The AI arena is free today

Open Superagent
API Provider1 active models1 organization

Xiaomi: API pricing, speed & models

Xiaomi hosts 1 active AI models, with input pricing from $0.43 per 1M tokens, with median throughput of 8 characters/sec, and P95 time to first token of 17.84s, with 100% success rate over 7 days. Compare Xiaomi's API speed, pricing, and reliability against other inference providers.

First-party only
Median throughput8 c/s
Median TTFT5.60s
P95 TTFT17.84s
Success rate (7d)100%
From$0.43 /M tok

Catalog

Type
Price
1 model
Model
At a glance

Xiaomipricing, performance & catalog

The citable facts about Xiaomi's 1 model — sourced from provider APIs and refreshed continuously.

Lowest price
MiMo-V2.5-Pro at $0.435 per 1M input tokens
Highest median throughput
MiMo-V2.5-Pro at 8 chars/s
Lowest median TTFT
MiMo-V2.5-Pro at 5.60s
Largest context
MiMo-V2.5-Pro at 1.0M tokens
Catalog
1 active models from 1 organization

Most affordable

  1. 1MiMo-V2.5-Pro$0.435/M

Fastest median throughput

  1. 1MiMo-V2.5-Pro8 c/s

Largest context

  1. 1MiMo-V2.5-Pro1.0M

FAQ

Common questions about Xiaomi.

What is Xiaomi?

Xiaomi is an API provider that hosts large language models. Active models: 1; From (input): $0.43 / 1M tok; Median throughput: 8 c/s; Median TTFT: 5.60s; Success rate (7d): 100%.

How many models does Xiaomi offer?

Xiaomi currently serves 1 active models out of 4 historical offerings on LLM Stats.

What is Xiaomi's API pricing?

Xiaomi input pricing starts from $0.43 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.

How fast is Xiaomi?

Xiaomi delivers a median throughput of 8 characters per second and P95 time to first token of 17.84s across its model catalog. See the Models tab for per-model throughput and TTFT breakdowns.

Is Xiaomi reliable?

Xiaomi has a 100% success rate across 10 API calls in the last 7 days, with a 0% error rate.

Does Xiaomi support function calling?

Yes. 1 of 1 models on Xiaomi support function calling (tool use). The Capabilities tab lists which specific models accept tool definitions.

Does Xiaomi support JSON mode and structured output?

Yes. 1 of 1 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.

Whose models does Xiaomi host?

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

How do I start using Xiaomi?

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.