Alibaba (Qwen)

Qwen3 Coder Next

Generally availableOpen weights262K context

Summary

Qwen3 Coder Next is an open-weight language model from Alibaba (Qwen), released on 3 Feb 2026. It accepts text and generates text, with a 262K-token context window and up to 66K output tokens per response. As of 18 Nov 2026, the lowest listed API price is $0.12 per million input tokens and $0.80 per million output tokens (OpenRouter), across 4 providers we track.

Open-weight Qwen coding model for agents, repository edits, and multi-turn tool use

Last verified 18 Nov 2026. Every figure on this page links to its source.

Specifications

DeveloperAlibaba (Qwen)
Release date3 Feb 2026 [models.dev]
StatusGenerally available [models.dev]
WeightsOpen weights [Hugging Face]
Licenseapache-2.0 [Hugging Face]
Parameters79.7B [Hugging Face]
Context window262K (262,144 tokens) [models.dev]
Max output66K tokens [models.dev]
Knowledge cutoffSept 2025 [models.dev]
InputText [models.dev]
OutputText [models.dev]
Reasoning modeNo [models.dev]
Tool callingYes [models.dev]
Structured outputYes [models.dev]
Hugging FaceQwen/Qwen3-Coder-Next [Hugging Face]

Qwen3 Coder Next API pricing by provider

USD per million tokens. Sorted by input price.

ProviderInputOutputCached inputContextSource
OpenRouter
qwen/qwen3-coder-next
$0.12$0.80$0.07262KOpenRouter, 18 Nov 2026
Hugging Face Inference Providers
Qwen/Qwen3-Coder-Next
$0.20$1.50–262Kmodels.dev, 18 Nov 2026
Amazon Bedrock
qwen.qwen3-coder-next
$0.50$1.20–262Kmodels.dev, 18 Nov 2026
Vercel AI Gateway
alibaba/qwen3-coder-next
$0.50$1.20–256Kmodels.dev, 18 Nov 2026

Running Qwen3 Coder Next locally

Estimated memory, from the parameter count and the architecture in config.json on Hugging Face. Includes about 0.8 GB of runtime overhead.

QuantizationWeightsTotal, 8K contextTotal, 32K context
Q4_K_M (4-bit)48 GB50 GB52 GB
Q8_0 (8-bit)85 GB86 GB89 GB
FP16 / BF16 (16-bit)159 GB161 GB163 GB

At 4-bit with an 8K conversation, Qwen3 Coder Next needs about 50 GB, more than any single consumer graphics card; it needs a unified-memory machine, a multi-GPU setup or a split between graphics card and system RAM. Check your own hardware, or see Best computer for local AI on our sister site AIPCs.

Frequently asked questions

What is the context window of Qwen3 Coder Next?

Qwen3 Coder Next has a context window of 262,144 tokens (262K) and can generate up to 65,536 tokens in a single response, according to models.dev.

How much does the Qwen3 Coder Next API cost?

Qwen3 Coder Next is listed from $0.12 per million input tokens and $0.80 per million output tokens (OpenRouter). Prices last verified 18 Nov 2026.

Is Qwen3 Coder Next open source?

Qwen3 Coder Next is an open-weight model: its weights are published on Hugging Face as Qwen/Qwen3-Coder-Next under the apache-2.0 license. Check the license terms before commercial use.

When was Qwen3 Coder Next released?

Alibaba (Qwen) released Qwen3 Coder Next on 3 Feb 2026, according to models.dev.

Which providers offer Qwen3 Coder Next?

We track Qwen3 Coder Next on 4 providers: OpenRouter, Hugging Face Inference Providers, Amazon Bedrock, Vercel AI Gateway.

How much VRAM does Qwen3 Coder Next need?

About 50 GB at 4-bit (Q4_K_M) with an 8K-token conversation, and about 86 GB at 8-bit. That is more than any single consumer graphics card holds. These are estimates from the model's published parameter count and architecture.

Similar models from other labs

Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.

ModelLabReleasedContextInput $/1MOutput $/1MWeights
Mistral Small 4Mistral AI16 Mar 2026262K$0.15$0.60Open
Jamba MiniAI21 Labs8 Jan 2026256K$0.20$0.40Open
Hy3 previewTencent (Hunyuan)20 Apr 2026262K$0.18$0.60Open
Step 3.5 FlashStepFun29 Jan 2026262K$0.10$0.30Open
NVIDIA Nemotron 3 Super 120B A12BNVIDIA11 Mar 2026262K$0.07$0.40Open
Gemma 4 31B ITGoogle DeepMind2 Apr 2026262K$0.14$0.40Open

Change history

  • Name changed from Qwen3-Coder-Next to Qwen3 Coder Next
  • Reasoning mode changed from yes to no
  • Context window changed from 256K to 262K
  • Max output changed from 256K to 66K
  • Name changed from Qwen3 Coder Next to Qwen3-Coder-Next
  • Reasoning mode changed from no to yes
  • Max output changed from 236K to 256K
  • Context window changed from 262K to 256K
  • Max output changed from 66K to 236K
  • Name changed from Qwen3-Coder-Next to Qwen3 Coder Next
  • Name changed from Qwen3 Coder Next to Qwen3-Coder-Next
  • Context window changed from 256K to 262K
  • Reasoning mode changed from yes to no
  • Max output changed from 256K to 66K
  • Context window changed from 262K to 256K
  • Max output changed from 236K to 256K
  • Reasoning mode changed from no to yes
  • Reasoning mode changed from yes to no
  • Context window changed from 256K to 262K
  • Max output changed from 256K to 236K
  • Max output changed from 66K to 256K
  • Reasoning mode changed from no to yes
  • Context window changed from 262K to 256K
  • Name changed from Qwen3-Coder-Next to Qwen3 Coder Next
  • Name changed from Qwen3 Coder Next to Qwen3-Coder-Next

Sources