Qwen3-Coder-480B-A35B-Instruct
- Family
- Qwen3-Coder
- Released
- 2025-07-22
- Context
- 256K
- Parameters
- 480B total, 35B active
- Architecture
- Mixture of Experts
- Specialization
- code
- Openness
- Open source
- License
- Apache 2.0OSI-approvedPermitted
- Weights
- Available
- Code
- Unknown
- Training
- Pretrained
Cheapest of 7 routes · OpenRouter · cache read $0.100
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.
Overview
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.
Top use-case fit: coding, agents, and build tasks
Coding
Q/$ CAgents
Q/$ BProviders(7)
Compare all 7Compare API pricing across 7 tracked provider routes for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Cache | Route |
|---|---|---|---|---|
| OpenRouter | $0.300 | $1.00 | read $0.100 | Serverless |
| Novita AI | $0.380 | $1.55 | - | Serverless |
| GCP Vertex AI | $0.220 | $1.80 | - | Serverless |
| Vercel AI Gateway | $0.220 | $1.80 | read $0.022 | Serverless |
| AWS Bedrock | - | - | - | ServerlessPartial Scheduled retirement: March 30, 2027 |
| Fireworks AI | - | - | - | ProvisionedPartial |
| NVIDIA NIM | - | - | - | ServerlessPartial |
Available via routers & gateways(15)
LiteLLM
GatewayOpen-source Python SDK and proxy server that unifies 100+ LLM APIs behind a single OpenAI-compatible interface, with load balancing, cost tracking, and configurable failover.
OpenRouter
HybridUnified hybrid gateway to 500+ models from 80+ providers via a single OpenAI-compatible API, with an optional Auto Router that selects a model per prompt from market spend data.
Portkey
GatewayProduction AI gateway routing to 1,600+ LLMs with failover, load balancing, caching, and guardrails; MIT-licensed open-source core is self-hostable. Now part of Palo Alto Networks as Prisma AIRS AI Gateway.
AIRouter
RouterCommercial LLM router (branded "AI Router" on its site) that picks the best model per request via a Decision API or an OpenAI-compatible Chat Completions endpoint, with a private selection mode that routes on anonymized patterns; sold as BYOK subscription plans priced by routed tokens.
Amazon Bedrock Intelligent Prompt Routing
RouterAWS Bedrock's native prompt router that predicts each model's performance per request and routes between two models of the same family (Anthropic Claude, Meta Llama or Amazon Nova).
Helicone
GatewayObservability-first AI gateway with routing, caching, rate limiting, and request tracing; Apache-2.0 open-source platform with a managed hosted tier for logging and analytics.
Capabilities
Benchmark peer barsfor Coding
Benchmark scores(5)
| Benchmark | Score | Version | Evaluation | Source |
|---|---|---|---|---|
| 68.7 | Berkeley Function Calling Leaderboard (BFCL v3)Observed 2026-04-12 | — | ||
| 38.7 | Scale AI standardized SWE-bench ProObserved 2026-06-23 | — | ||
| 66.5 | Nebius/OpenHands independent SWE-bench VerifiedObserved 2026-06-23 | — | ||
| 1388.0 | text_style_control overall 2026-10-22 (style control, default view)Observed 2026-10-26 | Configuration: Qwen3-Coder-480B-A35B-Instruct Harness: LMArena blind pairwise human votes, Bradley-Terry Evaluator: LMArena Confidence: confirmed Notes: LMArena text style control leaderboard, overall category, published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @9761a3ce, latest split). Board entry 'Qwen3-Coder-480B-A35B-Instruct': rank 182, Arena Score 1387.5 (95% CI 1382.5-1392.5), 25192 votes. Retrieved 2026-10-26. | Source Source: LMArena (lmarena.ai), CC BY 4.0 | |
| 1333.0 | text creative_writing 2026-10-22Observed 2026-10-22 | Configuration: Qwen3-Coder-480B-A35B-Instruct Harness: LMArena blind pairwise human votes, Bradley-Terry Evaluator: LMArena Confidence: confirmed Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Qwen3-Coder-480B-A35B-Instruct' (category creative_writing in text/latest-00000-of-00001.parquet): rank 189 of 416, rating 1332.9 (95% CI 1322.3-1343.6), 3241 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27. | Source Source: LMArena (lmarena.ai), CC BY 4.0 |
Migration checks
No linked migration route is available for this model yet.