[Integrations](https://spiral.ai/integrations) › [Gemini CLI](https://spiral.ai/integrations/gemini-cli) › [Reka Edge](https://spiral.ai/integrations/gemini-cli/reka-edge)

# How to Use Reka Edge in Gemini CLI

Reka Edge is a 7B model for answering visual questions, analyzing video, locating objects, and choosing tool actions. It returns text and supports a dedicated object detection prompt, but has no dedicated reasoning mode.

|  |  |
| --- | --- |
| Model | Reka Edge |
| Available through | OpenRouter |
| Category | LLM |
| Price | Up to $0.000539 per run at the default inputs. $0.13 per 1M input tokens, $0.13 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Reka Edge in Gemini CLI

- Use Reka Edge to compare the two screenshots in this project's test fixtures. Report visible changes in layout and object placement.
- Add an image description feature to this project using Reka Edge. Ask for one sentence describing the visible scene.
- Use Reka Edge with the instruction Detect: red car on the sample image in this repository. Show the returned detection text.
- Build a video review view around Reka Edge that displays a short summary of visible actions in the project's sample clip.
- Create a comparison report using Reka Edge and three inspection images from this project's fixtures. List differences by image.

## How to set up Reka Edge in Gemini CLI

Pick the way that suits you. Each takes about two minutes.

### Use Spiral's MCP server

1. **Add the server**: Or add it to `~/.gemini/settings.json` yourself:

```bash
gemini mcp add --scope user --transport http spiral https://api.spiral.ai/mcp
```

2. **Sign in**: Start `gemini` and run:

```text
/mcp auth spiral
```

3. **Check it**: In Gemini CLI, run `/mcp`. From your shell:

```bash
gemini mcp list
```

### Use the Spiral skill

1. **Send Gemini CLI this message**: Your agent reads Spiral's skill and sets itself up.

```
set up https://spiral.ai/SKILL.md
```

2. **Sign in or paste a key**: Approve Spiral in the browser, or give the agent a key from the console.

### Use the Spiral CLI

1. **Install and sign in**: Installs the Spiral CLI, signs you in and adds its skill to your coding agents.

```bash
npx -y spiral-cli@latest init
```

### Call the Spiral API

1. **Create an API key**: In the console, under API keys.

2. **Run Reka Edge**: One request; the result comes back by polling or a webhook.

```bash
curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "openrouter",
    "model": "rekaai/reka-edge",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: Gemini CLI finds Reka Edge on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/gemini-cli

## Reka Edge tools and prices

- [Reka Edge](https://spiral.ai/tools/openrouter/rekaai/reka-edge) (OpenRouter): Up to $0.000539 per run at the default inputs. $0.13 per 1M input tokens, $0.13 per 1M output tokens.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| seed |  | — |  |
| stop |  | — |  |
| tools |  | — |  |
| top_k | 0 to … | — |  |
| top_p | 0 to 1 | — |  |
| logprobs |  | — |  |

## What can you do with Reka Edge in Gemini CLI?

Build tools that turn images and video into descriptions, comparisons, or object detections with Reka Edge. Useful projects include inspection reports, footage review tools, and applications that choose actions from visual evidence.

### Answer questions about a scene

Ask Reka Edge what is visible in a workspace or product photo. Request a short description tied to the objects shown.

### Locate named objects

Use Reka Edge with a Detect: instruction to find a described tool, vehicle, or other object in an image.

### Compare inspection photos

Give Reka Edge two or three images and ask for visible differences in object placement or scene contents.

### Summarize recorded activity

Ask Reka Edge to describe the sequence of visible actions in a video, with unclear events listed separately.

### Prepare highlight notes

Use Reka Edge to suggest moments worth reviewing in sports or event footage and describe the action that makes each useful.

### Choose actions from visual evidence

Have Reka Edge interpret a scene and propose a suitable action from a defined set of tools.

## Overview

- [OpenRouter](https://spiral.ai/providers/openrouter)
- [All Gemini CLI guides](https://spiral.ai/integrations/gemini-cli)

## Reka Edge in other agents

- [Amp](https://spiral.ai/integrations/amp/reka-edge)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/reka-edge)
- [Claude](https://spiral.ai/integrations/claude-desktop/reka-edge)
- [Claude Code](https://spiral.ai/integrations/claude-code/reka-edge)
- [Cline](https://spiral.ai/integrations/cline/reka-edge)
- [Codex](https://spiral.ai/integrations/codex/reka-edge)
- [Cursor](https://spiral.ai/integrations/cursor/reka-edge)
- [Devin](https://spiral.ai/integrations/devin/reka-edge)
- [dots](https://spiral.ai/integrations/dots/reka-edge)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/reka-edge)
- [Gemini](https://spiral.ai/integrations/gemini/reka-edge)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/reka-edge)
- [goose](https://spiral.ai/integrations/goose/reka-edge)
- [Grok](https://spiral.ai/integrations/grok/reka-edge)
- [Grok Build](https://spiral.ai/integrations/grok-build/reka-edge)
- [Hermes](https://spiral.ai/integrations/hermes/reka-edge)
- [Instinct](https://spiral.ai/integrations/instinct/reka-edge)
- [Manus](https://spiral.ai/integrations/manus/reka-edge)
- [Muse](https://spiral.ai/integrations/muse/reka-edge)
- [Muse Code](https://spiral.ai/integrations/muse-code/reka-edge)
- [n8n](https://spiral.ai/integrations/n8n/reka-edge)
- [Notion](https://spiral.ai/integrations/notion/reka-edge)
- [OpenClaw](https://spiral.ai/integrations/openclaw/reka-edge)
- [opencode](https://spiral.ai/integrations/opencode/reka-edge)
- [Perplexity](https://spiral.ai/integrations/perplexity/reka-edge)
- [Raycast](https://spiral.ai/integrations/raycast/reka-edge)
- [VS Code](https://spiral.ai/integrations/vscode/reka-edge)
- [Windsurf](https://spiral.ai/integrations/windsurf/reka-edge)
- [Zapier](https://spiral.ai/integrations/zapier/reka-edge)

## More Gemini CLI guides

- [ReMM SLERP 13B](https://spiral.ai/integrations/gemini-cli/remm-slerp-13b)
- [Reka Flash 3](https://spiral.ai/integrations/gemini-cli/reka-flash-3)
- [Qwen4 Max](https://spiral.ai/integrations/gemini-cli/qwen4-max)
- [Relace Apply 3](https://spiral.ai/integrations/gemini-cli/relace-apply-3)
- [Qwen3.8 Omni Flash](https://spiral.ai/integrations/gemini-cli/qwen3-8-omni-flash)
- [Relace Search](https://spiral.ai/integrations/gemini-cli/relace-search)

## Questions about Reka Edge in Gemini CLI

**Can Gemini CLI use Reka Edge?**

Yes. Add Spiral to Gemini CLI as an MCP server, and Gemini CLI can find and run Reka Edge like any built-in tool.

**How much does Reka Edge cost in Gemini CLI?**

Up to $0.000539 per run at the default inputs. $0.13 per 1M input tokens, $0.13 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Gemini CLI plan is separate.

**Do I need an OpenRouter account to use Reka Edge in Gemini CLI?**

No. Spiral runs Reka Edge on its own OpenRouter account. You sign in to Spiral once and never paste a key.

**How long does it take to set up Reka Edge in Gemini CLI?**

About two minutes: add the server, then sign in, then check it.

**Does Gemini CLI wait while Reka Edge runs?**

Reka Edge runs in the background. Gemini CLI starts the run, checks on it and gives you the text, json when it's ready.

**What is Reka Edge best suited for?**

Reka Edge focuses on image and video understanding, object detection, and tool use. Useful tasks include answering questions about a scene, summarizing visible actions, and locating a named object.

**Can Reka Edge generate images or videos?**

Reka Edge generates text from text, images, or video. Use it for descriptions, analysis, and instructions based on visual content.

**How many images can Reka Edge compare at once?**

Reka's documentation specifies at most three images per prompt. For a comparison, label each image and ask about specific objects, positions, or visible changes.

**How much context does Reka Edge support?**

Reka Edge has a 16,384-token context window. Keep requests focused on the material needed to answer the question.

**How should I ask Reka Edge to locate an object?**

Use Reka's detection instruction, such as “Detect: red car.” Describe the target with concrete details such as color, clothing, or position.

