Qwen3-Coder Models by Alibaba

AlibabaApache 2.0Open source
Alibaba releases · 51 in the last 12 months · this family litChangelog →
5 models2025–2026Up to 1M ctxFrom $0.070/1M input

Last refreshed 2026-10-17. Next refresh: weekly.

Details

ResearcherAlibaba
LicenseApache 2.0OSI-approved
Commercial usePermitted
Models5
Released2025–2026
Max context1M

Capabilities

Reasoning1 of 5 models
JSON / Tool useAll models
Structured OutputsAll models
Code Execution3 of 5 models

About

Qwen3-Coder is Alibaba’s Qwen Team agentic coding model family for repository-scale software engineering and tool-using coding agents. The first highlighted open release is Qwen3-Coder-480B-A35B-Instruct, a large MoE coder with a long native context aimed at multi-turn coding, browser-use, and tool-use agent loops. The Qwen team also ships Qwen Code, a command-line coding agent adapted for these models, and documents use with community IDEs and scaffolds such as Claude Code and Cline via Alibaba Cloud Model Studio.

Decision facts

Best fit
reasoningJSON / Tool usestructured outputs
Capability starting point
Qwen3-Coder-Next with 256.14K context and reasoning, JSON / Tool use, and structured outputs
Lowest tracked input
Qwen3-Coder-30B-A3B-Instruct · $0.070/1M · Novita AI
Closest related family
Ovis Image

Current Variants

Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.

4 in view1 retired

Use when the workload needs code, 256.14K context, and reasoning.

2026-02code256.14K contextreasoning

Use when the workload needs code, 256K context, and JSON / Tool use.

2025-12code256K contextJSON / Tool use

Use when the workload needs code, 1M context, and JSON / Tool use.

2025-07code1M contextJSON / Tool use

Use when the workload needs code, 256K context, and JSON / Tool use.

2025-07code256K contextJSON / Tool use

Release Timeline

4 release groups
2026-02
1 current
Qwen3-Coder-Next
code256.14K contextreasoning
Current
2025-12
1 current
Qwen3-Coder-30B-A3B-Instruct
code256K contextJSON / Tool use
Current
2025-09
1 retired
Qwen3-Coder-Plus
code1M contextJSON / Tool use
Archived
2025-07
2 current
Qwen3-Coder-480B-A35B-Instruct
code256K contextJSON / Tool use
Current
Qwen3-Coder-Flash
code1M contextJSON / Tool use
Current

Specifications(5 models)

Qwen3-Coder model specifications comparison
ModelReleasedContextParametersReasoningJSON / Tool useStructured OutputsCode Exec
Qwen3-Coder-Next2026-02256.14K80B total, 3B activeYesYesYesYes
Qwen3-Coder-30B-A3B-Instruct2025-12256K30.5B total, 3.3B activeNoYesYesYes
Qwen3-Coder-Flash2025-071M—NoYesYesNo
Qwen3-Coder-480B-A35B-Instruct2025-07256K480B total, 35B activeNoYesYesYes

Pricing

Qwen3-Coder model pricing by provider
ModelProviderInput / 1MOutput / 1MType
Qwen3-Coder-30B-A3B-InstructNovita AI$0.07$0.27Serverless
Qwen3-Coder-30B-A3B-InstructOpenRouter$0.07$0.28Serverless
Qwen3-Coder-NextOpenRouter$0.12$0.8Serverless
Qwen3-Coder-30B-A3B-InstructAWS Bedrock$0.15$0.62Serverless
Qwen3-Coder-30B-A3B-InstructVercel AI Gateway$0.15$0.6Serverless
Qwen3-Coder-FlashOpenRouter$0.195$0.975Serverless
Qwen3-Coder-NextNovita AI$0.2$1.5Serverless
Qwen3-Coder-480B-A35B-InstructGCP Vertex AI$0.22$1.8Serverless
Qwen3-Coder-480B-A35B-InstructVercel AI Gateway$0.22$1.8Serverless
Qwen3-Coder-FlashAlibaba Cloud PAI-EAS$0.3$1.5Serverless
Qwen3-Coder-480B-A35B-InstructOpenRouter$0.3$1Serverless
Qwen3-Coder-480B-A35B-InstructNovita AI$0.38$1.55Serverless
Qwen3-Coder-NextAWS Bedrock$0.5$1.2Serverless
Qwen3-Coder-NextVercel AI Gateway$0.5$1.2Serverless