Start free trial

Xiaomi: MiMo-V2.5

xiaomi/mimo-v2-5
CompareAPITry this model

MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding

Modalities
In / out per 1M$0.14 / $0.28
Context1M
ReleasedApr 22, 2026

Providers

5 providers serve this model upstream.

Providers serving this model
ProviderInput /MOutput /MCache read /MLatency P50Throughput P50Uptime
Xiaomifp8$0.14$0.28$0.003.97s24 tps98.81%
Venicefp8$0.40$2.00$0.082.22s21 tps97.38%
NovitaAIfp8$0.17$0.34$0.004.57s29 tps95.47%
GMICloudfp8$0.12$0.24$0.004.69s26 tps94.89%
StreamLake$0.17$0.34$0.003.92s19 tps42.02%

Market-wide measurements, refreshed every 15 minutes. They describe who serves MiMo-V2.5 in general, not how ProjectCOZY routes your requests.

Pricing

List rates per 1M tokens — what MiMo-V2.5 costs pay-as-you-go elsewhere, not what you pay here.

Input
$0.14
per 1M tokens
Output
$0.28
per 1M tokens
Cache read
$0.00
per 1M cached tokens
Included in every pass
MiMo-V2.5 is included in every ProjectCOZY pass at no extra cost — one flat rate, no per-token metering. The rates above are there for comparison.

Performance

Time to first token and output speed across every provider, over the last 3 days.

0.0s10.0s20.0s30.0s40.0s
Oct 16, 12 AMOct 16, 8 AMOct 16, 4 PMOct 17, 12 AMOct 17, 8 AMOct 17, 4 PMOct 18, 12 AMOct 18, 8 AMOct 18, 4 PMOct 19, 12 AMOct 19, 8 AM
NovitaAI GMICloud Venice StreamLake Xiaomi
0 tok/s50 tok/s100 tok/s150 tok/s200 tok/s
Oct 16, 12 AMOct 16, 8 AMOct 16, 4 PMOct 17, 12 AMOct 17, 8 AMOct 17, 4 PMOct 18, 12 AMOct 18, 8 AMOct 18, 4 PMOct 19, 12 AMOct 19, 8 AM
NovitaAI GMICloud Venice StreamLake Xiaomi

Uptime

100% of requests were served successfully over the last 3 days, across all providers.

Last 3 daysAvailability 99.22%
Oct 16, 11:00 AMNow
Availability over the last 24 hoursAvailability 99.45%
100% 97% 93% 90%
Oct 18, 11:00 AMNow

Apps

Tools that most often run MiMo-V2.5, by tokens this week.

ISEKAI ZEROGame · 46.1% of tokens271.7BClineIde Extension · 21% of tokens123.7BFreebuff15.7% of tokens92.2BClaude CodeCli Agent · 9.6% of tokens56.6BHermes AgentPersonal Agent · 7.7% of tokens45.1B

Activity

6729.9B tokens processed market-wide in the last month.

0250.0B500.0B750.0B1000.0B
Sep 19Sep 24Sep 29Oct 4Oct 9Oct 14Oct 19
Tokens

FAQ

Which model id do I use for MiMo-V2.5?
xiaomi/mimo-v2.5. Send it as the model field from any OpenAI-compatible client, against http://192.168.1.55/v1.
How much context does MiMo-V2.5 hold?
1,050,000 tokens per request, of which up to 131,072 can be the response.
What can it accept and return?
Input: text, audio, image, video. Output: text.
What does MiMo-V2.5 cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $0.14 per 1M input tokens and $0.28 per 1M output tokens.
Who built MiMo-V2.5?
Xiaomi, in the MiMo family.

Explore

Other models your pass can call.

Aion 3.5aion-labs/aion-3.5256KAionAion 3.5 Miniaion-labs/aion-3.5-mini256KAionAion-2.0aion-labs/aion-2.0128KAionAion-3.0aion-labs/aion-3.0128KAionAion-3.0-Miniaion-labs/aion-3.0-mini128KAionAion-RP 1.0 (8B)aion-labs/aion-rp-llama-3.1-8b32KAion