Xiaomi

MiMo V2.6 ProOpen

Xiaomi MiMo V2.6 Pro: open-weights model with strong math results and 1.0M context.

#388released Sep 8, 2026·Open Weights·Not disclosed
textimage1.0M ctx
API providersRun Model →Leaderboard
Intelligence
52.5 #388
Top 50% tier
Output Speed
72 t/s
TTFT 340 ms · ITL 13.9 ms/tok
Blended price (3:1)
$0.477 /1M
In $0.48/M · Out $0.95/M
Context
1.0M
≈ 2,500 A4 pages · max out 16,384

Quality Domain Radar

6-Axis Frontier Evaluation vs Category Average & Flagship

MiMo V2.6 Pro
Claude Mythos Preview (#1)
Average (68)
Coding (45)Mathematics (95)Hard Science (GPQA) (42)Agentic & Tool Use (56.5)Knowledge (MMLU) (45)Vision / Multimodal (30)

Radar axes are approximated from category scores where direct benchmark measurements are missing — see Methodology.

Strengths & Trade-offs

Where it wins

  • Open weights — self-host, fine-tune and audit with no vendor lock-in
  • 1.0M context — swallows whole repos, codebases or corpora in one pass
  • Sub-400ms time-to-first-token
  • Very low blended price — $0.477/1M mixed tokens

Killer Use Cases

Quantitative pipelines
Numeric reasoning for finance, science and engineering calculations.
High-volume batch jobs
Classification, extraction and summarization at minimal cost per call.
Whole-repo analysis
Single-pass ingestion of large codebases, contracts or research corpora.

Developer Quickstart & API

Set MIMO_API_KEY first — get an API key
curl https://api.mimo.mi.com/v1/chat/completions \
  -H "Authorization: Bearer $MIMO_API_KEY" \
  -H "content-type: application/json" \
  -d '{
    "model": "mimo-v2-6-pro",
    "messages": [{"role": "user", "content": "Refactor this function for O(n) time and explain the change."}]
  }'

Official Resources & Links

API deployment

Compare hosts & latency

Throughput, TTFT and cache pricing across Groq, Cerebras, Together, DeepInfra, Fireworks, Bedrock and Azure.

GroqCerebrasTogether AIDeepInfraFireworks AIAWS BedrockAzure AI
View providers matrix →

Scores by Source

Live Specs & Architecture

Under the hood
  • Prompt caching supported — cached input reads at $0.048/1M tokens.
Release date
Sep 8, 2026
Parameters
Not disclosed
License
Open Weights
Context Window
1,000,000 tokens
Max Output
16,384 tokens
Modalities
text + image
Cache Pricing
read $0.048 · write $0.6 /1M
Reasoning
—
Input Price
$0.48/M
Output Price
$0.95/M
Output Speed
72 t/s
Time to First Token
340 ms
Data Updated
Sep 26, 2026

Estimated monthly bill

Estimated monthly spend
$0.00
Calculating savings vs GPT-4o...

Cite & embed

GitHub Markdown badge
Loading badge markdown...
BibTeX
@misc{llmpodium2026mimov26pro,
  title = {Benchmark Analysis and Intelligence Evaluation of MiMo V2.6 Pro},
  author = {LLMPodium Research},
  year = {2026},
  url = {https://llmpodium.com/models/mimo-v2-6-pro}
}

Embed Score Badge

Add a live Podium Score badge to your GitHub or Hugging Face README — it links back to the live ranking.

Preview
MiMo V2.6 Pro LLMPodium Score
Markdown
Loading badge snippet...
HTML
Loading badge snippet...

More from Xiaomi

Alternative Models

Closest alternatives to MiMo V2.6 Pro based on capabilities, pricing, and benchmark scores.

0 / 4