OpenAI: GPT-3.5 Turbo Instruct

openai/gpt-3.5-turbo-instruct · OpenAIUnmeasurable

Tokenizer lineage (measured): OpenAI cl100k
Evidence confidence: Moderate
Declared tokenizer tag: GPT
Entered catalogue: 28 September 2023
Last tested: 3 September 2026
Measurement: Unmeasurable: prompt caching corrupts its token accounting

Evidence

✓ near-exact agreement (41/41) with ibm-granite/granite-4.0-h-micro

Compare with IBM: Granite 4.0 Micro

Download JSON Report a correction

Identity statement

OpenAI: GPT-3.5 Turbo Instruct 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.

Evidence stack

Signals of different kinds, weighed together

Signal	Result	Reference
Tokenizer signature	Not measured	–
API surface	No other entry shares this exact contract	api_647692d5
Context and output	4,095 context · 3,685 max output	declared
Reasoning contract	None declared	declared
Serving providers observed	OpenAI	measured 3 September 2026

Closest measured models

Agreement across the mutually clean test strings

IBM: Granite 4.0 Microibm-granite/granite-4.0-h-micro41/41 · 100%IBM: Granite 4.1 8Bibm-granite/granite-4.1-8b41/41 · 100%Microsoft: Phi 4microsoft/phi-441/41 · 100%OpenAI: GPT-3.5 Turboopenai/gpt-3.5-turbo41/41 · 100%Meta: Llama 3.2 1B Instructmeta-llama/llama-3.2-1b-instruct29/41 · 71%Nous: Hermes 4 70Bnousresearch/hermes-4-70b29/41 · 71%

Click a row to open the full comparison.

The measured fingerprint

Marginal prompt-token cost of each test string, grouped by script

All 50 rows, 9 excluded as corrupt

English and whitespace

en-prose14

en-long16

spaces-203

spaces-603

tabs-203

newlines-204

mixed-ws5

Digits

digits-93

digits-124

digits-3010

digits-sep7

float-long9

CJK

zh-common18

zh-long25

zh-rarex

ja-kana14

ja-kanji17

kox

Other scripts

ru16

ar25

he24

hi32

th25

elx

Emoji

emoji-basicx

emoji-skinx

emoji-zwj-familyx

emoji-zwj-x3x

emoji-flags24

emoji-profx

Rare Unicode

math32

boxdrawx

combining14

cjk-ext-b13

surrogates40

zalgo36

rtl-mix11

Code

py-code25

py-indent15

json20

html16

regex44

camel5

snake6

Repetition and encodings

rare-word-x531

repeat-tok22

base6435

hex11

url17

uuid27

An x marks a row excluded as corrupt (caching or provider interference detected during measurement). Overhead subtracted: 8 prompt tokens.

Declared record

What the catalogue claims about this model

This model is a variant of GPT-3.5 Turbo tuned for instructional prompts and omitting chat-related optimizations. Training data: up to Sep 2021.

Modalities: text->text
Declared tokenizer: GPT
Prompt price: $1.50 / M tokens
Completion price: $2.00 / M tokens

Supported parameters

frequency_penaltylogit_biaslogprobsmax_tokenspresence_penaltyresponse_formatseedstopstructured_outputstemperaturetop_logprobstop_p

defaults: {}

Catalogue entry

History

Every observation, kept as taken

28 September 2023Enters the OpenRouter catalogue declared as GPT.
3 September 2026Fingerprinted in the YFarmX catalogue sweep · 41 of 50 strings measured clean.
3 September 2026YFarmX assessment: consistent with the OpenAI cl100k family, moderate confidence.

Cite this page as the evidence record for OpenAI: GPT-3.5 Turbo Instruct: the URL is stable, measurements are dated, and revisions append to the history above. Method: tokenizer fingerprinting, v1, 50 strings.