Reference
API model economics
Subscribe to see where we rank in the Quality per USD ranking below from claw-eval.
Frontier AI models
Frontier AI models
Based on common openclaw tasks the frontier AI models rank 10 to 13 in Quality per USD at https://claw-eval.github.io/
Other AI models
Other AI models
In the same analysis, with pricing for Xiaomi outside China, the model MiMo V2 Pro of Xiaomi has same score as the frontier model Gemini 3.1 Pro at a fraction of the cost.
| # | Model | Provider | Score | Price of 1M output tokens | USD per 1M output tokens | Quality per USD |
|---|---|---|---|---|---|---|
| 1 | DeepSeek V3.2 | DeepSeek | 40.2% | $0.42 | $0.42 | 95.714 |
| 2 | MiniMax M2.7 | MiniMax | 48.7% | $1.20 | $1.20 | 40.583 |
| 3 | MiMo V2 Pro | Xiaomi | 57.8% | $2 | $2.00 | 28.900 |
| 4 | MiMo V2 Omni | Xiaomi | 45.2% | $2 | $2.00 | 22.600 |
| 5 | GLM 5 Turbo | Zhipu AI | 55.8% | ¥22 | $3.03 | 18.416 |
| 6 | GLM 5V Turbo | Zhipu AI | 53.8% | ¥22 | $3.03 | 17.756 |
| 7 | Gemini 3 Flash | 49.2% | $3.00 | $3.00 | 16.400 | |
| 8 | Qwen3.5 397A17B (qwen3.5-397b-a17b) | Alibaba | 56.8% | $3.60 | $3.60 | 15.778 |
| 9 | Kimi K2.5 | Moonshot AI | 37.2% | $3.00 | $3.00 | 12.400 |
FAQ
Fallback when local inference fails
Can you add a fallback model in case the local model fails in a request?
If you subscribe to our Technical Support and then book a Done For You service, we can help you subscribe to Xiaomi and configure your setup to use it as a fallback. However, in any case optimizing your OpenClaw prompts can cut token usage by 50%.