Reka Edge

rekaai/reka-edge · RekaaiNot yet established

Declared family: Unknown
Entered catalogue: 20 March 2026
Last tested: 21 August 2026
Measured signature: tk_9f6f8410

Compare with Reka Flash 3

Report a correction

Identity statement

Reka Edge has a clean measured fingerprint that currently sits alone: no other measured model shares its signature.

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	Counted cleanly, and no other model in the catalogue counts the same way	tk_9f6f8410
How its API is set up	A combination of settings no other listing in the catalogue uses	api_e4dc6c29
How much it can read and write	Reads up to 16,384 tokens at onceOpenRouter's listing shows 14,745 output tokens, which is 90% of the context window, the figure it carries where the provider declares no maximum.	its own listing
Whether it thinks before answering	Reasons when asked to	its own listing
Who served our requests	Reka	we measured it, 21 August 2026

Closest measured models

Agreement across the mutually clean test strings

Reka Flash 3rekaai/reka-flash-332/46 · 70%OpenAI: GPT-3.5 Turbo Instructopenai/gpt-3.5-turbo-instruct26/41 · 63%IBM: Granite 4.0 Microibm-granite/granite-4.0-h-micro28/50 · 56%IBM: Granite 4.1 8Bibm-granite/granite-4.1-8b28/50 · 56%Microsoft: Phi 4microsoft/phi-428/50 · 56%OpenAI: GPT-3.5 Turboopenai/gpt-3.5-turbo28/50 · 56%

Click a row to open the full comparison.

The measured fingerprint

What each test string cost this model, in tokens

We sent Reka Edge fifty short pieces of text and recorded what each one cost it in tokens. The bars below are those costs. Two models built on the same tokenizer produce the same bars; a model built on a different one produces a different set, which is what makes this a fingerprint.

All 50 rows

English and whitespace

en-prose14

en-long15

spaces-203

spaces-603

tabs-203

newlines-204

mixed-ws5

Digits

digits-94

digits-125

digits-3011

digits-sep8

float-long10

CJK

zh-common19

zh-long26

zh-rare24

ja-kana15

ja-kanji17

ko19

Other scripts

ru16

ar25

he24

hi32

th26

el28

Emoji

emoji-basic9

emoji-skin29

emoji-zwj-family17

emoji-zwj-x353

emoji-flags24

emoji-prof28

Rare Unicode

math31

boxdraw28

combining14

cjk-ext-b14

surrogates40

zalgo36

rtl-mix11

Code

py-code25

py-indent15

json20

html17

regex44

camel5

snake6

Repetition and encodings

rare-word-x531

repeat-tok21

base6435

hex11

url17

uuid28

Overhead subtracted: 5 prompt tokens.

Declared record

What the catalogue claims about this model

Reka Edge is an extremely efficient 7B multimodal vision-language model that accepts image/video+text inputs and generates text outputs. This model is optimized specifically to deliver industry-leading performance in image understanding,...

Modalities: text+image+video->text
Declared tokenizer: Other
Prompt price: $0.10 / M tokens
Completion price: $0.10 / M tokens

Supported parameters

frequency_penaltylogprobsmax_tokenspresence_penaltyseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p

defaults: {"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null}

Catalogue entry Weights on Hugging Face

History

Every observation, kept as taken

20 March 2026Enters the OpenRouter catalogue with no declared family.
21 August 2026Fingerprinted in the YFarmX catalogue sweep · 50 of 50 strings measured clean.