What is the cheapest Xiaomi model?

MiMo-V2.5 is the lowest blended-price option among tracked active non-embedding models, or among all models if only embeddings are listed: $0.14 input and $0.28 output per million tokens ($0.18 blended). Blended pricing uses 75% input and 25% output for generation models; your cheapest option may differ with your workload.

Which Xiaomi model has the highest AA Intelligence score?

MiMo-V2.6-Pro has the highest listed Artificial Analysis Intelligence Index score among tracked active Xiaomi models: 46.3. This is one evaluation, not a guarantee of the best result for every task. Models without measured results are not ranked as zero.

How do I calculate monthly Xiaomi API costs?

Multiply input tokens in millions by the input rate and add output tokens in millions multiplied by the output rate. For example, 20 million input and 5 million output tokens on MiMo-V2.5 cost an estimated $4.20 at the listed rates. This excludes tool charges, cache-specific charges, taxes and any endpoint-specific adjustments.

Which Xiaomi model has the largest context window?

MiMo-V2.5 has a listed context window of 1.1M tokens, the largest among tracked active Xiaomi models. Context capacity and maximum response length are separate limits; verify both on the model page and in the endpoint documentation.

What is the latest Xiaomi model in the catalog?

MiMo-V2.6-Flash has the most recent listed release date among tracked active Xiaomi models: 2026-09-21. Models without a usable release date are excluded from this comparison. Catalog release dates do not guarantee immediate API availability.

Do Xiaomi models support image inputs?

4 tracked active models list image inputs, including MiMo-V2.5, MiMo-V2.6-Flash, MiMo-V2.6-Pro. Accepting images does not mean a model generates images; check each model's separate input and output formats and endpoint limits.

Can prompt caching lower Xiaomi API costs?

5 tracked active models have a listed cached-input rate, including MiMo-V2.5, MiMo-V2.5-Pro, MiMo-V2.6-Flash. Savings depend on eligible repeated input and the endpoint's cache rules, duration and any write charges.

Do Xiaomi models support tool calling?

5 tracked active models list tool-calling capabilities, including MiMo-V2.5, MiMo-V2.5-Pro, MiMo-V2.6-Flash. Verify the exact tool schema and availability with your API endpoint before integrating.

How should I compare Xiaomi benchmark scores and prices?

Compare scores within the same evaluation: Artificial Analysis Intelligence Index, DesignArena Elo, general Arena Elo and MMLU-Pro use different tasks and scales. Missing results are not zeroes. Pair a relevant measured benchmark with input/output pricing and tests of your own workload; the cheapest or highest-scoring model is not automatically the best fit.

Are retired Xiaomi models included in the price list?

The price list shows active models by default. Turn on Show retired models to include retired catalog entries, where available. A retained model page preserves reference information, not a promise that its API is still available.

Is Xiaomi an AI lab or an inference host?

Xiaomi is categorized as an AI lab in this catalog. Individual model pages list available API hosts separately; model creator and API host are different roles.

AI lab

Xiaomi API pricing & models

We track 5 Xiaomi models, priced from $0.14 per 1M input tokens with context windows up to 1.1M tokens.

Models tracked

Text & Reasoning · Vision

$0.18

Cheapest model

MiMo-V2.5

46.3

Top quality score

MiMo-V2.6-Pro

1.1M

Largest context

6-mo price trend 0%

Price list

All Xiaomi models and prices

Current Xiaomi API prices per 1M tokens, context windows and benchmark scores. Click a column to sort, or a model for full pricing details.

Show retired models


MiMo-V2.6-Pro Xiaomi	$0.435	$0.87	1.1M	46.3	—	—	—	0%
MiMo-V2.6-Flash Xiaomi	$0.14	$0.28	1.1M	37.9	—	—	—	0%
MiMo-V2.5-Pro Xiaomi	$0.435	$0.87	1.1M	26	1270	—	—	0%
MiMo-V2.5 Xiaomi	$0.14	$0.28	1.1M	—	1264	—	—	0%
MiMo-V2.6-Pro-UltraSpeed Xiaomi	$4.35	$8.7	1M	—	—	—	—	0%

MiMo-V2.6-Pro Xiaomi

Input /1M: $0.435
Output /1M: $0.87
Context: 1.1M
AA Intelligence: 46.3
DesignArena Elo: —
Arena Elo: —
MMLU-Pro: —
30d trend: 0%

MiMo-V2.6-Flash Xiaomi

Input /1M: $0.14
Output /1M: $0.28
Context: 1.1M
AA Intelligence: 37.9
DesignArena Elo: —
Arena Elo: —
MMLU-Pro: —
30d trend: 0%

MiMo-V2.5-Pro Xiaomi

Input /1M: $0.435
Output /1M: $0.87
Context: 1.1M
AA Intelligence: 26
DesignArena Elo: 1270
Arena Elo: —
MMLU-Pro: —
30d trend: 0%

MiMo-V2.5 Xiaomi

Input /1M: $0.14
Output /1M: $0.28
Context: 1.1M
AA Intelligence: —
DesignArena Elo: 1264
Arena Elo: —
MMLU-Pro: —
30d trend: 0%

MiMo-V2.6-Pro-UltraSpeed Xiaomi

Input /1M: $4.35
Output /1M: $8.7
Context: 1M
AA Intelligence: —
DesignArena Elo: —
Arena Elo: —
MMLU-Pro: —
30d trend: 0%

Xiaomi input vs output prices

USD per 1M tokens for each model.

Xiaomi price history

Blended price per 1M tokens over the last 6 months.

By use case

Xiaomi models by category

Text & Reasoning

5 models · cheapest

MiMo-V2.5

$0.18 blended / 1M

Vision

4 models · cheapest

MiMo-V2.5

$0.18 blended / 1M

Comparisons

Xiaomi vs other AI providers

Compare MiMo-V2.6-Pro with models from other AI providers, including pricing and benchmark results.

Xiaomi vs Google

MiMo-V2.6-Pro vs Nano Banana Pro (Gemini 3 Pro Image)

$0.54 vs $4.50 · Arena Elo — vs 1211

Xiaomi vs Anthropic

MiMo-V2.6-Pro vs Claude Opus 5.5

$0.54 vs $8.00 · Arena Elo — vs —

Xiaomi vs OpenAI

MiMo-V2.6-Pro vs GPT-5.2 Pro

$0.54 vs $58 · Arena Elo — vs 1255

Xiaomi vs xAI

MiMo-V2.6-Pro vs Grok 4.7

$0.54 vs $3.00 · Arena Elo — vs —

Xiaomi vs Meta

MiMo-V2.6-Pro vs Muse Spark 1.3

$0.54 vs $2.00 · Arena Elo — vs —

Xiaomi vs DeepSeek

MiMo-V2.6-Pro vs DeepSeek V4.1 Flash

$0.54 vs $0.34 · Arena Elo — vs —

FAQ

Xiaomi pricing FAQ

Tracked active Xiaomi models range from $0.14 to $4.35 per million input tokens. Output rates are listed separately for each model. Prices vary by model and API endpoint; these are token rates, not a subscription quote.