MiMo-V2.5: API Pricing, Context Window & Benchmarks
MiMo-V2.5 is a language model from Xiaomi, released in April 2026, with multimodal input, a 1.0M-token context window, and pricing from $0.400/M input and $2.00/M output.
MiMo-V2.5 is Xiaomi's native omnimodal sparse Mixture-of-Experts model with 310B total parameters, 15B activated parameters, and a 1M-token context window. Built on the MiMo-V2-Flash backbone, it adds dedicated vision and audio encoders
MiMo-V2.5 benchmarks
Rankings
Quality Tracker
MiMo-V2.5 Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Sat Jul 18 2026MiMo-V2.5 pricing
Providers
MiMo-V2.5 starts at $0.168 per million input tokens and $0.336 per million output tokens via Novita. See all 2 providers below with their per-token pricing, latency, throughput, and modality support.
| Provider | Input $/M | Output $/M | Workload 1M + 100K | Context in / out | TTFT p50 / p95 s | Output avg / p5 c/s | Success 7d | Modalities in / out |
|---|---|---|---|---|---|---|---|---|
 Novita | $0.168 | $0.336 | $0.202 | 1.0M/131.1K | 1.08/1.08 | 328/328 | 40.00%(45) | / |
 DeepInfra | $0.400 | $2.00 | $0.600 | 262.1K/131.1K | 0.52/1.75 | 233/54 | 100.00%(61) | / |
Workload cost uses 1M input tokens plus 100K output tokens at published list prices without assuming a cache hit. Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests. Success is calculated from completed versus failed requests over the trailing seven days.
MiMo-V2.5 model size
MiMo-V2.5 has 310.8 billion parameters and was trained on 48 trillion tokens. See how it compares to other models in the same parameter range.
MiMo-V2.5 context window
Input and output token limits for MiMo-V2.5, plus how it ranks on long-context understanding.
MiMo-V2.5 API
Run a request to see the response
Use it in your code
Billed at $0.40 input / $2.00 output per 1M tokens through the LLM Stats gateway.
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://gateway.llm-stats.com/v1"
)
response = client.chat.completions.create(
model="mimo-v2.5",
messages=[
{"role": "user", "content": "What is machine learning?"}
]
)
print(response.choices[0].message.content)Need an API key? Create one above in the playground, or read the API documentation.
MiMo-V2.5 latency
MiMo-V2.5 time to first token, sustained output throughput, and failed-request rate from live API traffic over the trailing 7 days.
Provider operational metrics
Time to first token, output throughput, and failed-request rate from live API traffic
MiMo-V2.5 examples
Recent arena outputs from MiMo-V2.5, picked from the highest-ranked matchups.
MiMo-V2.5 license
MiMo-V2.5 is released under the MIT license, which permits commercial use, has 310.8B parameters.
- License
- MIT
- Commercial use allowed
- Parameters
- 310.8B
MIT License - allows commercial use
MiMo-V2.5 resources
Official sources for MiMo-V2.5: official playground, official launch post, model weights.
MiMo-V2.5 vs other models
The most-compared alternatives to MiMo-V2.5 are Claude Opus 4.6, Gemini 3 Pro, Gemini 3 Flash. Open any pair side-by-side for benchmarks, pricing, context, and latency.
Models like MiMo-V2.5
Models ranked just above and below MiMo-V2.5 by LLM Stats score.
FAQ
Common questions about MiMo-V2.5.