Alibaba

Qwen3-Coder-Next

Text

Retired Retired on 2026-10-10.

Open-weight Qwen coding model for agents (3B active); 256K context; OpenAI-compatible API

Retired Qwen3-Coder-Next API reference →

Get API Key

Model health Insufficient data

runapi.ai

# Base URL
https://runapi.ai

# Endpoints
POST /v1/chat/completions
POST /v1/responses
POST /v1/messages
POST /v1beta/models/qwen3-coder-next:generateContent
POST /v1beta/models/qwen3-coder-next:streamGenerateContent

curl https://runapi.ai/v1/chat/completions \
  -H "Authorization: Bearer $RUNAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "qwen3-coder-next",
  "messages": [
    {
      "role": "user",
      "content": "Read this screenshot of a failing dashboard, explain what the error message means, and suggest the code change that would fix it."
    }
  ]
}'

from openai import OpenAI

client = OpenAI(
    base_url="https://runapi.ai/v1",
    api_key="your-runapi-key"
)

response = client.chat.completions.create(
    model="qwen3-coder-next",
    messages=[{"role": "user", "content": "Read this screenshot of a failing dashboard, explain what the error message means, and suggest the code change that would fix it."}]
)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://runapi.ai/v1",
  apiKey: "your-runapi-key"
});

const response = await client.chat.completions.create({
  model: "qwen3-coder-next",
  messages: [{ role: "user", content: "Read this screenshot of a failing dashboard, explain what the error message means, and suggest the code change that would fix it." }]
});

https://runapi.ai 5 endpoints

9 versions available

OVERVIEW

What Qwen3-Coder-Next is built for

Qwen3-Coder-Next is an open-weight coding model from Alibaba Qwen, released under Apache 2.0 on February 3, 2026. It is built on Qwen3-Next-80B-A3B, a sparse Mixture-of-Experts model with hybrid attention that has 80B total parameters and 3B active per token. Qwen trained it for coding agents and repository-level work.

Qwen's model card says it runs in non-thinking mode only and does not produce thinking blocks, so a response starts with the answer or the tool call. Alibaba's API serves it with a 262,144-token context window, up to 204,800 input tokens, and up to 65,536 output tokens.

On RunAPI, call qwen3-coder-next through the OpenAI-compatible Chat Completions endpoint (/v1/chat/completions) with an OpenAI SDK pointed at https://runapi.ai/v1. It takes text input. Tools use the standard OpenAI tools format, and the model returns tool_calls in the response.

Model ID

qwen3-coder-next

Released

February 3, 2026

Architecture

MoE, 80B total / 3B active, Apache 2.0 weights

Context window

262,144 tokens

Max output

65,536 tokens

Thinking

None (non-thinking only)

Endpoint on RunAPI

OpenAI Chat Completions, text input

Specifications

Provider	Alibaba
Model ID	qwen3-coder-next
Modality	Text
Task types	Synchronous
API endpoint	/v1/chat/completions
	/v1/responses

	/v1/messages
	/v1beta/models/qwen3-coder-next:generateContent
	/v1beta/models/qwen3-coder-next:streamGenerateContent
Billing unit	1K tokens
Catalog status	Retired

HOW IT WORKS

Use This Model in 3 Steps

Get Your Key

Sign up for free and create an API key for qwen3-coder-next from the dashboard.
Send a Request

POST to /v1/chat/completions with the qwen3-coder-next model slug and your parameters.
Get Results

Read the completed qwen3-coder-next response directly from the endpoint.

What this model offers

Endpoint coverage

Exposes 1 public endpoint(s): chat_completion.

Usage-based billing

Metered by 1K tokens with no subscription requirement.

API REFERENCE

Endpoint Specification

Endpoint: POST /v1/chat/completions
Model ID: qwen3-coder-next
Task Types: chat_completion

Request parameters

No request parameters are published for this endpoint.

USE CASES

Customer support

Answer customer questions from a private knowledge base, reducing ticket volume.

Document analysis

Draft contract summaries and flag key clauses for attorney review.

Code generation

Auto-generate unit tests, code reviews, and refactoring suggestions in CI.

FAQ

Frequently asked questions about Qwen3-Coder-Next

What is Qwen3-Coder-Next built for?

Coding agents and repository-level work, such as reading a codebase, editing several files, and calling tools in a loop. Qwen reports SWE-Bench-Pro results comparable to models with 10 to 20 times more active parameters.

Does qwen3-coder-next support tool calling?

Yes. Send tools in the OpenAI format on Chat Completions and the model returns tool_calls. Qwen's model card describes tool calling as one of the model's main strengths.

Does Qwen3-Coder-Next have a thinking mode?

No. Qwen's model card says it supports non-thinking mode only and does not generate thinking blocks. If a task needs a reasoning step, use a Qwen3.5 or Qwen3.6 model, which have a thinking mode.

How many parameters does Qwen3-Coder-Next use per token?

3B of its 80B parameters are active for each token. The model is built on Qwen3-Next-80B-A3B, which combines a sparse Mixture-of-Experts design with hybrid attention.

How do I select qwen3-coder-next?

Pass the model ID shown in the quickstart.

What's the rate limit on this variant?

Per-key rate limits scale with your usage tier. The pricing page shows current limits. If you need higher throughput, contact support to discuss tier upgrades.

Can I switch variants later?

Yes. Variant is a parameter in the request. Switch by changing the model ID — no code changes, no re-authentication, no separate billing setup. All variants share the same API key and request shape.

Does it stream?

Where streaming is available, RunAPI streams end-to-end. LLM models support token-level streaming. Media models use async task polling or webhook callbacks for result delivery.

Where do I report quality issues?

Open an issue on the public GitHub repo or email support at [email protected]. Include the task ID and model ID so the team can investigate the specific generation.

Do I need a separate provider account?

No. Your RunAPI API key is enough to access this variant and every other model in the catalog. You do not need accounts with the underlying provider.

Building with a team?

We're here to help with enterprise setup, integrations, and technical questions.