LLM Reference

Qwen3-Coder-480B-A35B-Instruct

Released
2025-07-22
Last refreshed
2026-06-29
Status
Researched 13d ago
Open sourceCommercial use: permittedCodingRAGAgentsLong contextClassificationJSON / Tool use

Qwen3-Coder-480B-A35B-Instruct is worth evaluating for coding, rag, and agents when its provider route and context window match the workload.

Use it for

  • Teams evaluating coding, rag, and agents
  • Workloads that can use a 262k context window
  • Buyers comparing 4 tracked provider routes

Do not use it for

  • Vision or document-understanding workloads
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
Training
Pretrained
Created by

AI research institute of Alibaba Group.

Hangzhou, Zhejiang, China
Founded 2017
Website
Pricing
Output / 1M
$1.55
Input / 1M
$0.380

Cheapest of 6 routes · Novita AI

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. The model is purpose-built for software engineering tasks and agentic workflows: code generation, code review, test writing, multi-step debugging, and browser-based agentic task execution. On release, it achieved state-of-the-art results among open models on Agentic Coding, Agentic Browser-Use, and Agentic Tool-Use benchmarks, with performance comparable to Claude Sonnet 4 on these tasks. Available via Fireworks AI, Google Vertex AI, NVIDIA NIM, AWS Bedrock, Novita AI, and the Vercel AI Gateway.

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) and supports a native context window of 256,000 tokens, extendable to 1 million tokens via YaRN position scaling.

The model is purpose-built for software engineering tasks and agentic workflows: code generation, code review, test writing, multi-step debugging, and browser-based agentic task execution. On release, it achieved state-of-the-art results among open models on Agentic Coding, Agentic Browser-Use, and Agentic Tool-Use benchmarks, with performance comparable to Claude Sonnet 4 on these tasks. The instruction-tuned variant supports function calling and structured output natively.

Qwen3-Coder-480B-A35B-Instruct is available via Fireworks AI, Google Vertex AI, NVIDIA NIM, AWS Bedrock, Novita AI, and the Vercel AI Gateway. It is the largest model in the Qwen3 Coder family and represents the top open-source coding capability from Alibaba as of mid-2025. The 256K native context window accommodates large codebases, multi-file sessions, and long agentic task traces within a single context.

Qwen3-Coder-480B-A35B-Instruct has a 262k-token context window.

Qwen3-Coder-480B-A35B-Instruct input tokens at $0.22/1M, output at $1.8/1M.

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

Coding

Q/$ D

2 relevant benchmarks in the decision map.

RAG

Included by capability and metadata signals in the decision map.

Agents

Q/$ B

2 relevant benchmarks in the decision map.

Provider price ladder

Compare all 6

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

ProviderInput / 1MOutput / 1MCacheRoute
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
AWS Bedrock---
ServerlessPartial

Available via routers & gateways(15)

Capabilities

Function CallingTool 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.
BenchmarkScoreVersionSource
Berkeley Function Calling Leaderboard v368.7Berkeley Function Calling Leaderboard (BFCL v3)https://gorilla.cs.berkeley.edu/leaderboard.html
SWE-bench Pro38.7Scale AI standardized SWE-bench Prohttps://labs.scale.com/leaderboard/swe_bench_pro_public
SWE-bench Verified66.5Nebius/OpenHands independent SWE-bench Verifiedhttps://nebius.com/blog/posts/openhands-trajectories-with-qwen3-coder-480b

Migration checks

No linked migration route is available for this model yet.

Frequently asked questions

What is the context window of Qwen3-Coder-480B-A35B-Instruct?

Qwen3-Coder-480B-A35B-Instruct has a context window of 262k tokens.

How much does Qwen3-Coder-480B-A35B-Instruct cost?

Qwen3-Coder-480B-A35B-Instruct pricing ranges from $0.22/1M to $1.5/1M input tokens depending on the provider.

When was Qwen3-Coder-480B-A35B-Instruct released?

Qwen3-Coder-480B-A35B-Instruct was released on 2025-07-22.

Which providers offer Qwen3-Coder-480B-A35B-Instruct?

Qwen3-Coder-480B-A35B-Instruct is available from 6 providers: Fireworks AI, GCP Vertex AI, NVIDIA NIM, AWS Bedrock, Vercel AI Gateway, Novita AI.

What benchmarks has Qwen3-Coder-480B-A35B-Instruct been tested on?

Qwen3-Coder-480B-A35B-Instruct has been evaluated on 3 benchmarks, including Berkeley Function Calling Leaderboard v3, SWE-bench Pro, SWE-bench Verified.