/ Models

Language models

Reka Edge

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,...

Maker
Rekaai
Context window
16K
Max output
16K
Input / 1M
$0.1
Output / 1M
$0.1
1M in + 1M out
$0.2

Everything else

Max output16K
Input / 1M$0.1
Output / 1M$0.1
Cache read / 1M
Cache write / 1M
1M in + 1M out$0.2
Takesimage, text, video
Returnstext
Toolsyes
Reasoningoptional
Open weightsyes
Released2026-03-20
Knowledge cutoff
Retires
Catalog idrekaai/reka-edge

Using it

In 00, this model is picked per agent — and per tier, so the model that answers your customers need not be the one that writes your code. Get 00.

← all models