Official site · origin not confirmed
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 |
|---|---|---|---|---|---|
| Gemma 4 26B A4B | bf16 | $0.07 | $0.22 | 262,144 | 100.0% |
| Qwen3 14B | int4 | $0.10 | $0.22 | 40,960 | 100.0% |
| GLM-5.3-Flash | fp8 | $0.17 | $0.55 | 1,048,576 | 99.9% |
| DeepSeek V4.1 Flash | fp8 | $0.21 | $0.84 | 1,048,576 | 100.0% |
| DeepSeek V4 Flash | fp8 | $0.35 | $1.06 | 1,048,576 | 100.0% |
| DeepSeek V4 Pro | fp8 | $1.06 | $3.17 | 1,048,576 | — |