Official site · origin not confirmed
4 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-120b | fp8 | $0.04 | $0.28 | 131,072 | 96.5% |
| DeepSeek V4 Flash | fp8 | $0.20 | $0.60 | 1,048,576 | 98.8% |
| Qwen3.8-27B | fp8 | $0.20 | $2.50 | 262,144 | 99.8% |
| GLM 4.7 | fp4 | $0.70 | $2.50 | 131,072 | 98.5% |