MiMo-V2.6-Flash benchmarks, pricing and specs
MiMo-V2.6-Flash is a Xiaomi MiMo model released on September 22, 2026 that takes text, image, audio and video input and produces text. It costs $0.14 per 1M input tokens and $0.28 per 1M output tokens and accepts up to 1,000,000 tokens of context. It scores 1451 Elo on Arena Text, #35 of 49 current models (Arena, measured October 8, 2026).
- Per 1M input tokens
- $0.14
- Per 1M output tokens
- $0.28
- Context window
- 1M
- Arena Text
- 1451 Elo · #35/49
Data verified October 13, 2026 · Dataset 2026-10-13
Key facts
- Provider
- Xiaomi MiMo
- Model family
- MiMo-V2.6
- Release date
- September 22, 2026
- Status
- Current
- Access
- API and open weights
- API model id
- mimo-v2.6-flash
- Context window
- 1,000,000 tokens
- Max output
- 128,000 tokens
- Input
- text, image, audio, video
- Output
- text
- Task families
- text, multimodal
- Declared capabilities
- reasoning, agentic coding, image understanding, video understanding, audio understanding
MiMo-V2.6-Flash pricing
It is the #4 cheapest of 47 current text models priced per 1M input tokens.
Independent benchmark results
Scores come from independent evaluators that ran the model themselves, pinned to a dated snapshot. Rank is among current models in the same snapshot. Xiaomi MiMo's own launch figures are listed under strengths with the publisher named, because they are not measured the same way.
| Benchmark | Score | Rank | Measured | Source |
|---|---|---|---|---|
| Arena Text | 1451 Elo | #35 of 49 | October 8, 2026 | Arena · 2026-10-12 |
Strengths, cautions and best uses
Strengths
- Xiaomi reports 87.6 on Terminal Bench 2.1, close to the Pro model at a third of the price
- A 309B-parameter mixture-of-experts model with 15B active, taking text, image, video and audio with a 1M-token context
- $0.14 input and $0.28 output per 1M tokens on the overseas API, halved on the Batch API
Cautions
- Xiaomi's own table puts it well behind the Pro model on exploitation tasks (ExploitBench 25.3 against 47.9)
- The API checkpoint (RL or MOPD weights) is not identified
Best for
- High-frequency multimodal calls
- Low-cost agent workloads
Alternatives to MiMo-V2.6-Flash
The closest current textmodels by price. The cheapest model that scores as well or better is listed first; failing that, the cheapest one within 3% of the benchmark's scale.
Cheaper, similar score
GPT-6 Luna
- 29% cheaper per 1M input tokens, $0.10 vs $0.14
- 8 points lower on Arena Text, 1443 vs 1451
- From OpenAI
GLM-5.3-Flash
- 7% more per 1M input tokens, $0.15 vs $0.14
- 24 points higher on Arena Text, 1475 vs 1451
- From Z.ai
GPT-4.1 nano
- 29% cheaper per 1M input tokens, $0.10 vs $0.14
- 129 points lower on Arena Text, 1322 vs 1451
- From OpenAI
Claude Haiku 5.5
- 29% cheaper per 1M input tokens, $0.10 vs $0.14
- From Anthropic
Compare MiMo-V2.6-Flash with
Other MiMo-V2.6 models
MiMo-V2.6-Flash FAQ
How much does MiMo-V2.6-Flash cost?
MiMo-V2.6-Flash costs $0.14 per 1M input tokens and $0.28 per 1M output tokens at the standard tier. It is the #4 cheapest of 47 current text models priced per 1M input tokens. Source: Xiaomi, verified October 13, 2026.
What is the context window of MiMo-V2.6-Flash?
MiMo-V2.6-Flash accepts up to 1,000,000 tokens of context. It can return up to 128,000 tokens in one response. That ranks #25 of 57 current text models by context length.
How does MiMo-V2.6-Flash score on independent benchmarks?
MiMo-V2.6-Flash scores 1451 Elo on Arena Text, #35 of 49 current models (Arena, measured October 8, 2026). These are independent evaluations, not Xiaomi MiMo's own launch figures.
Is MiMo-V2.6-Flash open source or API only?
MiMo-V2.6-Flash is available both through Xiaomi MiMo's API and as open weights you can run yourself.
What are the best alternatives to MiMo-V2.6-Flash?
The closest current alternatives by price and measured performance are GPT-6 Luna (29% cheaper per 1M input tokens, $0.10 vs $0.14), GLM-5.3-Flash (7% more per 1M input tokens, $0.15 vs $0.14), GPT-4.1 nano (29% cheaper per 1M input tokens, $0.10 vs $0.14) and Claude Haiku 5.5 (29% cheaper per 1M input tokens, $0.10 vs $0.14).
Sources
- Xiaomi MiMo model updates · Xiaomi · official · verified October 13, 2026
- MiMo-V2.6-Flash model weights · Xiaomi · official · verified October 13, 2026
- Xiaomi MiMo API pay-as-you-go pricing · Xiaomi · official · verified October 13, 2026
- Arena leaderboard dataset (lmarena-ai/leaderboard-dataset) · Arena · independent · verified October 12, 2026 · CC-BY-4.0
Cite this page
Van Data Team. "MiMo-V2.6-Flash Benchmarks, Pricing and Specs." AI Model Benchmark Dataset 2026-10-13. https://vandatateam.com/ai-model-benchmarks/mimo-v2-6-flash
Reuse the data: JSON · CSV · or explore every model in the AI model benchmark comparison.
Production evaluation
Deciding whether MiMo-V2.6-Flash fits your workload?
Public benchmarks narrow the shortlist. We test the finalists on your own tasks, data and cost limits, then build the routing and review controls to run the winner in production.
- Evaluation cases and acceptance thresholds tied to real work
- Model routing, fallbacks and cost controls