OpenAI: GPT-4 Turbo

openai/gpt-4-turbo · OpenAINot yet established

Declared family: GPT
Evidence confidence: Unknown
Declared tokenizer tag: GPT
Entered catalogue: 9 April 2024
Last tested: Not yet measured
Measurement: Awaiting measurement

Evidence stack

Signals of different kinds, weighed together

Signal	Result	Reference
Tokenizer signature	Not measured	–
API surface	Identical contract to 2 other entries	api_40bcda49
Context and output	128,000 context · 4,096 max output	declared
Reasoning contract	None declared	declared
Serving providers observed	None recorded yet	–

Declared record

What the catalogue claims about this model

The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling. Training data: up to December 2023.

Modalities: text+image->text
Declared tokenizer: GPT
Prompt price: $10.0 / M tokens
Completion price: $30.0 / M tokens

Supported parameters

frequency_penaltylogit_biaslogprobsmax_tokenspresence_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_logprobstop_p

defaults: {}

Catalogue entry

History

Every observation, kept as taken

9 April 2024Enters the OpenRouter catalogue declared as GPT.

Cite this page as the evidence record for OpenAI: GPT-4 Turbo: 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.