Official site · origin not confirmed
8 endpoints, cheapest first. This is the view the model-by-model tables cannot give you: what one provider actually offers, and at what precision.
| Model | Quant | $/M in | $/M out | Context | Uptime 30m |
|---|---|---|---|---|---|
| gpt-oss-20b | fp8 | $0.02 | $0.09 | 131,072 | 99.9% |
| Nemotron 3.5 Lightning | int4 | $0.04 | $0.18 | 262,144 | 99.9% |
| Gemma 4 26B A4B | unknown | $0.04 | $0.22 | 131,072 | 100.0% |
| Qwen3.5-9B | fp4 | $0.08 | $0.13 | 262,144 | 100.0% |
| MiMo-V2.6-Flash | fp4 | $0.12 | $0.28 | 1,048,576 | 98.8% |
| Qwen3.6 35B A3B | fp4 | $0.05 | $0.70 | 262,144 | 100.0% |
| Qwen3.5-35B-A3B | fp4 | $0.08 | $0.75 | 262,144 | 100.0% |
| Qwen3.8-27B | fp4 | $0.05 | $2.20 | 262,144 | 100.0% |