# Qwen3.8-2.4T-A95B

> Sparse mixture-of-experts reasoning model from Alibaba's Qwen team, with tool calling and structured output.

## Key facts

- Model author: Qwen
- Input: $2.00 per 1M tokens
- Output: $6.00 per 1M tokens
- Context window: 1,048,576 tokens
- Input modalities: text
- Output modalities: text
- Capabilities: reasoning, structured_output, tools
- Released: 2026-08-12
- Model IDs: `qwen/qwen3.8-2.4t-a95b`
- Model page: https://www.realrelay.ai/model/qwen/qwen3.8-2.4t-a95b

## Overview

Qwen3.8-2.4T-A95B is a sparse mixture-of-experts model from Alibaba's Qwen team, with 95 billion active parameters out of 2.4 trillion in total. It takes text in and returns text, with reasoning, tool calling and structured output. It is a text-only model, so requests and responses carry no images or audio.

It has a 1,048,576-token context window. It accepts text input and returns text. It was released on August 12, 2026.

## Capabilities

Qwen3.8-2.4T-A95B supports tool calling, reasoning and structured output. It accepts text input and returns text.

The sparse design means only 95 billion of the 2.4 trillion parameters are active for each token. Combined with tool calling and structured output, the text interface lets applications drive the model with function definitions and receive results in a fixed format.

## Pricing

Qwen3.8-2.4T-A95B costs $2.00 per 1M input tokens and $6.00 per 1M output tokens. Qwen3.8-2.4T-A95B is available through RealRelay's OpenAI-compatible API.

## Use cases

Use Qwen3.8-2.4T-A95B for text agents that reason through a task, call the tools you define and return results as structured output.

Its context window of 1,048,576 tokens also suits long-document analysis, such as reading a large report or a codebase in one request and answering questions about it. Reasoning support helps when answers depend on several steps.

## Call it

OpenAI-compatible chat completions:

```bash
curl https://www.realrelay.ai/v1/chat/completions \
  -H "Authorization: Bearer $REALRELAY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "qwen/qwen3.8-2.4t-a95b", "messages": [{"role": "user", "content": "Hello"}]}'
```

## FAQ

### What is Qwen3.8-2.4T-A95B?

Qwen3.8-2.4T-A95B is a sparse mixture-of-experts model from Alibaba's Qwen team, with 95 billion active parameters out of 2.4 trillion in total.

### How much does Qwen3.8-2.4T-A95B cost?

Qwen3.8-2.4T-A95B costs $2.00 per 1M input tokens and $6.00 per 1M output tokens.

### What is the context window of Qwen3.8-2.4T-A95B?

Qwen3.8-2.4T-A95B has a 1,048,576-token context window.

### What inputs and outputs does Qwen3.8-2.4T-A95B support?

Qwen3.8-2.4T-A95B accepts text input and returns text.

### Does Qwen3.8-2.4T-A95B support tool calling?

Yes. Qwen3.8-2.4T-A95B supports tool calling, reasoning and structured output.

### When was Qwen3.8-2.4T-A95B released?

Qwen3.8-2.4T-A95B was released on August 12, 2026.

### How do I call Qwen3.8-2.4T-A95B via the API?

Send requests to RealRelay's OpenAI-compatible API with the model ID qwen/qwen3.8-2.4t-a95b to use Qwen3.8-2.4T-A95B.