Models

MiMo-V2.5

xiaomi · 1050K ctx · 5 providers · updated 2026-08-04 22:15 UTC

Cheapest
$0.175 via OpenRouter
Avg price
$0.432 /1M
providers
5
Tokens (24h)
744B
Volume (24h)
$130.2K est.
(3 × $0.140 + $0.280) ÷ 4 = $0.175/1M — the $/1M figure blends input and output at 3:1 — that is the only way models with two different rates can be ranked on one axis. Your actual rate depends on your own input:output mix — input only $0.140, 3:1 $0.175, 1:1 $0.210, output only $0.280 per 1M.

The board shows this model's cheapest measured offer ($0.175/1M); the smaller figure under it is the mean of the 5 offers listed below ($0.432/1M). Add those up and divide — it matches. 24h token volume (744B) is sourced from OpenRouter public rankings — today's only public source of absolute per-model token counts (Vercel AI Gateway publishes share-of-traffic percentages); as more sources come online, the per-router breakdown will sum to this total here.

ProviderRouter / Source$ in /1M$ out /1MTTFTTPSUptimeEvidence
openrouter-best OpenRouter $0.140$0.280 API-measured
requesty Requesty $0.140$0.280 API-measured
novita-ai Novita AI $0.168$0.336 API-measured
openrouter Pricebook (LiteLLM) $0.400$2.00 Official list
deepinfra HuggingFace Router $0.400$2.00 390ms 51 API-measured

Volume trend

1.6T 30d d-29 · 624B tokensd-28 · 658B tokensd-27 · 666B tokensd-26 · 669B tokensd-25 · 745B tokensd-24 · 921B tokensd-23 · 1.1T tokensd-22 · 1.2T tokensd-21 · 1.3T tokensd-20 · 1.4T tokensd-19 · 1.4T tokensd-18 · 1.4T tokensd-17 · 1.4T tokensd-16 · 1.2T tokensd-15 · 1.2T tokensd-14 · 1.3T tokensd-13 · 1.5T tokensd-12 · 1.6T tokensd-11 · 1.6T tokensd-10 · 1.5T tokensd-9 · 1.4T tokensd-8 · 1.5T tokensd-7 · 1.6T tokensd-6 · 1.3T tokensd-5 · 736B tokensd-4 · 722B tokensd-3 · 735B tokensd-2 · 590B tokensd-1 · 588B tokensd-0 · 744B tokens

Last 30 days: 624B → 744B (+19%); range 588B–1.6T tokens/day. Source: OpenRouter public rankings; refreshed hourly.

Data & method

Cheapest ranked by blended = (3×in + out) ÷ 4; performance columns show only when a source provides them, never estimated. “Official list” = LiteLLM open pricebook (MIT); “API-measured” = provider/aggregator public APIs. Machine-readable data: /api/v1/models/mimo-v2.5.json. Free reuse requires attribution to tkx.org.

About

MiMo-V2.5 is a large language model offered on AI model marketplaces, designed for natural language processing tasks. It is associated with the organization Xiaomi and served by multiple inference providers.

AI-generated summary from public information — is this yours?

FAQ

How much does MiMo-V2.5 cost?

Cheapest measured offer right now: $0.14/1M input, $0.28/1M output via openrouter-best — across 5 tracked providers, refreshed hourly.

Who serves MiMo-V2.5?

5 providers currently serve it. The table above lists each with input/output price, TTFT, TPS, uptime and an evidence tier.

How heavily is MiMo-V2.5 used?

MiMo-V2.5 routed 744B tokens in the last 24h. The daily bars above show routed volume over recent days. Source: OpenRouter public rankings — one of the few routers publishing per-model usage; TKX refreshes hourly.

Related analysis

Back to rankings