> ## 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.

# Qwen 3.8 Flash

> Alibaba's newest Flash tier — ultra cost-efficient multimodal MoE. 1M context, vision, cheaper per token than the Max line.

## Overview

Alibaba's newest Flash tier — ultra cost-efficient multimodal MoE. 1M context, vision, cheaper per token than the Max line.

## Specs

| Field | Value |
| - | - |
| Model ID | `qwen3.8-flash` |
| Best for | High-volume multimodal chat, cheap long context |
| Context window | 1M |
| Max output tokens | 131K |
| Input modalities | Text, Image |
| Output modalities | Text |
| Tool calling | Yes |
| Structured outputs | Yes |
| Prompt caching | Yes |
| Vision | Yes |
| Reasoning | Yes |
| Speed | Fast |
| Cost band | Cheap |
| Release stage | Stable |

## Pricing

| | Per 1M tokens |
| - | :-: |
| Input | \$0.2045 |
| Output | \$0.641 |

## 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="qwen3.8-flash",
    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=strong"
```


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.