---
title: LLaVA-1.6-Mistral-7B | Runware Docs
url: https://runware.ai/docs/models/meta-llava-1-6-mistral-7b
description: Vision-language model for image understanding and captioning
---
# LLaVA-1.6-Mistral-7B

LLaVA-1.6-Mistral-7B is a multimodal vision-language model that processes images alongside text to generate descriptive and reasoning-based responses. It enables image captioning and visual understanding by combining a vision encoder with a Mistral 7B language backbone.

- **ID**: `runware:150@2`
- **Status**: live
- **Release Date**: January 31, 2024
- **Capabilities**: Image to Text, Caption

## Pricing

- **80 - 100 tokens**: `$0.0019`

## Request Parameters

**API Options**

Platform-level options for task execution and delivery.

### [taskType](https://runware.ai/docs/models/meta-llava-1-6-mistral-7b#request-tasktype)

- **Type**: `string`
- **Required**: true
- **Value**: `caption`

Identifier for the type of task being performed

### [taskUUID](https://runware.ai/docs/models/meta-llava-1-6-mistral-7b#request-taskuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID v4 identifier for tracking tasks and matching async responses. Must be unique per task.

### [outputType](https://runware.ai/docs/models/meta-llava-1-6-mistral-7b#request-outputtype)

- **Type**: `string`
- **Default**: `URL`

Image output type.

**Allowed values**: `URL` `base64Data` `dataURI`

### [outputFormat](https://runware.ai/docs/models/meta-llava-1-6-mistral-7b#request-outputformat)

- **Type**: `string`
- **Default**: `JPG`

Specifies the file format of the generated output. The available values depend on the task type and the specific model's capabilities.

- \`JPG\`: Best for photorealistic images with smaller file sizes (no transparency).
- \`PNG\`: Lossless compression, supports high quality and transparency (alpha channel).
- \`WEBP\`: Modern format providing superior compression and transparency support.

> [!NOTE]
> \*\*Transparency\*\*: If you are using features like background removal or LayerDiffuse that require transparency, you must select a format that supports an alpha channel (e.g., \`PNG\`, \`WEBP\`, \`TIFF\`). \`JPG\` does not support transparency.

**Allowed values**: `JPG` `PNG` `WEBP`

### [outputQuality](https://runware.ai/docs/models/meta-llava-1-6-mistral-7b#request-outputquality)

- **Type**: `integer`
- **Min**: `20`
- **Max**: `99`
- **Default**: `95`

Compression quality of the output. Higher values preserve quality but increase file size.

### [webhookURL](https://runware.ai/docs/models/meta-llava-1-6-mistral-7b#request-webhookurl)

- **Type**: `string`
- **Format**: `URI`

Specifies a webhook URL where JSON responses will be sent via HTTP POST when generation tasks complete. For batch requests with multiple results, each completed item triggers a separate webhook call as it becomes available.

**Learn more** (1 resource):

- [Webhooks](https://runware.ai/docs/platform/webhooks) (platform)

### [deliveryMethod](https://runware.ai/docs/models/meta-llava-1-6-mistral-7b#request-deliverymethod)

- **Type**: `string`
- **Default**: `sync`

Determines how the API delivers task results.

**Allowed values**:

- `sync` Returns complete results directly in the API response.
- `async` Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse.

**Learn more** (1 resource):

- [Task Polling](https://runware.ai/docs/platform/task-polling) (platform)

### [uploadEndpoint](https://runware.ai/docs/models/meta-llava-1-6-mistral-7b#request-uploadendpoint)

- **Type**: `string`
- **Format**: `URI`

Specifies a URL where the generated content will be automatically uploaded using the HTTP PUT method. The raw binary data of the media file is sent directly as the request body. For secure uploads to cloud storage, use presigned URLs that include temporary authentication credentials.

**Common use cases:**

- **Cloud storage**: Upload directly to S3 buckets, Google Cloud Storage, or Azure Blob Storage using presigned URLs.
- **CDN integration**: Upload to content delivery networks for immediate distribution.

```text
// S3 presigned URL for secure upload
https://your-bucket.s3.amazonaws.com/generated/content.mp4?X-Amz-Signature=abc123&X-Amz-Expires=3600

// Google Cloud Storage presigned URL
https://storage.googleapis.com/your-bucket/content.jpg?X-Goog-Signature=xyz789

// Custom storage endpoint
https://storage.example.com/uploads/generated-image.jpg
```

The content data will be sent as the request body to the specified URL when generation is complete.

### [ttl](https://runware.ai/docs/models/meta-llava-1-6-mistral-7b#request-ttl)

- **Type**: `integer`
- **Min**: `60`

Time-to-live (TTL) in seconds for generated content. Only applies when `outputType` is `URL`.

### [includeCost](https://runware.ai/docs/models/meta-llava-1-6-mistral-7b#request-includecost)

- **Type**: `boolean`
- **Default**: `false`

Include task cost in the response.

**Inputs**

Input resources for the task (images, audio, etc). These must be nested inside the \`inputs\` object.

### [image](https://runware.ai/docs/models/meta-llava-1-6-mistral-7b#request-inputs-image)

- **Path**: `inputs.image`
- **Type**: `string`
- **Required**: true

Image input (UUID, URL, Data URI, or Base64).

**Generation Parameters**

Core parameters for controlling the generated content.

### [model](https://runware.ai/docs/models/meta-llava-1-6-mistral-7b#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `runware:150@2`

Identifier of the model to use for generation.

**Learn more** (3 resources):

- [Text To Image: Model Selection The Foundation Of Generation](https://runware.ai/docs/guides/text-to-image#model-selection-the-foundation-of-generation) (guide)
- [Image Inpainting: Model Specialized Inpainting Models](https://runware.ai/docs/guides/image-inpainting#model-specialized-inpainting-models) (guide)
- [Image Outpainting: Other Critical Parameters](https://runware.ai/docs/guides/image-outpainting#other-critical-parameters) (guide)

### [prompt](https://runware.ai/docs/models/meta-llava-1-6-mistral-7b#request-prompt)

- **Type**: `string`

Instructions or questions to guide the image analysis.

## Response Parameters

### [taskType](https://runware.ai/docs/models/meta-llava-1-6-mistral-7b#response-tasktype)

- **Type**: `string`
- **Required**: true
- **Value**: `caption`

Type of the task.

### [taskUUID](https://runware.ai/docs/models/meta-llava-1-6-mistral-7b#response-taskuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID of the task.

### [text](https://runware.ai/docs/models/meta-llava-1-6-mistral-7b#response-text)

- **Type**: `string`
- **Required**: true

Generated caption text describing the input.

### [cost](https://runware.ai/docs/models/meta-llava-1-6-mistral-7b#response-cost)

- **Type**: `float`

Task cost in USD. Present when `includeCost` is set to `true` in the request.

## Examples

### Tidepool Robot Tea Picnic (Caption)

**Request**:

```json
{
  "taskType": "caption",
  "taskUUID": "8b27a5b6-eeab-4ee3-a998-0daa0ae48c95",
  "model": "runware:150@2",
  "prompt": "Describe this image in 3-5 vivid sentences, identifying the main subject, setting, notable objects, mood, and any surprising visual details.",
  "inputs": {
    "image": "https://assets.runware.ai/assets/inputs/3a69fc0c-d298-4fb2-82d8-46074743fa4e.jpg"
  }
}
```

**Response**:

```json
{
  "taskType": "imageCaption",
  "taskUUID": "8b27a5b6-eeab-4ee3-a998-0daa0ae48c95",
  "text": "The image presents a whimsical beach scene featuring a robot sitting on a red and white checkered blanket. The robot, with its friendly face and arms, is the main subject of the image. It is positioned under a large blue and white striped umbrella, which provides shade for the robot and the two cups of coffee placed on the blanket. The beach setting is characterized by sandy shores and a calm sea, with a few seagulls scattered in the background.",
  "cost": 0.0019
}
```

---

### Abandoned Library Chess Table (Caption)

**Request**:

```json
{
  "taskType": "caption",
  "taskUUID": "44083438-c1e5-4d76-81d5-ad98c39f4a45",
  "model": "runware:150@2",
  "prompt": "Provide a vivid caption for this image in 2-3 sentences, identifying the main setting, notable objects, lighting, mood, and any implied story suggested by the scene.",
  "inputs": {
    "image": "https://assets.runware.ai/assets/inputs/f201b6da-5fb3-49b7-ada8-dd45295bd014.jpg"
  }
}
```

**Response**:

```json
{
  "taskType": "imageCaption",
  "taskUUID": "44083438-c1e5-4d76-81d5-ad98c39f4a45",
  "text": "In this image, a cozy library scene is captured, with a cat comfortably sleeping on a stack of books. The room is illuminated by a warm, golden light, creating a serene and inviting atmosphere. The presence of a chess set on a table suggests a quiet, intellectual setting, perhaps hinting at the cat's owner's love for the game.",
  "cost": 0.0019
}
```

---

### Deserted Planetarium Classroom Display (Image to Text)

**Request**:

```json
{
  "taskType": "caption",
  "taskUUID": "96c350a1-866b-4685-8bcc-14332636a36d",
  "model": "runware:150@2",
  "prompt": "Provide a detailed caption for this image, describing the setting, notable objects, lighting, mood, and any unusual visual contrasts.",
  "inputs": {
    "image": "https://assets.runware.ai/assets/inputs/3fcf73ee-d1f6-40cd-89c6-9d9aa58c93e0.jpg"
  }
}
```

**Response**:

```json
{
  "taskType": "imageCaption",
  "taskUUID": "96c350a1-866b-4685-8bcc-14332636a36d",
  "text": "The image presents a classroom setting that has been transformed into a surreal and otherworldly environment. The room is filled with rows of wooden desks, each equipped with an open book, suggesting a space for learning and study. The desks are arranged in a traditional classroom layout, with a teacher's desk positioned at the front of the room. The most striking feature of the room is the ceiling, which has been transformed into a night sky filled with planets and stars.",
  "cost": 0.0019
}
```

---

### Deserted Carnival Under Eclipse (Caption)

**Request**:

```json
{
  "taskType": "caption",
  "taskUUID": "34c2fd43-f5b5-4f24-b96e-ecc91d72bfb1",
  "model": "runware:150@2",
  "prompt": "Describe this image in 3-5 sentences, identifying the main setting, notable objects, lighting conditions, and the overall mood. Mention any details that suggest a story.",
  "inputs": {
    "image": "https://assets.runware.ai/assets/inputs/499fccbc-e073-421b-be25-81d8c6ad385a.jpg"
  }
}
```

**Response**:

```json
{
  "taskType": "imageCaption",
  "taskUUID": "34c2fd43-f5b5-4f24-b96e-ecc91d72bfb1",
  "text": "The image depicts a desolate carnival at dusk, with a large Ferris wheel standing tall in the background. The ground is covered in cracked earth, and a few tattered teddy bears are scattered around, adding to the abandoned feel of the scene. The sky is dark, with a large, ominous black sun looming in the center, casting an eerie glow over the entire landscape.",
  "cost": 0.0019
}
```