---
id: "rekaai/reka-edge"
also: ["rekaai/reka-edge-2603", "RekaAI/reka-edge-2603"]
card_usd_per_m: "0.1 in, 0.1 out, at reka"
cheapest_list_usd_per_m: "0.1 in, 0.1 out, at reka on openrouter"
cheapest_effective_usd_per_m: "0.0991 in, 0.0586 out, at reka on openrouter"
context: 16384
max_output: 14745
input: ["image", "text", "video"]
output: ["text"]
released: "2026-03-20"
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["frequency_penalty", "logprobs", "max_tokens", "presence_penalty", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p"]
endpoints: 2
gateways: "openrouter (2)"
no_training: 1
trains: 0
retains_prompts: 0
---
# 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,...