MiMo-V2.5-Pro: API Pricing, Context Window & Benchmarks
MiMo-V2.5-Pro is a language model from Xiaomi, released in April 2026, with a 1.0M-token context window, and pricing from $1.00/M input and $3.00/M output.
MiMo-V2.5-Pro is Xiaomi's 1.02T-parameter sparse Mixture-of-Experts language model with 42B active parameters and a 1M-token context window. It inherits the MiMo-V2-Flash hybrid-attention and Multi-Token Prediction design, extends context
MiMo-V2.5-Pro benchmarks
Rankings
Quality Tracker
MiMo-V2.5-Pro Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Sat Jul 18 2026MiMo-V2.5-Pro pricing
Providers
MiMo-V2.5-Pro starts at $0.435 per million input tokens and $0.870 per million output tokens via Xiaomi. See all 3 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 |
|---|---|---|---|---|---|---|---|---|
 Xiaomi | $0.435 | $0.870 | $0.522 | 1.0M/131.1K | 2.82/10.74 | 132/5 | 94.59%(37) | / |
 DeepInfra | $1.00 | $3.00 | $1.30 | 1.0M/131.1K | 0.62/8.32 | 192/34 | 98.68%(76) | / |
 Novita | $2.00 | $6.00 | $2.60 | 1.0M/131.1K | 1.21/1.77 | 285/249 | 14.29%(21) | / |
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-Pro model size
MiMo-V2.5-Pro has 1.0 trillion parameters and was trained on 27 trillion tokens. See how it compares to other models in the same parameter range.
MiMo-V2.5-Pro context window
Input and output token limits for MiMo-V2.5-Pro, plus how it ranks on long-context understanding.
MiMo-V2.5-Pro API
Run a request to see the response
Use it in your code
Billed at $1.00 input / $3.00 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-pro",
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-Pro latency
MiMo-V2.5-Pro 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-Pro examples
Recent arena outputs from MiMo-V2.5-Pro, picked from the highest-ranked matchups.
MiMo-V2.5-Pro license
MiMo-V2.5-Pro is released under the MIT license, which permits commercial use, has 1.0T parameters.
- License
- MIT
- Commercial use allowed
- Parameters
- 1.0T
MIT License - allows commercial use
MiMo-V2.5-Pro resources
Official sources for MiMo-V2.5-Pro: api documentation, official playground, model weights.
MiMo-V2.5-Pro vs other models
The most-compared alternatives to MiMo-V2.5-Pro are Claude 3 Opus, GPT-4o, Qwen3 VL 235B A22B Instruct. Open any pair side-by-side for benchmarks, pricing, context, and latency.
Models like MiMo-V2.5-Pro
Models ranked just above and below MiMo-V2.5-Pro by LLM Stats score.
FAQ
Common questions about MiMo-V2.5-Pro.