Last verified
LIMITED ACCESS1000 TOK/S PEAK1M CONTEXTFAST PRO TIERPROMPT CACHE

MiMo-V2.5-Pro-UltraSpeed API Pricing

Xiaomi describes MiMo-V2.5-Pro-UltraSpeed as an early-access high-throughput Pro tier with a 1,000 tokens/s peak. Live list pricing is $1.305/M input, $2.61/M output, and $0.0108/M cached input.

Input - per 1M tokens
$1.30/M
Source Xiaomi USD cache miss
Output - per 1M tokens
$2.61/M
Context 1M
Cached input - per 1M tokens
$0.01/M
Prompt cache hit row 99% off
Effective - agentic blend
$0.43/M
92/8 split - 82% cache
§ 01 / TERMINAL

Run the numbers.

Calculator pre-loaded with the limited-access UltraSpeed row from Xiaomi's page. Treat this as a premium throughput tier, not the default MiMo Pro cost.

$ /mo
Workload split
Prompt cache hit rate
Tokens you can process
—
Words equivalent (English)
—
Effective rate
—
Open full calculator (all models · share URL · CSV) →
§ 02 / SCENARIOS

Real-world presets.

CODING AGENT

Repo repair task

$0.084/task
60,000 in / 2,000 out~1,197 units/$100
OFFICE

Analyst memo draft

$0.060/memo
40,000 in / 3,000 out~1,665 units/$100
SEARCH

Web research brief

$0.040/brief
25,000 in / 3,000 out~2,471 units/$100
CHATBOT

Product support turn

$0.010/turn
6,000 in / 1,000 out~9,578 units/$100
§ 03 / TOKENIZER

Paste text. See tokens. See cost.

Estimate · xiaomi-tokenizer-estimate · ≈3.85 chars/token Auto-counts as you type

This is a chars-per-token approximation, not a real tokenizer. Actual tokens vary by language, code density, and tool-call overhead — counts are typically ±10–20% off for English prose, more for code or non-Latin scripts. For exact billing, use the vendor's official tokenizer.

Characters 282
Words 44
Tokens (estimated) 73 tokens
Cost as input · uncached $0.000095 USD
Cost as output · uncached $0.000191 USD
Cost as cached input $0.000001 USD
§ 04 / SHELF

Up against the shelf.

All models →
Model Input /M Output /M Effective blended Context Best for
MiMo-V2.5 $0.14 cache $0.00 $0.28 $0.05 verified Xiaomi row 1M Budget omni-modal / text-capable agent loops
MiMo-V2.5-Pro $0.43 cache $0.00 $0.87 $0.14 verified Xiaomi row 1M Xiaomi flagship agentic reasoning
MiMo-V2.5-Pro-UltraSpeed Current $1.30 cache $0.01 $2.61 $0.43 limited access 1M High-throughput coding agents
MiniMax M3 $0.30 cache $0.06 $1.20 $0.19 verified sibling 1M MiniMax frontier coding agents
DeepSeek V4 Pro $0.43 cache $0.00 $0.87 $0.14 verified sibling 1M Low-cost reasoning workloads
Qwen3 Max $1.20 cache $1.20 $6.00 $1.05 verified sibling 1M Alibaba flagship workloads

Frequently asked.

Practical questions about MiMo-V2.5-Pro-UltraSpeed pricing, cache hits, context size, and latency-sensitive MiMo Pro workloads.

Q · 01 What is MiMo-V2.5-Pro-UltraSpeed priced at? +
Xiaomi's MiMo page lists MiMo-V2.5-Pro-UltraSpeed at $1.305/M input, $0.0108/M cached input, and $2.61/M output.
Q · 02 How is the effective price calculated? +
The headline effective tile uses the site standard agentic blend: 92% input, 8% output, and 82% input cache hits. For MiMo-V2.5-Pro-UltraSpeed, that lands at about $0.43/M blended tokens.
Q · 03 What context window does MiMo-V2.5-Pro-UltraSpeed support? +
Xiaomi's MiMo page lists 1M context for the V2.5 family row used on this page.
Q · 04 Does this page model media/audio/image pricing? +
No. Xiaomi lists TTS and ASR rows separately; this page is only the MiMo text-token API row for the V2.5 model. Media/audio pages should be built in a separate pass.
Q · 05 When was this price last checked? +
This page was verified against mimo.mi.com on 2026-07-01.
Y
Reviewed by Yaroslav Vikhariev Founder - AI//COST - Pricing pulled from mimo.mi.com - Last verified July 01, 2026
Methodology Report a correction More by Y.V.