Xiaomi: API pricing, speed & models

Xiaomi is an API provider that hosts large language models. Active models: 3; From (input): $0.14 / 1M tok; Median throughput: 65 c/s; Median TTFT: 8.93s; Success rate (7d): 100%.

Xiaomi currently serves 3 active models out of 6 historical offerings on LLM Stats.

Xiaomi input pricing starts from $0.14 per 1M tokens, with the most expensive offering at $0.435 per 1M tokens. See the Pricing tab above for the full per-model breakdown.

Xiaomi delivers a median throughput of 65 characters per second and P95 time to first token of 11.55s across its model catalog. See the Models tab for per-model throughput and TTFT breakdowns.

Xiaomi has a 100% success rate across 3 API calls in the last 7 days, with a 0% error rate.

Yes. 9 of 3 models on Xiaomi support function calling (tool use). The Capabilities tab lists which specific models accept tool definitions.

Yes. 9 of 3 models on Xiaomi support structured output (JSON mode / schema-constrained generation). The Capabilities tab shows which specific models accept response_format or json_schema parameters.

Yes. Xiaomi's catalog includes 2 vision-capable models. See the Models and Capabilities tabs for the full per-model breakdown.

Xiaomi hosts models from Xiaomi. See the Models tab for the full catalog grouped by creator.

Sign up at https://mimo.xiaomi.com/ to get an API key, then call Xiaomi's API directly from your application. Most clients work out of the box by pointing the OpenAI SDK at Xiaomi's base URL with your key. Use the Models and Pricing tabs above to pick the right model for your latency, cost, and context-window requirements.