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 |
|---|---|---|---|---|---|
| DeepSeek V4 Flash | fp4 | $0.09 | $0.18 | 262,144 | 99.4% |
| GLM-5.2 | fp8 | $0.50 | $3.15 | 1,048,576 | 99.6% |
| Kimi K2.6 | int4 | $1.00 | $4.00 | 262,144 | 100.0% |
| Kimi K3 | fp4 | $3.00 | $15.00 | 974,842 | 99.6% |