Atlas / Models / Qwen / Qwen: Qwen3 Coder Next

Qwen: Qwen3 Coder Next✓ Catalog verified

qwen/qwen3-coder-next

Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per token, delivering performance comparable to models with 10 to 20x higher active compute, which makes it well suited for cost-sensitive, always-on agent deployment. The model is trained with a strong agentic focus and performs reliably on long-horizon coding tasks, complex tool usage, and recovery from execution failures. With a native 256k context window, it integrates cleanly into real-world CLI and IDE environments and adapts well to common agent scaffolds used by modern coding tools. The model operates exclusively in non-thinking mode and does not emit <think> blocks, simplifying integration for production coding agents.

Input price
$0.12 /1M
Output price
$0.75 /1M
Context
262K
Modalities
text
Released
Feb 4, 2026
Tool calling
✓ Yes
Atlas signal
85/100
01

Overview

Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per token, delivering performance comparable to models with 10 to 20x higher active compute, which makes it well suited for cost-sensitive, always-on agent deployment. The model is trained with a strong agentic focus and performs reliably on long-horizon coding tasks, complex tool usage, and recovery from execution failures. With a native 256k context window, it integrates cleanly into real-world CLI and IDE environments and adapts well to common agent scaffolds used by modern coding tools. The model operates exclusively in non-thinking mode and does not emit <think> blocks, simplifying integration for production coding agents.

Access: available through the official Qwen API. Context window: 262K.

Pricing and metadata from the ModelsAtlas catalog.Last refreshed Aug 5, 2026
02

Specifications

API identifierqwen/qwen3-coder-next
ProviderQwen
Model typeText LLM
Context window262K catalog
Input modalitiestext
Output modalitiestext
ReleasedFeb 4, 2026
TokenizerQwen
ModeratedNo
Architecture modalitytext->text
Supported parameters
frequency_penaltylogit_biasmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p
Source: provider documentation + catalog feedMethodology →

API defaults

Default parameters
{
  "top_p": 0.95,
  "temperature": 1,
  "frequency_penalty": null
}
03

Pricing

Live pricing components for qwen/qwen3-coder-next as published in the catalog.

$0.12
Input /1M
$0.75
Output /1M
Per request
Per image
Pricing componentRaw unit priceNormalizedUnit
Prompt tokens$1.2e-7$0.12 / 1MPer input token
Completion tokens$7.5e-7$0.75 / 1MPer output token
Request feeN/AN/APer request
Image feeN/AN/APer image unit
Web search feeN/AN/APer search request
Source: catalog pricing feedCompare all pricing →Cheapest models →
04

Cost calculator

Estimate monthly spend from your own token volumes.

Scale / Volume

Estimated Total Cost

$0.21Calculated from current list pricing in the ModelsAtlas catalog.
05

Capabilities

CapabilityStatusWhat it means
Visual UnderstandingNot advertisedImage and document analysis support
Audio ProcessingNot advertisedSpeech and voice aligned flows
Tool Calling✓ SupportedSupports tools / function calling
Self-Hosting✓ SupportedDeploy outside managed APIs
Derived from catalog capability tags and supported parameters
06

Capability signals

Directional signals derived from model metadata and capability tags — not official benchmark submissions.

Qwen: Qwen3 Coder Next
MMLU Signal (Reasoning)
79signal
Coding Signal (HumanEval proxy)
97signal
Math Signal (GSM8K proxy)
79signal
Science Signal (GPQA proxy)
83signal
Estimated from metadata — not an official benchmark runAll benchmarks →Methodology →
07

Quick start

Call Qwen: Qwen3 Coder Next through an OpenAI-compatible client.

from openai import OpenAI

client = OpenAI(
    base_url="https://openrouter.ai/api/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="qwen/qwen3-coder-next",
    messages=[{"role": "user", "content": "Explain quantum physics."}]
)

print(response.choices[0].message.content)
08

Alternatives

Closest models by context window from a different provider.

09

Sources & attribution

Pricing and metadata are maintained in the ModelsAtlas catalog.

Capability bars use metadata tags — directional estimates onlyHow we source and verify data →
10

Frequently asked questions

How much does Qwen: Qwen3 Coder Next cost?

$0.12 per 1M input tokens and $0.75 per 1M output tokens on the official Qwen API.

What is the context window of Qwen: Qwen3 Coder Next?

Qwen: Qwen3 Coder Next supports up to 262K tokens of context.

Does Qwen: Qwen3 Coder Next support tool / function calling?

Yes, Qwen: Qwen3 Coder Next supports tool / function calling — you can register tools and the model will emit structured tool calls.

How do I access Qwen: Qwen3 Coder Next?

Use the official Qwen API with the model id `qwen/qwen3-coder-next`. See the Quick start section above for code examples.