Official site · 🇨🇳 China
21 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 |
|---|---|---|---|---|---|
| gpt-oss-20b | fp8 | $0.04 | $0.18 | 131,072 | 95.3% |
| Qwen3.5-9B | fp8 | $0.10 | $0.15 | 262,144 | 69.4% |
| gpt-oss-120b | fp8 | $0.05 | $0.45 | 131,072 | 99.4% |
| DeepSeek V4 Flash | fp8 | $0.14 | $0.28 | 1,048,576 | 99.8% |
| Gemma 4 26B A4B | fp8 | $0.12 | $0.40 | 262,144 | 99.6% |
| Gemma 4 31B | fp8 | $0.13 | $0.40 | 262,144 | 98.9% |
| Qwen3 32B | fp8 | $0.14 | $0.57 | 131,072 | 100.0% |
| DeepSeek V3.2 | fp8 | $0.26 | $0.42 | 163,840 | 99.2% |
| DeepSeek V3 0324 | fp8 | $0.25 | $1.00 | 163,840 | 99.6% |
| DeepSeek V3.1 Terminus | fp8 | $0.27 | $1.00 | 163,840 | 98.9% |
| Qwen3.6 35B A3B | fp8 | $0.20 | $1.60 | 262,144 | 99.9% |
| Qwen3.5-35B-A3B | fp8 | $0.24 | $1.80 | 262,144 | — |
| Qwen3.5-122B-A10B | fp8 | $0.26 | $2.08 | 262,144 | 100.0% |
| Kimi K2.5 | int4 | $0.45 | $2.25 | 262,144 | 100.0% |
| Nex-N2-Pro | unknown | $0.50 | $2.50 | 262,144 | — |
| Qwen3.6 27B | fp8 | $0.30 | $3.20 | 262,144 | 99.9% |
| Kimi K2.6 | fp8 | $0.77 | $3.40 | 262,144 | 99.7% |
| Kimi K2.7 Code | fp8 | $0.86 | $3.80 | 262,144 | 100.0% |
| GLM-5.2 | fp8 | $1.19 | $3.74 | 1,048,576 | 100.0% |
| GLM-5.1 | fp8 | $1.19 | $3.74 | 204,800 | 98.8% |
| DeepSeek V4 Pro | fp8 | $1.32 | $3.96 | 1,048,576 | 100.0% |