Qwen3 Coder 480B A35B Instruct
AI model by Alibaba. Real-time pricing and benchmark data.
Benchmarks
Editorial Analysis
Profile. Qwen3 Coder 480B A35B Instruct is positioned in the mid-tier at $7.50/M output tokens. The benchmark profile is balanced — scoring across standard tests — making it a default choice for teams that need general-purpose reasoning without paying frontier-model prices.
Latency. On latency, Qwen3 Coder 480B A35B Instruct reports 66 tok/s output speed and 3160ms time-to-first-token. Output speed is on the slower end; for real-time chat consider pairing with a streaming front-end or routing latency-sensitive requests to a faster model.
Cost model. For a workload of 1M input tokens + 100K output tokens, Qwen3 Coder 480B A35B Instruct costs $2.25 per million input-equivalent requests. Multiply by your monthly request volume to project the bill, and compare against the speed/correctness profile above to decide if the trade-off is worth it for your workload.
Editorial summary generated from public pricing and benchmark data (Artificial Analysis API). All numbers are sourced — see the Artificial Analysis methodology for benchmark definitions. Last refreshed 2026-08-24.
Compare with similar models
| Model | Input | Output | Speed |
|---|---|---|---|
Qwen3 Coder 480B A35B InstructCurrent | $1.50 | $7.50 | 66 tok/s |
| Mistral Medium | $1.50 | $7.50 | 135 tok/s |
| Mistral Medium 3.5 | $1.50 | $7.50 | 132 tok/s |
| o3 | $2.00 | $8.00 | 112 tok/s |
| GPT-4.1 | $2.00 | $8.00 | 142 tok/s |
| Jamba 1.5 Large | $2.00 | $8.00 | — |