> ## Documentation Index
> Fetch the complete documentation index at: https://docs.kymaapi.com/llms.txt
> Use this file to discover all available pages before exploring further.

# DeepSeek V4 Flash Vision

> Experimental vision-enabled release of DeepSeek V4 Flash (open weights, MIT, 305B MoE) — the same efficiency tier with image input. DeepSeek labels it experimental; expect the id to move when a stable release lands.

## Overview

`deepseek-v4-flash-vision-exp` — Experimental vision-enabled release of DeepSeek V4 Flash (open weights, MIT, 305B MoE) — the same efficiency tier with image input. DeepSeek labels it experimental; expect the id to move when a stable release lands.

## Specs

| Field              | Value                                           |
| ------------------ | ----------------------------------------------- |
| Model ID           | `deepseek-v4-flash-vision-exp`                  |
| Best for           | Cheap multimodal reasoning on the V4 Flash line |
| Context window     | 1.048576M                                       |
| Max output tokens  | 384K                                            |
| Input modalities   | Text, Image                                     |
| Output modalities  | Text                                            |
| Tool calling       | Yes                                             |
| Structured outputs | Yes                                             |
| Prompt caching     | No                                              |
| Speed              | Fast                                            |
| Cost band          | Cheap                                           |
| Release stage      | Preview                                         |

## Pricing

|        | Per 1M tokens |
| ------ | :-----------: |
| Input  |    \$0.297    |
| Output |    \$0.891    |

## Example

```python theme={null}
from openai import OpenAI

client = OpenAI(base_url="https://kymaapi.com/v1", api_key="kyma-...")

response = client.chat.completions.create(
    model="deepseek-v4-flash-vision-exp",
    messages=[{"role": "user", "content": "..."}],
    tools=[...],  # function calling supported
)
```

## Agent query example

Ask the API which models fit, instead of hardcoding an id:

```bash theme={null}
curl "https://kymaapi.com/v1/models?recommended_for=chat&tools=true&quality_tier=efficient"
```