R

Reka: reka-edge-2603

reka-edge-2603
16.4K context14.7K outToolsVisionVideoStructured
Released Mar 20, 2026Updated Nov 6, 2026

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, video analysis, object detection, and agentic tool-use.

Tokenizer OtherRekaAI/reka-edge-2603

Pricing

Input price
$0.11/ 1M tokens
Output price
$0.11/ 1M tokens
Context window 16.4K tokensCompatible endpoints openaiVendor Reka

Uptime

Performance

Loading performance data...

Usage & Ranking

Loading usage...

Supported parameters

All providers = every upstream serving this model supports it. Some providers = depends on which upstream handles the request. Default = the value sent when you leave the parameter unset.

ParameterProvidersDefault
frequency_penaltyAll providersNot sent by default
logprobsAll providers-
max_tokensAll providers-
presence_penaltyAll providersNot sent by default
repetition_penaltySome providersNot sent by default
seedAll providers-
stopAll providers-
structured_outputsAll providers-
temperatureAll providersNot sent by default
tool_choiceAll providers-
toolsAll providers-
top_kAll providersNot sent by default
top_logprobsAll providers-
top_pAll providersNot sent by default

Frequently asked questions

Use reka-edge-2603 in

SillyTavernJanitor.AIClineClaude Code

Similar models

R
reka-flash-3
Reka
L
lfm3-1.7b:free
Liquid
M
kimi-k3.1-pro
Moonshot
M
or-kimi-k3.1-pro
Moonshot
M
minimax-m3.1-flash:free
MiniMax
D
deepseek-v4.1-flash-1017
DeepSeek