Qwen3-Coder-480B-A35B-Instruct

Released
2025-07-22
Last refreshed
2026-06-29
Status
Researched 103d ago
Open sourceCommercial use: permittedCodingRAGAgentsLong contextClassificationJSON / Tool use
Alibaba releases · 46 in the last 12 months · this family litChangelog →
Specifications
Released
2025-07-22
Context
262k
Parameters
480B total, 35B active
Architecture
Mixture of Experts
Specialization
code
Openness
Open source
License
Apache 2.0OSI-approvedCommercial use: permitted
Weights
Available
Code
Unknown
Training
Pretrained
Created by

AI research institute of Alibaba Group.

Hangzhou, Zhejiang, China
Founded 2017
Website
Pricing
Output / 1M
$1.00
Input / 1M
$0.300

Cheapest of 7 routes · OpenRouter · cache read $0.100

About

Qwen3-Coder-480B-A35B-Instruct is Alibaba's flagship open-source code generation and agentic model, released July 22, 2025 under the Apache 2.0 license. The model has 480 billion total parameters with 35 billion active parameters per token, organized across 62 transformer layers with 160 specialized expert networks and 8 experts activated per token. It uses Grouped Query Attention (GQA) with 96 query heads and 8 key-value heads and supports a native context window of 262,144 tokens, extendable to 1 million tokens via YaRN position scaling.

Top use-case fit: coding, agents, and build tasks

Coding

Q/$ C

Agents

Q/$ B

Provider price ladder

Compare all 7

Compare API pricing across 4 providers for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MCacheRoute
OpenRouter$0.300$1.00read $0.100
Serverless
Novita AI$0.380$1.55-
Serverless
GCP Vertex AI$0.220$1.80-
Serverless
Vercel AI Gateway$1.50$7.50read $0.300
Serverless

Available via routers & gateways(15)

Capabilities

JSON / Tool useStructured OutputsCode Execution

Benchmark peer barsfor Coding

Benchmark scores(3)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionEvaluationSource
Berkeley Function Calling Leaderboard v368.7Berkeley Function Calling Leaderboard (BFCL v3)Observed 2026-04-12—Source
SWE-bench Pro38.7Scale AI standardized SWE-bench ProObserved 2026-06-23—Source
SWE-bench Verified66.5Nebius/OpenHands independent SWE-bench VerifiedObserved 2026-06-23—Source

Migration checks

No linked migration route is available for this model yet.