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 | bf16 | $0.03 | $0.14 | 131,072 | 99.9% |
| gpt-oss-120b | bf16 | $0.03 | $0.18 | 131,072 | 99.8% |
| Gemma 4 26B A4B | bf16 | $0.06 | $0.33 | 262,144 | 99.9% |
| Gemma 4 31B | unknown | $0.10 | $0.33 | 262,144 | 96.5% |
| Nemotron 3 Super 120B | fp8 | $0.08 | $0.45 | 262,144 | 99.9% |
| GLM-5.3-Flash | unknown | $0.10 | $0.40 | 1,048,576 | 99.7% |
| DeepSeek V4.1 Flash | unknown | $0.12 | $0.40 | 1,048,576 | 99.7% |
| Qwen3.8-27B | unknown | $0.05 | $3.00 | 262,144 | 99.8% |