Open-weight models on custom LPU hardware, delivering some of the fastest inference speeds at low cost.
| Model | Input per 1M tokens | Output per 1M tokens |
|---|---|---|
| openai/gpt-oss-120b | $0.1500 | $0.6000 |
| openai/gpt-oss-20b | $0.0750 | $0.3000 |
| openai/gpt-oss-safeguard-20b | $0.0750 | $0.3000 |
| qwen/qwen3.8-27b | $0.8000 | $4.00 |