Pass IndexThe State of AISign in

Reka Edge

Reka Edge is an extremely efficient 7B multimodal vision-language model that accepts image/video+text inputs and generates text outputs.

text + image + video → text · made by Reka

$0.1$0.1per Mtok in / out
Reka · 3 sellers

Sold by 4 ways

SellerLaneRate
Reka apistandard$0.1per Mtok in$0.1per Mtok out$0.005per image$0.03per minutedocs.reka.ai · read 2026-08-25
Nous Research aggregatorstandard$0.1per Mtok in$0.1per Mtok outinference-api.nousresearch.com · read 2026-09-12
OpenRouter 2 ways$0.1per Mtok in$0.1per Mtok out
OpenRouter aggregatorstandard$0.1per Mtok in$0.1per Mtok outopenrouter.ai · read 2026-08-24
OpenRouter aggregatorreka/bf16$0.1per Mtok in$0.1per Mtok out$0.1per Mtok cachedopenrouter.ai · read 2026-08-25

About

Reka Edge — a text model from Reka, sold by 3 companies from $0.1 in and $0.1 out per million tokens.

It takes text, images and video and returns text, with a context window of 16,384 tokens. It was published in March 2026. Its sellers say it can call a tool. The catalogue files it under chat. Three companies sell it. The cheapest is $0.1 in and $0.1 out per million tokens at Nous Research. Beside the standard rate there is a regional lane.

Every current figure

Maker
Reka
Register
model
Takes
text + image + video
Returns
text
Context
16,384 tokens
Longest answer
14,745 tokens
Published
March 2026
Licence
not read
Sellers
3
Price
$0.1 in and $0.1 out per million tokens — Nous Research

Known as 3 names

rekaai/reka-edgereka-edgereka-edge-2603