Models
One name per model, however many providers serve it.
Reka: Reka Edge
Accepts- Text
- Image
- Video
Creates- Text
ToolsJSONReka Edge is an extremely efficient 7B multimodal vision-language model that accepts image/video+text inputs and generates text outputs.
rekaai/reka-edgeMar 20, 202616K context37,576 Toman/M input tokens37,576 Toman/M output tokensReka: Reka Flash 3
Accepts- Text
Creates- Text
JSONReasoningReka Flash 3 is a general-purpose, instruction-tuned large language model with 21 billion parameters, developed by Reka. It excels at general chat, coding tasks, instruction-following, and function calling.
rekaai/reka-flash-3Mar 12, 202566K context37,576 Toman/M input tokens75,152 Toman/M output tokens
2 of 581 models · Catalog updated 3 hours ago. · Free plan prices, in Toman at today's rate. Plans and prices

