Reka Edge
Reka Edge is a large language model made by Rekaai, added to the catalog on 20 Mar 2026. It has a context window of 16,384 tokens and costs $0.10 per 1M input tokens and $0.10 per 1M output tokens. It accepts text, images and video and produces text. Typical uses: answering questions about images, writing image descriptions and summarising video content.
Price checked ยท source: OpenRouter
What Reka Edge is
Reka Edge is a multimodal vision-language model from Reka. It accepts image, video, and text inputs and produces text. This makes it suitable for tasks that combine visual material with written prompts, as well as tasks based on text alone. The catalog identifies it as a 7B model and lists support for tools and structured outputs. Its listed output modality is text, including when the input contains images or video. The documented input and output types describe a model that works with visual content through text-based interaction.
The model has a context length of 16,384 tokens and a maximum output of 14,745 tokens. The context length provides room for prompts and supporting material within a single interaction, while the output limit sets the maximum length of a response. These specifications may suit work involving visual question answering, image descriptions, video summaries, or generating structured text from multimodal input. Tool support is relevant to workflows that use tools, and structured-output support is relevant when a response needs a defined format. The catalog does not specify particular tools, supported output schemas, or additional modalities, so those details depend on the available setup. Reka Edge is most directly suited to applications where the central task is understanding image or video content and expressing the result as text.
Key features
- Accepts image, video, and text inputs
- Produces text outputs
- Has a context length of 16,384 tokens
- Supports tools and structured outputs
- Maximum output length is 14,745 tokens
Typical uses
- Answering questions about images
- Writing image descriptions
- Summarising video content
- Generating structured text from visual input
Reka Edge pricing
US dollars, list price through OpenRouter.
| Item | Standard |
|---|---|
| Input, per 1M tokens | $0.10 |
| Output, per 1M tokens | $0.10 |
No price change since it was added on 20 Mar 2026.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0001 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.0026 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.0032 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.015 |
Reka Edge specifications
| Model id | rekaai/reka-edge |
|---|---|
| Version | reka-edge-2603 |
| Context window | 16,384 tokensAbout 12,288 English words |
| Max output | 14,745 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 20 Mar 2026 |
| Input types | image, text, video |
|---|---|
| Output types | text |
| Tool calling | Yes |
| Structured outputs | Yes |
| Reasoning effort control | No |
| Content moderation | Not applied by provider |
Sample outputs
The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.
No output has been recorded for Reka Edge yet.