Official site · origin not confirmed
7 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 | $0.02 | $0.30 | 1,048,576 | 99.9% |
| DeepSeek V4 Flash | fp4 | $0.02 | $0.42 | 1,048,576 | 99.9% |
| DeepSeek V4.1 Flash | fp4 | $0.08 | $0.40 | 1,048,576 | 99.9% |
| GLM-5.3-Flash | fp4 | $0.04 | $0.60 | 1,048,576 | 99.1% |
| GLM-5.3 | fp8 | $0.20 | $3.40 | 1,048,576 | 98.9% |
| GLM-5.3 | fp8 | $0.20 | $3.40 | 1,048,576 | 99.2% |
| Kimi K3 | fp4 | $2.80 | $14.00 | 1,048,576 | — |