# Qwen3-Coder-Next

> Open-weight Alibaba language model optimized for coding agents and local development workflows.

## Key facts

- Model author: Qwen
- Input: $0.30 per 1M tokens (starting tier)
- Output: $1.50 per 1M tokens (starting tier)
- Context window: 256,000 tokens
- Input modalities: text
- Output modalities: text
- Capabilities: reasoning, structured_output, tools
- Released: 2026-02-04
- Model IDs: `qwen/qwen3-coder-next`
- Model page: https://www.realrelay.ai/model/qwen/qwen3-coder-next

## Overview

Qwen3-Coder-Next is an open-weight causal language model from Alibaba, optimized for coding agents and local development workflows. It uses a sparse mixture-of-experts design that activates only a small share of its parameters per token, and it takes text in and returns text.

It has a 256K-token context window. It accepts text input and returns text. It was released on February 4, 2026. Its weights are open.

## Capabilities

Qwen3-Coder-Next supports tool calling, reasoning and structured output. It accepts text input and returns text.

As a model tuned for coding agents, it pairs tool calling with reasoning and structured output, so an agent can call tools, work through a task and return results in a fixed format. Its open weights and sparse design are aimed at local development as well as hosted use.

## Pricing

Pricing for Qwen3-Coder-Next starts from $0.30 per 1M input tokens and $1.50 per 1M output tokens. Pricing is tiered, so these figures are the starting tier. Qwen3-Coder-Next is available through RealRelay's OpenAI-compatible API.

## Use cases

Use Qwen3-Coder-Next to drive coding agents that read code, call tools to edit and test it, and report their results as structured output.

Because it is optimized for local development workflows and ships open weights, it also suits teams that prototype an agent against the hosted API and later run the same model in their own environment.

## 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-coder-next", "messages": [{"role": "user", "content": "Hello"}]}'
```

## FAQ

### What is Qwen3-Coder-Next?

Qwen3-Coder-Next is an open-weight causal language model from Alibaba, optimized for coding agents and local development workflows.

### How much does Qwen3-Coder-Next cost?

Pricing for Qwen3-Coder-Next starts from $0.30 per 1M input tokens and $1.50 per 1M output tokens. Pricing is tiered, so these figures are the starting tier.

### What is the context window of Qwen3-Coder-Next?

Qwen3-Coder-Next has a 256K-token context window.

### What inputs and outputs does Qwen3-Coder-Next support?

Qwen3-Coder-Next accepts text input and returns text.

### Does Qwen3-Coder-Next support tool calling?

Yes. Qwen3-Coder-Next supports tool calling, reasoning and structured output.

### When was Qwen3-Coder-Next released?

Qwen3-Coder-Next was released on February 4, 2026.

### How do I call Qwen3-Coder-Next via the API?

Send requests to RealRelay's OpenAI-compatible API with the model ID qwen/qwen3-coder-next to use Qwen3-Coder-Next.