OpenAI: GPT-3.5 Turbo (batch)

openai/gpt-3.5-turbo:batch · OpenAIDeclared and measured agree

Tokenizer lineage (measured): OpenAI cl100k
Declared tokenizer tag: GPT
Entered catalogue: 28 May 2023
Measurement: Variant: inherits its base model’s measurement
Evidence confidence: High

Why high: inherited from openai/gpt-3.5-turbo: a serving variant shares its base model's tokenizer.

Evidence

✓ inherited from openai/gpt-3.5-turbo: a serving variant shares its base model's tokenizer

Compare with OpenAI: GPT-3.5 Turbo

Report a correction

This entry is a serving variant of OpenAI: GPT-3.5 Turbo. 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-3.5 Turbo (batch) is OpenAI's model, and its measured tokenizer sits in OpenAI's own signature group alongside its sibling models. No other maker's measured model shares it so far.

Whose vocabulary this is

Tokenizer: cl100k_base
Origin of tokenizer: OpenAI tiktoken, open source
Model maker: OpenAI

cl100k_base is an open vocabulary table anyone can build on. Sharing it says which dictionary the model reads with, and nothing about who made the model.

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 1 other listing, field for field	api_e35a478b
How much it can read and write	Reads up to 16,385 tokens at once, writes up to 4,096	its own listing

Declared record

What the catalogue claims about this model

GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks. Training data up to Sep 2021.

Modalities: text->text
Declared tokenizer: GPT
Prompt price: $0.25 / M tokens
Completion price: $0.75 / M tokens

Supported parameters

frequency_penaltylogit_biaslogprobsmax_tokenspresence_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_logprobstop_p

defaults: {}

Catalogue entry

History

Every observation, kept as taken

28 May 2023Enters the OpenRouter catalogue declared as GPT.