MIMO FLAGSHIP1T TOTAL PARAMS42B ACTIVE1M CONTEXTPROMPT CACHE
MiMo-V2.5-Pro API Pricing
Xiaomi lists MiMo-V2.5-Pro as a 1T-total-parameter / 42B-active MiMo reasoning model with 1M context. Live API pricing is $0.435/M input, $0.87/M output, and $0.0036/M cached input.
Input - per 1M tokens
$0.43/M
Source Xiaomi USD cache miss
Output - per 1M tokens
$0.87/M
Context 1M
Cached input - per 1M tokens
$0.00/M
Prompt cache hit row 99% off
Effective - agentic blend
$0.14/M
92/8 split - 82% cache
§ 01 / TERMINAL
Run the numbers.
Calculator pre-loaded with Xiaomi's live MiMo-V2.5-Pro USD rates. Use it for coding-agent and long-context estimates where the Pro tier matters more than the base V2.5 price.
$ /mo
Workload split
Prompt cache hit rate
Tokens you can process
—
Words equivalent (English)
—
Effective rate
—
§ 02 / SCENARIOS
Real-world presets.
CODING AGENT
Repo repair task
$0.028/task
OFFICE
Analyst memo draft
$0.020/memo
SEARCH
Web research brief
$0.013/brief
CHATBOT
Product support turn
$0.003/turn
§ 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 271
Words 44
Tokens (estimated) 70 tokens
Cost as input · uncached $0.000030 USD
Cost as output · uncached $0.000061 USD
Cost as cached input $0.000000 USD
| 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 Current | $0.43 cache $0.00 | $0.87 | $0.14 verified Xiaomi row | 1M | Xiaomi flagship agentic reasoning |
| MiMo-V2.5-Pro-UltraSpeed | $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 pricing, cache hits, context size, and 1T-parameter MiMo Pro workloads.
Q · 01 What is MiMo-V2.5-Pro priced at? +
Xiaomi's MiMo page lists
MiMo-V2.5-Pro at $0.435/M input, $0.0036/M cached input, and $0.87/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, that lands at about $0.14/M blended tokens.Q · 03 What context window does MiMo-V2.5-Pro 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.