OpenAI: GPT-5.4 Pro (batch)

openai/gpt-5.4-pro:batch · OpenAIUnmeasurable

Declared family: GPT
Declared tokenizer tag: GPT
Entered catalogue: 5 March 2026
Measurement: Variant: inherits its base model’s measurement
Evidence confidence: Unknown

This entry is a serving variant of OpenAI: GPT-5.4 Pro. A variant shares its base model's tokenizer by construction, so the measurement lives on the base record and this page inherits it.

What we checked

Four different kinds of evidence, and what each one showed

We checked	What we found	Where it came from
How it counts tokens	Not measured yet	we measured it
How its API is set up	Set up identically to 2 other listings, field for field	api_62d60aef
How much it can read and write	Reads up to 1,050,000 tokens at once, writes up to 128,000	its own listing
Whether it thinks before answering	Always reasons, and cannot be turned off, at xhigh, high, medium, medium by default	its own listing

Declared record

What the catalogue claims about this model

GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks. It features a 1M+ token context window (922K input, 128K...

Modalities: text+image+file->text
Declared tokenizer: GPT
Prompt price: $15.0 / M tokens
Completion price: $90.0 / M tokens

Supported parameters

include_reasoningmax_tokensreasoningreasoning_effortresponse_formatseedstructured_outputstool_choicetoolsverbosity

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

5 March 2026Enters the OpenRouter catalogue declared as GPT.