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 |
|---|---|---|---|---|---|
| DeepSeek V4 Flash | fp4 | $0.05 | $0.65 | 1,048,576 | 100.0% |
| GLM-5.3-Flash | fp8 | $0.22 | $0.45 | 1,048,576 | 98.8% |
| Kimi K2.6 | int4 | $0.43 | $2.45 | 262,144 | 100.0% |
| GLM-5.3 | fp4 | $0.60 | $3.39 | 1,048,576 | 100.0% |
| Kimi K2.7 Code | int4 | $0.67 | $3.35 | 262,144 | 99.9% |
| GLM-5.2 | fp4 | $1.25 | $4.39 | 1,048,576 | — |