OpenAI: GPT-4.1 Nano (batch)

openai/gpt-4.1-nano:batch · OpenAIDeclared and measured agree
Tokenizer lineage (measured)
GPT
Evidence confidence
High
Why high: inherited from openai/gpt-4.1-nano: a serving variant shares its base model's tokenizer.
Declared tokenizer tag
GPT
Entered catalogue
14 April 2025
Last tested
Not yet measured
Measurement
Variant: inherits its base model’s measurement
Evidence
  • ✓ inherited from openai/gpt-4.1-nano: a serving variant shares its base model's tokenizer

This entry is a serving variant of OpenAI: GPT-4.1 Nano. 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-4.1 Nano (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
SignalResultReference
Tokenizer signatureNot measured
API surfaceIdentical contract to 2 other entriesapi_4d6ed85d
Context and output1,047,576 context · 32,768 max outputdeclared
Reasoning contractNone declareddeclared
Serving providers observedNone recorded yet

Declared record

What the catalogue claims about this model

For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million...

Modalities
text+image+file->text
Declared tokenizer
GPT
Prompt price
$0.05 / M tokens
Completion price
$0.20 / M tokens

Supported parameters

max_tokensresponse_formatseedstructured_outputstemperaturetool_choicetoolstop_p

defaults: {}

Catalogue entry

History

Every observation, kept as taken
  • 14 April 2025Enters the OpenRouter catalogue declared as GPT.

Cite this page as the evidence record for OpenAI: GPT-4.1 Nano (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.