Qwen · open weights · medium
Qwen: Qwen3 32B
Open weights, so you can run it locally. The published id includes 32B. That label is copied from the id, not measured here. Size class is this site's filter bucket, not a benchmark.
API price, in pounds
- Input, per million
- £0.0596
- Output, per million
- £0.209
OpenRouter lists $0.0800 in and $0.2800 out per million tokens. Converted at 0.74501 on 2026-11-10. Fetched 2026-11-11. Context length listed as 131,072 tokens.
Sourced local speeds
- 69.83 reply tokens/sec on GeForce RTX 5090, Q4_K_M. Source. Run r_vhbqyt1f_xr, marked Measured by llm-speed. Chat-short. No power draw in the row. Page read 11 November 2026.