The Mimo Token API updates page tracks all official announcements, feature releases, and pricing changes for Mimo Token API. (Currently 2 posts, last updated on 2026-08-15.) Posts are listed in reverse chronological order to help developers, product managers, and AI users quickly understand the latest changes and make informed decisions about renewals, switching, or integration.

All updates are curated from the official Mimo Token API pricing page, covering model releases and deprecations, API changes, pricing adjustments and promotions, quota and rate limit updates, and third-party integration adapters. Check back regularly, or visit the Mimo Token API pricing page for full plan details, top-up deals, and API key setup guides.

Mimo Token API Pricing, Top-up, Deals, Quota, Usage, Setup & Updates

2 posts · Updated 2026-08-15

Mimo Token API Updates · Article List

PricingPublished 2026-08-15Updated 2026-08-15

Xiaomi MiMo-V2.5 API Price Cut Up to 99%: Pro ¥3/¥6 vs ¥7/¥21 Pricing Comparison

MiMoAPIPricing ComparisonPrice CutV2.5Xiaomi

Xiaomi MiMo-V2.5 API pricing was permanently cut on May 27, 2026, by up to 99%, removing context-length tiers. MiMo-V2.5-Pro now costs ¥0.025 cache-hit / ¥3 input / ¥6 output per 1M tokens, and the standard model ¥0.02 / ¥1 / ¥2, versus the old V2 series (Pro ¥7/¥21). This pricing comparison breaks down the real reduction on cache-hit input, cache-miss input and output, and compares MiMo against DeepSeek and Claude to help you decide if it is worth switching.

AnalysisPublished 2026-08-11Updated 2026-08-15

MiMo-V2.5 API Pricing Compared: Pro vs Standard — Cache-Hit Savings & Which to Choose

MiMoAPIpricing comparisonV2.5Pro

Xiaomi MiMo-V2.5's open API now offers two text models: flagship Pro (¥3 input / ¥6 output, ¥0.025 cache hit) and multimodal Standard (¥1 input / ¥2 output, ¥0.02 cache hit), both at flat per-million-token pricing with no context-length tiering. Web search costs ¥16 per 1K calls, ASR ¥0.5/hour, the TTS series is temporarily free, and the V2 series retired June 30. This article compares the two models' capabilities, ideal workloads, and cost curves under different cache-hit rates, helping you balance complex reasoning against high-frequency calls for the lowest cost.

Mimo Token API FAQ: How to Save More? Pricing, Cache Deals, API Key Setup & Top-up Questions

What new models or key updates are available for MiMo-V2.5 API?

Recent key updates: MiMo-V2.5 series is now the sole model family after V2 retirement; text-model pricing dropped significantly (Pro input ¥3/output ¥6, standard input ¥1/output ¥2) with lower cache-hit pricing; web search lowered to ¥16/1K calls. TTS speech synthesis remains free for a limited time.

What are the prices for MiMo-V2.5 Pro and Standard text models?

All pay-as-you-go, per 1M tokens. Pro: input ¥3/output ¥6 (cache hit ¥0.025). Standard: input ¥1/output ¥2 (cache hit ¥0.02), no longer tiered by context length. Priced uniformly on the Xiaomi open platform.

How much does web search and speech support cost on MiMo API?

Web search plugin ¥16 per 1,000 calls domestically, $5 per 1,000 calls overseas. ASR billed by audio duration (¥0.5/hour domestic, $0.074/hour overseas). TTS series (base TTS, VoiceClone, VoiceDesign) currently free for a limited time with no billing timeline announced. Budget accordingly if speech features are production-critical.

Can I use the same key for MiMo API and Token Plan? How do I get one?

Cannot mix. MiMo open API uses `sk-` prefixed keys deducting from account balance; create in console under "API Keys" after registration. Token Plan uses `tp-` prefixed keys with separate Base URLs; obtain from the Token Plan subscription page. These are fully separate billing systems. Base URLs: China (api.xiaomimimo.com), Singapore (api-sg.xiaomimimo.com), Amsterdam (api-eu.xiaomimimo.com)—choose based on account region.

How does MiMo API context caching save money? Which scenarios benefit most?

Cache hits drastically cut input costs (Pro from ¥3 to ¥0.025, standard from ¥1 to ¥0.02 per 1M tokens—over 98% saved). Cache writes are free; no developer config needed—prefix matching triggers automatically. Best scenarios: multi-turn conversations with shared history, repeated contexts on the same project, API calls with fixed system prompts. Output-heavy workloads (e.g., batch generation) see limited benefit since caching mainly saves on input.

Mimo Token Plan Related

Mimo Token Plan Pricing, Top-up, Deals & Official Entry

Mimo Token Plan subscription pricing. 4 tiers (Token Plan, from ¥39/mo/mo). with 4.1B-82B Credits/mo. MiMo-V2.5-Pro and 5 more models. MiMo Code, OpenCode, OpenClaw and 8 more tools integrations. Plan quotas, perks, and official entry—is it worth it?