# Reve 2.1 Remix — Atlas Cloud API

> Reve 2.1 Remix composes one to six reference images with a natural-language prompt into a single coherent image at native 4K, blending subject, style, and background while keeping references consistent.

This is the machine-readable API reference for **Reve 2.1 Remix** on Atlas Cloud,
a unified API platform for 400+ AI models across text, image, video, audio and 3D.

- **Model ID**: `reve-ai/reve-2.1/remix`
- **Built by**: REVE AI
- **Modality**: Image
- **Model page**: https://www.atlascloud.ai/models/reve-ai/reve-2.1/remix
- **API key**: https://www.atlascloud.ai/console/api-keys
- **Docs**: https://www.atlascloud.ai/docs

## Pricing on Atlas Cloud

- $0.24 per image
- Pay-as-you-go. No minimum spend, no subscription required.

> **These are the authoritative Atlas Cloud rates for this model.** Any price that
> appears in the vendor description further down refers to a different platform or
> a different model variant and does not apply here.

## Use this model from an AI agent

Atlas Cloud ships three first-party integration surfaces. All three authenticate
with the same API key via the `ATLASCLOUD_API_KEY` environment variable.

### MCP server

The official MCP server (`atlascloud-mcp`) exposes this model to any
MCP-compatible host — Claude Code, OpenAI Codex, Cursor, Gemini CLI, Goose,
Claude Desktop. One-line install:

```bash
# Claude Code
claude mcp add atlascloud -- npx -y atlascloud-mcp

# OpenAI Codex CLI
codex mcp add atlascloud -- npx -y atlascloud-mcp

# Gemini CLI
gemini mcp add atlascloud -- npx -y atlascloud-mcp

export ATLASCLOUD_API_KEY="your-api-key"
```

Then ask in plain English; the agent calls `atlas_generate_image` with `model: "reve-ai/reve-2.1/remix"`.
The server fetches each model's schema and validates parameters before submitting,
so invalid requests fail fast without spending credits.

MCP docs: https://www.atlascloud.ai/docs/mcp-server

### Agent Skills

`atlas-cloud-skills` is a portable skill package (API reference, code templates in
Python / Node.js / cURL, model IDs with pricing) for Claude Code, Cursor, Codex and
12+ other agents:

```bash
npx skills add AtlasCloudAI/atlas-cloud-skills
export ATLASCLOUD_API_KEY="your-api-key"
```

Skills docs: https://www.atlascloud.ai/docs/skills

### CLI

The `atlas` binary runs Atlas Cloud from a terminal or CI script. Async media jobs
are polled and downloaded automatically (use `--no-download` when a script only
needs the output URLs):

```bash
# Install (Homebrew, npm, or shell installer)
brew install AtlasCloudAI/tap/atlascloud
# npm install -g atlascloud-cli
# curl -fsSL https://raw.githubusercontent.com/AtlasCloudAI/cli/main/install.sh | sh

atlas auth login
atlas generate image reve-ai/reve-2.1/remix -p "Your prompt here"
```

CLI docs: https://www.atlascloud.ai/docs/cli

## HTTP API reference

- **Submit endpoint (POST)**: `https://api.atlascloud.ai/api/v1/model/generateImage` — start an async generation; returns a `prediction_id`
- **Poll endpoint (GET)**: `https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}` — poll this until the prediction finishes
- **Model ID**: `reve-ai/reve-2.1/remix`


## API Information

This model can be used via our HTTP API or more conveniently via our client libraries.
See the input and output schema below, as well as the usage examples.


### Input Schema

The API accepts the following input parameters:

- **`model`** (`string`, _required_):
  model name
  - Default: `"reve-ai/reve-2.1/remix"`

- **`prompt`** (`string`, _required_):
  The text description of the desired image. The maximum length is 4000 characters. You can refer to a reference image by frame: <frame>N</frame> is the Nth entry in references (0-based, so the first reference is <frame>0</frame>).

- **`images`** (`array[string]`, _required_):
  A list of reference images. Each image can be a URL or a base64-encoded image string. You must provide between 1 and 6 reference images. Refer to them in the prompt with XML <frame> tags, e.g. <frame>0</frame> for the first image.

A single image may be at most 40 MB and 33,554,432 pixels (for example 8192x4096), with neither dimension exceeding 8192 pixels. A single call may include at most 50,331,648 pixels and 100 MB of image data (after base64 decoding) across all images.

Supported input image formats:
WEBP
JPEG
PNG
GIF
TIFF (the most common flavors)
AVIF (the most common flavors)
  - Min items: 1
  - Max items: 6

- **`aspect_ratio`** (`string`, _optional_):
  The desired aspect ratio of the generated image. Use "auto" to let the model pick the most appropriate aspect ratio.
  - Default: `"auto"`
  - Options: "auto", "4:1", "3:1", "21:9", "2:1", "17:9", "16:9", "3:2", "4:3", "5:4", "1:1", "4:5", "3:4", "2:3", "9:16", "1:2", "1:3", "1:4"

- **`resolution`** (`string`, _optional_):
  The output resolution. 4k is the default resolution.
  - Default: `"4k"`
  - Options: "4k"

- **`remove_background`** (`boolean`, _optional_):
  If enabled, keeps only the central subject and makes the background of the image transparent as a post-processing step.
  - Default: `false`

- **`effects`** (`array[object]`, _optional_):
  An optional list of post-processing effects to apply to the generated image, applied in order. Each item selects one effect (grouped into the categories textures, light and color) and may override that effect's parameters. Every effect's adjustable parameters — including control type, value type, default and range — are described in x-enum-options, keyed by effect name; a parameter's "id" is the key used to set it under "parameters", "int" sliders use a -100..100 UI range and other sliders are floats. Applying effects may add cost and processing time.
  - Default: `[]`
  - Min items: 0
  - Max items: 51
  - Item properties:
    - **`effect`** (`string`, _required_):
      The post-processing effect to apply. The adjustable parameters for the selected effect are described in x-enum-options[effect].
      - Options: "cmyk_halftone", "grain", "dither", "texture_overlay", "stippling", "gameboy", "engraving", "risograph", "engraving_patterns", "halftone_texture", "color_tile", "geomosaic", "adjustments", "vignette", "radial_blur_vignette", "halation", "light_leak", "motion_blur", "radial_blur", "faceted_glass", "frosted_glass", "glow", "sparkle", "sun_rays", "tilt_shift", "chromatic_aberration", "heat_distortion", "lens_flare", "bokeh", "deep_cine_2", "neon_day", "neon_night", "neon_port", "sand_cine_3", "duotone", "clean_land", "vivid_land_1", "vivid_land_2", "vivid_port", "warm_port", "grit_mono", "low_light", "punch_day", "quiet_port", "soft_day", "soft_port", "story_mono", "code_green", "drama_cine", "retro_blue_2", "jazz_album"

    - **`parameters`** (`object`, _optional_):
      Optional parameter overrides for the selected effect, keyed by parameter id (e.g. "u_dotFrequency"). The valid keys, value types, defaults and ranges depend on "effect" and are listed in x-enum-options[effect].parameters. Omitted parameters fall back to their defaults.
      - Default: `{}`


- **`output_format`** (`string`, _optional_):
  The format of the output image.
  - Default: `"png"`
  - Options: "png", "jpeg", "webp"

- **`enable_base64_output`** (`boolean`, _optional_):
  If enabled, the output will be encoded into a BASE64 string instead of a URL. This property is only available through the API.
  - Default: `false`

- **`enable_sync_mode`** (`boolean`, _optional_):
  If set to true, the function will wait for the result to be generated and uploaded before returning the response. It allows you to get the result directly in the response. This property is only available through the API.
  - Default: `false`



**Required Parameters Example**:

```json
{
  "model": "reve-ai/reve-2.1/remix",
  "prompt": "",
  "images": [
    ""
  ]
}
```


**Full Example**:

```json
{
  "model": "reve-ai/reve-2.1/remix",
  "prompt": "",
  "images": [
    ""
  ],
  "aspect_ratio": "auto",
  "resolution": "4k",
  "remove_background": false,
  "effects": [],
  "output_format": "png",
  "enable_base64_output": false,
  "enable_sync_mode": false
}
```


### Output Schema

The API returns the following output format:


- **`code`** (`integer`, _optional_):
  HTTP status code of the response.

- **`message`** (`string`, _optional_):
  Human-readable message; non-empty on failure.

- **`data`** (`object`, _optional_):
  - Properties:
    - **`id`** (`string`, _optional_):
      Unique identifier for the prediction.

    - **`model`** (`string`, _optional_):
      Model ID used for the prediction.

    - **`outputs`** (`array[string]`, _optional_):
      Array of URLs to the generated content. Null when status is not completed.

    - **`urls`** (`object`, _optional_):
      Object containing related API endpoints.
      - Properties:
        - **`get`** (`string`, _optional_):
          URL to poll for the prediction result.


    - **`status`** (`string`, _optional_):
      Status of the task: created, processing, completed, timeout, or failed.

    - **`created_at`** (`string`, _optional_):
      ISO timestamp of when the request was created (e.g., "2023-04-01T12:34:56.789Z").

    - **`error`** (`string`, _optional_):
      Error message if the task failed, empty string otherwise.

    - **`error_code`** (`integer`, _optional_):
      Error code if the task failed.

    - **`executionTime`** (`number`, _optional_):
      Total execution time in milliseconds.

    - **`timings`** (`object`, _optional_):
      Detailed timing breakdown.
      - Properties:
        - **`inference`** (`number`, _optional_):
          Inference time in milliseconds.





**Example Response**:

```json
{
  "code": 0,
  "message": "",
  "data": {
    "id": "",
    "model": "",
    "outputs": [
      ""
    ],
    "urls": {
      "get": ""
    },
    "status": "",
    "created_at": "",
    "error": "",
    "error_code": 0,
    "executionTime": 0,
    "timings": {
      "inference": 0
    }
  }
}
```


## Usage Examples

### cURL

```bash
# Step 1: Start generation (async)
curl -X POST "https://api.atlascloud.ai/api/v1/model/generateImage" \
  -H "Authorization: Bearer $ATLASCLOUD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "reve-ai/reve-2.1/remix",
  "prompt": "",
  "images": [
    ""
  ],
  "aspect_ratio": "auto",
  "resolution": "4k",
  "remove_background": false,
  "effects": [],
  "output_format": "png",
  "enable_base64_output": false,
  "enable_sync_mode": false
}'

# Response will contain: {"code": 200, "data": {"id": "prediction_id", "status": "processing"}}

# Step 2: Poll for result (replace {prediction_id} with the id returned above)
curl -X GET "https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}" \
  -H "Authorization: Bearer $ATLASCLOUD_API_KEY"

# Keep polling until status is "completed", "succeeded" or "failed"
# When completed, outputs will contain the generated content URL(s)
```

## Additional Resources

### Documentation

- [Model Playground](https://www.atlascloud.ai/models/reve-ai/reve-2.1/remix)

## About this model

_Vendor-supplied description. Any pricing or endpoint mentioned below refers to_
_other platforms — use the Atlas Cloud values above._

### Reve 2.1 — Remix

**Developer:** Reve AI
**Model ID:** `reve-ai/reve-2.1/remix`
**Release Date:** July 9, 2026

#### Overview

Reve 2.1 Remix takes several reference images plus a natural-language prompt and composes them into a single new image at native 4K. You can pull a subject from one picture, a style from another, and a background from a third, then describe how they should come together. Rather than repainting blindly, Reve treats an image as a structured set of regions — an "image as code" approach in which style and content references stay consistent across generations, so you can maintain a look, a character, or a brand system while remixing.

This `remix` variant is the multi-image entry point to Reve 2.1: you supply between one and six reference images and reference them directly in the prompt. Use it when you want to blend or combine visual inputs — as opposed to generating from scratch (`reve-ai/reve-2.1/text-to-image`) or modifying a single image (`reve-ai/reve-2.1/edit`).

#### The Reve 2.1 Model

Reve 2.1 is an update to Reve's flagship image model that sharpens the model's visual intelligence — how well it reasons about structure, hierarchy, and spatial relationships before rendering. On public leaderboards it ranks second overall while using less than a tenth of the compute of the models ranked around it, and it remains the top-rated 4K image generator.

Its foundation is a "large layout model." Images are represented as structured regions that can be reasoned about much like code, which means controllability is built into the model's visual intelligence rather than bolted on afterward. Practical consequences of this design include:

_(Description truncated. Full text on the model page.)_

---

Atlas Cloud — one API for 400+ AI models. Model page: https://www.atlascloud.ai/models/reve-ai/reve-2.1/remix · Docs: https://www.atlascloud.ai/docs