> For the complete documentation index, see [llms.txt](https://docs.ionos.com/cloud/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.ionos.com/cloud/ai/ai-model-hub/models/coding-models/qwen3-coder-next-80b.md).
# Qwen3 Coder Next 80B
**Summary:** Qwen3-Coder-Next 80B is a state-of-the-art coding model from Alibaba Cloud, engineered for advanced software development tasks with native support for reasoning and tool calling. This model is specialized for code generation, completion, debugging, refactoring, and multi-step agentic coding workflows, supporting an extensive range of programming languages, frameworks, and tools. Its large parameter count and extended context window make it ideal for complex enterprise development scenarios, automated code review pipelines, and AI-assisted software engineering at scale.
| **Intelligence** | **Speed** | **Input** | **Output** |
| :---------------------------------------------------------------------------------------------------------------------------------------------------------: | :---------------------------------------------------------------------------------------: | :---------------------------------------------------------------------------------------------------------------------------------------: | :---------------------------------------------------------------------------------------------------------------------------------------: |
|    |   |    |    |
| *High* | *Medium* | *Text* | *Text* |
## Central parameters
**Description:** Medium-sized coding-specialized model with 80B parameters from Alibaba Cloud, optimized for code generation, agentic programming workflows, and multi-language software development tasks.
**Model identifier:** `Qwen/Qwen3-Coder-Next`
## IONOS CLOUD AI Model Hub Lifecycle and Alternatives
| **IONOS CLOUD start date** | **End of Life** | **Alternative** | **Successor** |
| :------------------------: | :-------------: | :-------------: | :-----------: |
| *March 30, 2026* | N/A | | |
## Origin
| **Provider** | **Country** | **License** | **Flavor** | **Release** |
| :---------------------------------------------------------------------------------: | :---------: | :--------------------------------------------------------------------------------------------: | :--------: | :-----------------: |
| [**Alibaba Cloud**](https://www.alibabacloud.com/) | China | [**Apache 2.0**](https://www.apache.org/licenses/LICENSE-2.0) | Instruct | *February 10, 2026* |
## Technology
| **Context window** | **Parameters** | **Quantization** | **Multilingual** | **Further details** |
| :----------------: | :------------: | :--------------: | :--------------: | :-------------------------------------------------------------------------------------------------------------: |
| *256k* | *80B* | *int4* | *Yes* | [**Hugging Face**](https://huggingface.co/bullpoint/Qwen3-Coder-Next-AWQ-4bit) |
## Modalities
| **Text** | **Image** | **Audio** |
| :--------------: | :-----------: | :-----------: |
| Input and output | Not supported | Not supported |
## Endpoints
| **Chat Completions** | **Embeddings** | **Image generation** |
| :------------------: | :------------: | :------------------: |
| v1/chat/completions | Not supported | Not supported |
## Features
| **Streaming** | **Reasoning** | **Tool calling** |
| :-----------: | :-----------: | :--------------: |
| Supported | Not supported | Supported |
### Tool calling: use `strict` for reliable tool names
Qwen3-Coder-Next supports [Tool Calling](/cloud/ai/ai-model-hub/how-tos/tool-calling.md). For the most reliable results, set `"strict": true` inside each tool's `function` object and `"additionalProperties": false` on its `parameters`.
With `strict` activated, the model generates the tool call against your schema, so the returned `function.name` is always one of the tools you registered. Without it, the model occasionally returns a name that is not a registered tool — often a value taken from one of your parameter descriptions. Agent frameworks that match tool names exactly will silently drop those calls, which can leave an agent loop stuck without any error.
{% hint style="warning" %}
**Warning:** `strict` belongs **inside** the `function` object, alongside `name` and `parameters`. Placing it one level up, next to `"type": "function"`, has no effect.
{% endhint %}
#### Request
```json
{
"model": "Qwen/Qwen3-Coder-Next",
"messages": [
{
"role": "user",
"content": "What is the current status of the repository?"
}
],
"tools": [
{
"type": "function",
"function": {
"name": "repository_tool",
"description": "Runs a read-only inspection command inside the working repository.",
"strict": true,
"parameters": {
"type": "object",
"properties": {
"action": {
"type": "string",
"description": "The inspection to run.",
"enum": ["status", "diff", "list_files"]
},
"path": {
"type": "string",
"description": "Path to inspect. Use \".\" for the repository root."
}
},
"required": ["action", "path"],
"additionalProperties": false
}
}
}
],
"max_tokens": 1000
}
```
#### Response (shortened for readability)
```json
{
"choices": [
{
"message": {
"role": "assistant",
"tool_calls": [
{
"id": "chatcmpl-tool-a1b2c3d4",
"type": "function",
"function": {
"name": "repository_tool",
"arguments": "{\"action\": \"status\", \"path\": \".\"}"
}
}
]
},
"finish_reason": "tool_calls"
}
]
}
```
Changing `tool_choice` is not required. Leaving it unset (or `"auto"`) keeps the default behaviour, so the model can still answer conversationally when no tool is required, which lets an agent signal that it has finished. `strict` only constrains the shape of a tool call when one is made.
## Rate limits
Rate limits ensure fair usage and reliable access to the AI Model Hub. In addition to the [contract-wide rate limits](/cloud/ai/ai-model-hub/how-tos/rate-limits.md), no model-specific limits apply.
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:
```
GET https://docs.ionos.com/cloud/ai/ai-model-hub/models/coding-models/qwen3-coder-next-80b.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.