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 |
|---|---|---|---|---|---|
| GLM-5.3-Flash | unknown | $0.04 | $0.50 | 1,048,576 | 99.2% |
| DeepSeek V4.1 Flash | unknown | $0.02 | $0.60 | 1,048,576 | 99.9% |
| DeepSeek V4 Flash | fp4 | $0.01 | $1.28 | 1,048,576 | 98.9% |
| GLM-5.2 | unknown | $0.10 | $4.00 | 1,048,576 | 100.0% |
| GLM-5.3 | unknown | $0.12 | $4.00 | 1,048,576 | 100.0% |
| DeepSeek V4 Pro | fp4 | $0.90 | $2.70 | 1,048,576 | 100.0% |
| Kimi K3 | fp4 | $0.99 | $13.00 | 1,048,576 | 100.0% |