry is a serving variant of OpenAI: GPT-4o-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: GPT-4o-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_610b4004
Context and output	128,000 context · 16,384 max output	declared
Reasoning contract	None declared	declared
Serving providers observed	None recorded yet	–

Declared record

What the catalogue claims about this model

GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...

Modalities: text+image+file->text
Declared tokenizer: GPT
Prompt price: $0.07 / M tokens
Completion price: $0.30 / M tokens

Supported parameters

frequency_penaltylogit_biaslogprobsmax_tokenspredictionpresence_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_logprobstop_pweb_search_options

defaults: {}

Catalogue entry

History

Every observation, kept as taken

18 July 2024Enters the OpenRouter catalogue declared as GPT.

Cite this page as the evidence record for OpenAI: GPT-4o-mini (batch): 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.