---
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](https://assets.runware.ai/covers/meta-llava-1-6-mistral-7b.jpg)

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.

- **Status**: live
- **ID**: `meta-llava-1-6-mistral-7b`
- Try in Playground
- **Release Date**: January 31, 2024
- **Zero Data Retention**: Yes
- **Capabilities**: Image to Text, Caption, Checkpoint

## Pricing

$0.003 from, per run · ~18s per request

**Measured runs**

- 1024×1024 input: `$0.003` (~5s)

**4 example generations**

- [caption](https://runware.ai/docs/models/meta-llava-1-6-mistral-7b/examples#example-restaurant-editorial-image-caption): `$0.0032` (~15s)
- [caption](https://runware.ai/docs/models/meta-llava-1-6-mistral-7b/examples#example-offshore-wind-editorial-caption): `$0.0032` (~32s)
- [caption](https://runware.ai/docs/models/meta-llava-1-6-mistral-7b/examples#example-residential-water-damage-assessment): `$0.0032` (~22s)
- [caption](https://runware.ai/docs/models/meta-llava-1-6-mistral-7b/examples#example-runway-show-accessibility-description): `$0.0045` (~18s)

billed by compute time, so a request costs what it took · times vary, measured end to end · [How pricing works](https://runware.ai/docs/models-api/pricing)

## 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.

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

- **Type**: `string`
- **Format**: `uri`

Webhook URL that receives JSON responses 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/models-api/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 results directly in the API response. Over HTTP, a task still running after 120 seconds continues as an async task and comes back with status 'processing'. Poll for its results using getResponse.
- `async` Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse.

**Learn more** (1 resource):

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

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

- **Type**: `boolean`

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).

**Core Parameters**

Primary parameters that define the task output.

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

- **Type**: `string`
- **Required**: true
- **Value**: `meta-llava-1-6-mistral-7b`

Send `auto` instead of an AIR identifier to have the model router choose the model for this task. The rest of the request is unchanged, every value you send is kept, and only the parameters you leave out are filled in. See [Model Router](https://runware.ai/docs/models-api/model-router).

**Learn more** (3 resources):

- [Text To Image: Model Selection](https://runware.ai/docs/learn/text-to-image#model-selection) (learn)
- [Image Inpainting: Model Specialized Inpainting Models](https://runware.ai/docs/learn/image-inpainting#model-specialized-inpainting-models) (learn)
- [Image Outpainting: Other Critical Parameters](https://runware.ai/docs/learn/image-outpainting#other-critical-parameters) (learn)

### [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`

Identifier for the type of task this response belongs to.

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

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

UUID v4 identifier echoed from the original request, used to match async responses to their tasks.

### [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

### caption (caption)

```
In the heart of a bustling kitchen, a trio of chefs, clad in pristine white chef jackets, are immersed in the art of culinary creation. The chef in the foreground, poised with a plate of food in hand, is meticulously plating a dish that showcases a piece of fish, its surface glistening with a vibrant green sauce, accompanied by a medley of vegetables.
```

```json
{
  "taskType": "caption",
  "taskUUID": "f4992123-435d-478a-afef-5eb33651e25f",
  "model": "runware:150@2",
  "prompt": "Write an accurate, detailed description of this image for a culinary magazine's accessible digital edition. Identify the visible people, their positions and actions, the plated food, kitchen tools, background activity, lighting, colors, and overall atmosphere. Describe only details supported by the image, avoid guessing identities or personal attributes, and present the result as one polished paragraph.",
  "inputs": {
    "image": "https://assets.runware.ai/assets/inputs/9681ace7-520d-4dbc-b1cc-ff429532b61f.jpg"
  }
}
```

---

### caption (caption)

```
Two offshore workers in red suits and helmets are performing maintenance on a wind turbine platform. They are using a yellow ladder to ascend the structure, with one worker holding onto the ladder while the other appears to be securing a cable or hose. The platform is situated in a vast body of water, with the horizon visible in the distance. The sky is overcast, and the lighting suggests it could be early morning or late afternoon.
```

```json
{
  "taskType": "caption",
  "taskUUID": "9c2af25e-236d-4784-b475-2b485d513d60",
  "model": "runware:150@2",
  "prompt": "Write an accurate, detailed editorial caption for this photograph. Identify the visible subjects, setting, actions, safety equipment, weather, lighting, and relevant background details. Use clear photojournalistic language and present tense. Do not invent names, dates, locations, company affiliations, or facts that cannot be verified from the image.",
  "inputs": {
    "image": "https://assets.runware.ai/assets/inputs/ba0836fd-2463-4fd3-bca1-aaedda012726.jpg"
  }
}
```

---

### caption (caption)

```
The image depicts an interior space that appears to be a kitchen, with visible signs of water damage and possible mold growth. The ceiling is damaged, with a significant area missing, exposing the underside of the ceiling material. There is visible discoloration and staining on the ceiling, indicating water damage. The ceiling material is peeling away, revealing the underlying structure.
```

```json
{
  "taskType": "caption",
  "taskUUID": "c4b9c5b2-3932-4d79-b5f5-a99c9140d108",
  "model": "runware:150@2",
  "prompt": "Provide an accurate, detailed description of this property-damage image for an insurance claim record. Identify the room, visible people and their actions, apparent source area, affected building materials and fixtures, debris, moisture indicators, and the location and extent of observable damage. Distinguish direct visual evidence from reasonable but uncertain inferences. Do not estimate repair costs or claim damage that cannot be seen.",
  "inputs": {
    "image": "https://assets.runware.ai/assets/inputs/8844426b-c59f-4d94-a1f3-e158cdbd79c4.jpg"
  }
}
```

---

### caption (caption)

```
In the image, a fashion show is taking place in a spacious, modern venue with a minimalist aesthetic. The runway is illuminated by a series of linear lights that cast a soft glow on the models and the audience. The main subjects are two models walking down the runway. The first model is wearing a striking blue dress that cascades down to form a train behind her.
```

```json
{
  "taskType": "caption",
  "taskUUID": "957b38ea-aba1-4bd6-a40a-ebb0b85a8872",
  "model": "runware:150@2",
  "prompt": "Write an accurate, detailed accessibility description of this image for a fashion publication. Identify the main subjects, clothing, mobility aids, actions, setting, composition, lighting, colors, and relevant background activity. Describe only details that are visually supported; do not guess identities, brands, medical conditions, or personal histories.",
  "inputs": {
    "image": "https://assets.runware.ai/assets/inputs/c9abe766-ea6b-4166-b11f-4827ed9b8303.jpg"
  }
}
```