Skip to content

Alibaba · Chat

Qwen3 Coder Next

Alibaba 🇨🇳ChatQwen familyOpen weights. One of its sources says the weights are publicly available.The maker lists this model as deprecated (14 May 2026).
From Neosantara's listing:
Open-weight Qwen coding model for agents, repository edits, and multi-turn tool use
llminfo IQ
118.2
Market median price
$0.525 blended / 1M
Max context
262K
Listings
38

Evidence and sources

International storefront (alibabacloud.com) is Singapore-incorporated; mainland operating entity 杭州阿里云智能科技有限公司 (Hangzhou).

🤗 Qwen/Qwen3-Coder-Next Model architecture, as its sources state it llminfo IQ 118.2, ranked among chat models. From 27 benchmarks. Plenty of data behind it.How llminfo IQ is computedCoding IQ 97.7, 95% interval 90–105. From 7 benchmark families across 4 sources. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.How Coding IQ is computedPoor value (36.8). Costs more per task than its benchmark results predict. From 11 benchmarks with measured task costs. Plenty of data behind it.How Value for money worksYap score: tokens used per coding task vs. models with the same resultsTypical (54 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.Median 27,962 output tokens per task at default effort.How the Yap score worksReleased 2 Feb 2026Maker HQ: CN (source)
All rankings: #25 in Hacker News discussions this week #122 on OpenRouter today #148 on OpenRouter this week #154 on OpenRouter this month #206 on NanoGPT recentlyAll rankings: #25 in Hacker News discussions this week #122 on OpenRouter today #148 on OpenRouter this week #154 on OpenRouter this month #206 on NanoGPT recentlySources: AWS Bedrock Runtime data, LiteLLM data, Models.dev data, Morpheus Inference Marketplace data, Neosantara Inference data, llminfo researchPrimary data from AWS Bedrock Runtime from LiteLLM: deprecation date from Models.dev: weights availability from Morpheus Inference Marketplace: architecture from Neosantara Inference: description from llminfo research: release date
Tags from its sources:instructtools

Advantages and trade-offs

Compared with 10 chat models, picked mainly by popularity and IQ

Advantages

Open weights available

The weights are public. 3 of the 9 peers that say either way have open weights.

Trade-offs

Deprecated by its maker

The maker has already deprecated this model (14 May 2026).

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 06:07 UTC.

Input & output

as stated by the model's providers
Text
Text

Capabilities

Supported operations and provider-stated features

ReasoningFunction callingStructured outputPrompt cachingBatch API

Listings

 Hugging FaceInference by ParasailQwen/Qwen3-Coder-NextSource: Hugging Face Inference Providers data262K$0.12$0.80
 Kiloqwen/qwen3-coder-nextSources: Kilo AI Gateway data, Models.dev data262K$0.12cache read $0.07$0.80
 NanoGPTqwen/qwen3-coder-nextSources: Models.dev data, NanoGPT262K$0.12cache read $0.07$0.80
 Nous Portalqwen/qwen3-coder-nextSource: Nous Portal Inference Gateway data262K$0.12cache read $0.07$0.80
 OpenRouterqwen/qwen3-coder-nextSources: GenAI Prices data, Models.dev data, OpenRouter data docs262K$0.12cache read $0.07$0.80
 Wavespeedqwen/qwen3-coder-nextSource: WaveSpeed AI data262K$0.12cache read $0.07$0.80
 Parasailparasail-qwen3-coder-next · bf16Source: Parasail data262K$0.12cache read $0.07$0.80
 Aihubmixqwen3-coder-nextSources: AIHubMix data docs, LiteLLM data262K$0.137$0.548
 Merge Gatewayqwen/qwen3-coder-nextSource: Models.dev data262K$0.15cache read $0.075$0.80
 Cortecs AIqwen3-coder-nextSources: Cortecs EU Router data, Models.dev data256K
Show all 31 listings

Showing 10 of 31: the cheapest per 1M input tokens from each provider.

Also sold by 302ai, Amazon Web Services, Eden AI, Eurouter, Flowdot, Jiekou, Neosantara, Novita AI, Ofox, Opper, Regolo, Stepping Stone, Together AI, Vercel.

7 listings without a price are hidden.

Included in plans

Coding Plan ProAlibaba CloudSubscription$50/moPlan page

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

Agentic

OpenHandsSource: OpenHands Index data
Source: OpenRouter benchmark exports · Oct 2026
qwen3-coder-next-2025-02-03 · 90-day results
Across 5 providers lowest 18.7% median 53.7% highest 60.2%OpenRouter's automatic routing 60%
Show results from 5 providers and OpenRouter's automatic routingHide results from 5 providers and OpenRouter's automatic routing
  • StreamLake
  • OpenRouter's automatic routing
  • Parasail
  • Alibaba
  • Novita
  • PrimeIntellect

Coding

Science

GPQA Diamond6 results
Source: OpenRouter benchmark exports · Oct 2026
qwen3-coder-next-2025-02-03 · 90-day results
Across 5 providers lowest 73.9% median 74.9% highest 76.3%OpenRouter's automatic routing 75.1%
Show results from 5 providers and OpenRouter's automatic routingHide results from 5 providers and OpenRouter's automatic routing
  • PrimeIntellect
  • StreamLake
  • OpenRouter's automatic routing
  • Alibaba
  • Parasail
  • Novita

General

Knowledge

Multilingual

Reasoning

Other

Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · OpenRouter public benchmark leaderboard and search-lane exports, CC BY 4.0. Fractional source scores converted to percentages; immutable dated snapshots. (licence) · Hugging Face official benchmark leaderboards; licence varies by benchmark · OpenHands Index (All Hands AI), Apache-2.0 (licence) · SnakeBench (Greg Kamradt / ARC Prize Foundation), MIT (licence)

Around the web

Also known as: aihubmix/qwen3-coder-next, alibaba/qwen3-coder-next, amazon/qwen.qwen3-coder-next, bailian/qwen3-coder-next, bedrock/ap-northeast-1/qwen.qwen3-coder-next, bedrock/ap-south-1/qwen.qwen3-coder-next, bedrock/ap-southeast-2/qwen.qwen3-coder-next, bedrock/ap-southeast-3/qwen.qwen3-coder-next, bedrock/eu-central-1/qwen.qwen3-coder-next, bedrock/eu-north-1/qwen.qwen3-coder-next, bedrock/eu-south-1/qwen.qwen3-coder-next, bedrock/eu-west-1/qwen.qwen3-coder-next, bedrock/eu-west-2/qwen.qwen3-coder-next, bedrock/sa-east-1/qwen.qwen3-coder-next, bedrock/us-east-1/qwen.qwen3-coder-next, bedrock/us-east-2/qwen.qwen3-coder-next, bedrock/us-west-2/qwen.qwen3-coder-next, bedrock_mantle/ap-northeast-1/qwen.qwen3-coder-next, bedrock_mantle/ap-south-1/qwen.qwen3-coder-next, bedrock_mantle/ap-southeast-2/qwen.qwen3-coder-next, bedrock_mantle/ap-southeast-3/qwen.qwen3-coder-next, bedrock_mantle/eu-central-1/qwen.qwen3-coder-next, bedrock_mantle/eu-north-1/qwen.qwen3-coder-next, bedrock_mantle/eu-south-1/qwen.qwen3-coder-next, bedrock_mantle/eu-west-1/qwen.qwen3-coder-next, bedrock_mantle/eu-west-2/qwen.qwen3-coder-next, bedrock_mantle/qwen.qwen3-coder-next, bedrock_mantle/sa-east-1/qwen.qwen3-coder-next, ionos/qwen/qwen3-coder-next, novita/qwen/qwen3-coder-next, parasail-qwen3-coder-next, qwen.qwen3-coder-next, qwen/qwen3-coder-next, qwen/qwen3-coder-next-fp8, qwen3-coder-next-80b, qwen3-coder-next-fp8, together_ai/qwen/qwen3-coder-next-fp8

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works