AI Observatory / Model Radar
Rekaai / rekaai/reka-edge
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,...
16,384
Context
16,384
Max output
$0.10 / 1M
Prompt price
2026-03-20
Created
01 / Snapshot
Pricing, context, modalities, and parameters.
Model Radar detail pages stay neutral and operator-readable: core metadata first, then workflow fit.
| Provider | Rekaai | Input modalities | image, text, video |
|---|---|---|---|
| Output modalities | text | Prompt price | $0.10 / 1M |
| Completion price | $0.10 / 1M | Request price | N/A |
| Context length | 16,384 | Max completion tokens | 16,384 |
| Supported parameters | frequency_penalty, max_tokens, presence_penalty, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_p | ||
Best for
rekaai/reka-edge
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,...
Cross-modal work
High-volume usage
Coding workflows
new
vision
tool-capable
low-cost
03 / Colophon
Routes and exits.
Each model page stays simple: overview, compare, related models, then back to the public hub.