Official site · 🇺🇸 United States
6 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 |
|---|---|---|---|---|---|
| Nemotron 3 Nano 30B | fp8 | $0.05 | $0.20 | 262,144 | 100.0% |
| gpt-oss-120b | bf16 | $0.05 | $0.25 | 131,072 | 100.0% |
| Gemma 4 31B | bf16 | $0.14 | $0.40 | 262,144 | 99.4% |
| GLM-5.3-Flash | fp4 | $0.15 | $0.50 | 1,048,576 | 99.7% |
| Kimi K2.6 | bf16 | $0.70 | $3.50 | 262,144 | 100.0% |
| GLM-5.3 | fp4 | $1.40 | $4.40 | 1,048,576 | 99.9% |