| Model | Input / output per 1M | Log probabilities | Quantization |
|---|---|---|---|
| gpt-oss-120b | $0.03 / $0.17 | yes | fp4 |
| gpt-oss-20b | $0.03 / $0.13 | yes | fp4 |
| Gemma 4 31B | $0.10 / $0.34 | yes | fp4 |
| DeepSeek V4.1 Flash | $0.20 / $0.65 | yes | fp8 |
| DeepSeek V4 Flash 0731 | $0.13 / $0.28 | yes | fp8 |
| GLM 5.3 Flash | $0.15 / $0.50 | yes | nvfp4 |
| Nemotron 3.5 Lightning | $0.07 / $0.20 | yes | bf16 |
| Qwen3.8 27B | $0.40 / $3.00 | yes | fp8 |
| MiniMax M3 | $0.23 / $0.96 | yes | fp4 |
| Kimi K2.6 | $0.65 / $3.41 | yes | fp4 |
| Llama 3.3 70B Instruct | $0.71 / $0.71 | yes | fp16 |