Official site · 🇺🇸 United States
20 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 | fp4 | $0.03 | $0.15 | 131,072 | 99.3% |
| Qwen3.5-9B | bf16 | $0.10 | $0.25 | 262,144 | 100.0% |
| Mistral Small 3.2 | bf16 | $0.09 | $0.30 | 131,072 | 98.8% |
| Gemma 3 27B | fp8 | $0.08 | $0.45 | 131,072 | 99.9% |
| Xiaomi MiMo-V2.5 | fp8 | $0.14 | $0.28 | 1,048,576 | 99.4% |
| DeepSeek V4 Flash | fp8 | $0.14 | $0.28 | 1,048,576 | 94.9% |
| Gemma 4 26B A4B | bf16 | $0.13 | $0.40 | 262,144 | 99.3% |
| Gemma 4 31B | fp8 | $0.15 | $0.40 | 262,144 | 87.6% |
| gpt-oss-120b | fp4 | $0.10 | $0.75 | 131,072 | 100.0% |
| Qwen3 Coder Next | bf16 | $0.12 | $0.80 | 262,144 | 100.0% |
| Qwen3.6 35B A3B | fp8 | $0.15 | $1.00 | 262,144 | 99.9% |
| Qwen3.5-35B-A3B | fp8 | $0.15 | $1.00 | 262,144 | 100.0% |
| Trinity Large Thinking | fp4 | $0.22 | $0.85 | 262,144 | 100.0% |
| Llama 4 Maverick | fp8 | $0.35 | $1.00 | 524,288 | 99.9% |
| MiniMax-M3 | fp8 | $0.30 | $1.20 | 1,048,576 | 99.0% |
| Qwen3.5 397B A17B | fp8 | $0.50 | $3.60 | 262,144 | 99.9% |
| Kimi K2.6 | int4 | $0.75 | $3.50 | 262,144 | 99.6% |
| Kimi K2.7 Code | int4 | $0.76 | $3.50 | 262,144 | 99.8% |
| GLM-5.2 | fp4 | $1.40 | $4.40 | 262,144 | 99.9% |
| GLM-5.1 | fp8 | $1.40 | $4.40 | 202,752 | 100.0% |