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, video analysis, object detection, and agentic tool-use.
rekaai/reka-edge
- Context
- 16k tokens
- Completion cap
- 16,384
- Tools
- Yes
- JSON
- Yes
- Released
- 2026-03-20
Call it from Geek Hub
Same OpenAI SDK. Change the base URL and the model id.
curl https://api.geekhub.mx/v1/chat/completions \
-H "Authorization: Bearer $GEEKHUB_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "rekaai/reka-edge",
"messages": [{"role": "user", "content": "Hola"}]
}'Frequently asked questions
- What is 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, video analysis, object detection, and agentic tool-use. Reka Edge runs on the Geek Hub API (OpenAI-compatible). Model id: rekaai/reka-edge.
- Is Reka Edge free?
- No. Input is $0.109 per 1M tokens and output is $0.109 per 1M tokens on Geek Hub (markup included).
- What is the context length of Reka Edge?
- Reka Edge has a 16k tokens context window. It supports up to 16,384 completion tokens.
- Does Reka Edge support tool calling and structured outputs?
- Reka Edge accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.
- When was Reka Edge released?
- Reka Edge was released on 2026-03-20.