Alibaba
100.00%Context262.1K
Max output65.5K
p50 latency1,015 ms
Throughput78.0 t/s
Input price$1.5
Output price$7.5
Zero retentionNo training
alibaba/qwen3-coder
Qwen3-Coder-480B-A35B-Instruct is a cutting-edge open coding model from Qwen, matching Claude Sonnet’s performance in agentic programming, browser automation, and core development tasks.
USD per one million tokens, using current provider data.
Last-hour p50 in milliseconds; lower is better.
Reported availability over the last 24 hours; not a contractual SLA.
Compare current pricing, performance, and privacy across every available provider.
| Provider | Maximum context | Max output | p50 latency | p50 throughput | 24h uptime | Input / 1M tokens | Output / 1M tokens | Privacy |
|---|---|---|---|---|---|---|---|---|
Alibaba | 262.1K | 65.5K | 1,015 ms | 78.0 t/s | 100.000% | $1.5 | $7.5 | |
Deepinfra | 262.1K | 66.5K | 307 ms | 56.0 t/s | 100.000% | $0.4 | $1.6 | |
Novita | 262.1K | 65.5K | 1,021 ms | 96.0 t/s | 100.000% | $0.3 | $2.5 | |
Vertex | 262.1K | 32.8K | 750 ms | — | 100.000% | $0.22 | $1.8 |
Available modalities and capabilities across inference providers.
alibaba/qwen3-coderMore options from the same creator or model category.