by Alibaba
Qwen3 Coder 480B scored 67% on SWE-bench. Massive 480B MoE architecture with 256K context handles entire codebases. Apache 2.0 licensed.
Parameters
480B (MoE)
Architecture
Mixture of Experts
Context
262K
Provider
Alibaba
Drop-in replacement for OpenAI API. Just change the base URL.
Only pay for actual GPU compute time. No idle costs.
99.9% uptime SLA, SOC 2 compliant, dedicated support.
Scales from zero to thousands of requests automatically.
| Fleek | Fireworks | Together | Baseten | |
|---|---|---|---|---|
| Input | $0.07 | $0.45 | $2.00 | $0.38 |
| Output | $0.29 | $1.80 | $2.00 | $1.53 |
| Savings | 70% | 70% | 70% |
Prices are per million tokens. Fleek pricing based on $0.0025/GPU-second.
See how much you'd save running Qwen3 Coder 480B on Fleek
| Model Name | Qwen3 Coder 480B |
| Total Parameters | 480B (MoE) |
| Active Parameters | 35B |
| Architecture | Mixture of Experts |
| Context Length | 262K tokens |
| Inference Speed | 52,500 tokens/sec |
| Provider | Alibaba |
| Release Date | Nov 1, 2025 |
| License | Apache 2.0 |
| HuggingFace | https://huggingface.co/Qwen/Qwen3-Coder-480B-Instruct |
Software Engineering benchmark - real GitHub issues
OpenAI code generation benchmark
Mostly Basic Python Problems
Click any benchmark to view the official leaderboard. Rankings among open-source models.
Join the waitlist for early access. Start free with $5 in credits.