MiMo-V2.6-Flash

MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi. Built on a Mixture-of-Experts architecture with 309B total parameters and 15B activated per token, it employs a hybrid attention mechanism for greater computational efficiency. The model features a 1M-token context window and native multimodal capabilities. Optimized for agentic workflows, it delivers strong performance across coding, visual, general, and research scenarios, excelling at complex, long-horizon tasks with robust generalization across a diverse range of agent harnesses.

xiaomi/mimo-v2.6-flash
Organization
Xiaomi
Family
mimo
Providers
17
Context
1,048,576
Output limit
131,072
Knowledge
—
Release
2026-09-22
Updated
2026-09-22
Weights
Open
Input
text, image, audio, video
Output
text
Capabilities
Tools, Reasoning, Temperature

Providers

Compare every cataloged offer for this model, including its provider, route, token limits, price, and capabilities.

18 offers · USD per million tokens
ProviderModel IDContextOutputInput / output · 1MReasoningToolsStructuredDetails
above.dev
mimo-v2.6-flash
1,048,576131,072$0.1692 / $0.3385YesYes—
View
AIHubMix
mimo-v2.6-flash
1,048,576131,072$0.155 / $0.31YesYes—
View
ClinePass
cline-pass/mimo-v2.6-flash
1,048,576131,072$0.14 / $0.28YesYes—
View
CrossModel
xiaomi/mimo-v2.6-flash
1,048,576131,072$0.16 / $0.32YesYes—
View
Deep Infra
XiaomiMiMo/MiMo-V2.6-Flash
1,048,576131,072$0.14 / $0.28YesYesYes
View
DevPass (LLM Gateway)
mimo-v2.6-flash
1,000,000131,072$0.14 / $0.28YesYes—
View
EmpirioLabs AI
mimo-v2-6-flash
1,000,000131,072$0.14 / $0.28YesYesYes
View
Kilo Gateway
xiaomi/mimo-v2.6-flash
1,048,576131,072$0.14 / $0.28YesYesYes
View
LLM Gateway
xiaomi/mimo-v2.6-flash
1,000,000131,072$0.14 / $0.28YesYesNo
View
NanoGPT
xiaomi/mimo-v2.6-flash
1,048,576131,072$0.14 / $0.28YesYesYes
View
OpenCode Go
mimo-v2.6-flash
1,048,576131,072$0.14 / $0.28YesYes—
View
OpenCode Zen
mimo-v2.6-flash-free
200,00032,000$0.00 / $0.00YesYes—
View
DeepInfravia OpenRouter
xiaomi/mimo-v2.6-flash
fp8
1,048,576943,718$0.14 / $0.28YesYesYes
View
Xiaomivia OpenRouter
xiaomi/mimo-v2.6-flash
fp8
1,048,576131,072$0.14 / $0.28YesYesYes
View
Vercel AI Gateway
xiaomi/mimo-v2.6-flash
1,048,576131,072$0.14 / $0.28YesYes—
View
Xiaomi Token Plan (China)
mimo-v2.6-flash
1,048,576131,072$0.00 / $0.00YesYes—
View
Xiaomi Token Plan (Europe)
mimo-v2.6-flash
1,048,576131,072$0.00 / $0.00YesYes—
View
Xiaomi Token Plan (Singapore)
mimo-v2.6-flash
1,048,576131,072$0.00 / $0.00YesYes—
View

Prices and limits apply to each offer. A dash means the value is not provided. OpenRouter offers show the hosting provider and routing channel separately.

Pricing

Compare token rates and cache charges across available routes and hosting configurations.

USD per million tokens
Input from$0.00Per 1M input tokens
Output from$0.00Per 1M output tokens
Available offers18Across 17 providers

Lowest listed input and output prices across the offers above; they may belong to different providers. These are base rates, before conditional pricing, discounts or additional fees.

Endpoint price comparisonLatest observed snapshot · 2 lowest-priced configurations
InputOutput
DeepInfradeepinfra/fp8
$0.14$0.28
Xiaomixiaomi/fp8
$0.14$0.28
xiaomi/mimo-v2.6-flashObserved
Input
$0.14
Output
$0.28
Cache read
$0.0028
Hosting prices through OpenRouter All endpoints and cache rates
EndpointInput / 1MOutput / 1MCache read / 1MCache write / 1M
DeepInfradeepinfra/fp8$0.14$0.28$0.0028—
Xiaomixiaomi/fp8$0.14$0.28$0.0028—

Each row is a hosting configuration. Open an offer in Providers for its full pricing conditions and additional fees. Endpoint observations may differ from the routing catalog's base price.

Performance

Review reported latency and output-throughput percentiles from the latest observed rolling window.

Latest 30-minute observation

Time to first token · milliseconds

Latency distributionRolling 30-minute snapshot · 2 endpoints
P50P75P90P99
DeepInfradeepinfra/fp8
9,016–130,183 ms
Xiaomixiaomi/fp8
3,666.5–50,883.44 ms
All latency percentiles 2 endpoints
EndpointP50P75P90P99
DeepInfradeepinfra/fp89,016 ms19,075 ms40,884 ms130,183 ms
Xiaomixiaomi/fp83,666.5 ms5,530.25 ms9,327.6 ms50,883.44 ms

Output throughput · tokens per second

Throughput distributionRolling 30-minute snapshot · 2 endpoints
P50P75P90P99
DeepInfradeepinfra/fp8
8–14 t/s
Xiaomixiaomi/fp8
41–117 t/s
All throughput percentiles 2 endpoints
EndpointP50P75P90P99
DeepInfradeepinfra/fp88 t/s9 t/s10 t/s14 t/s
Xiaomixiaomi/fp841 t/s59 t/s77 t/s117 t/s

Percentiles describe the observed request distribution. These are snapshots of a rolling window, not a historical time series.

Uptime

Compare successful request rates across the latest 5-minute, 30-minute, and 24-hour observations.

Successful requests by window
Availability by endpointCurrent overlapping windows · 2 endpoints
Endpoint5 minutes30 minutes24 hours
DeepInfradeepinfra/fp8
Xiaomixiaomi/fp8

Reported by OpenRouter at the time of collection; rate-limited requests are excluded. A dash means no measurement was reported. This is not a live availability check.

Benchmarks

Review attributed evaluation results on each source's original scale.

External evaluations

Sources: Artificial Analysis and Design Arena, via OpenRouter. Scores retain their original scales and are not Artificial Atlas ratings.

Detailed evaluations

Evaluation scoresAccuracy or item F1 · higher is better
gpqa diamondXiaomi: MiMo-V2.6-Flash
75%
tau bench verified airlineXiaomi: MiMo-V2.6-Flash
76.596%
EvaluationConfigurationSourceResultsDetails
gpqa diamondXiaomi: MiMo-V2.6-Flashxiaomi/mimo-v2.6-flash-20260921OpenRouter75%
Details
tau bench verified airlineXiaomi: MiMo-V2.6-Flashxiaomi/mimo-v2.6-flash-20260921OpenRouter76.596%
Details

Sources: Artificial Analysis, Design Arena and OpenRouter. Evaluation configurations and scales differ; results are not interchangeable. Updated Sep 24, 2026.

Activity

Daily prompt and completion tokens reported for this model's routes in OpenRouter's top 50. Missing days have no published value.

Last 90 complete UTC days
Daily token usage715,086,142,072 reported tokens · 2 days with observations
Jun 26, 2026Sep 23, 2026
Daily observations · 2 days
Date (UTC)Reported tokensReported routes
Sep 23, 2026566,971,371,5371
Sep 22, 2026148,114,770,5351

Source: OpenRouter (openrouter.ai/rankings), as of Sep 24, 2026. CC BY 4.0. Totals include only individually published routes. Tokenizers differ by provider; the aggregated “other” category is never assigned to a model.

Technical details & API

Explore specifications, supported parameters, reasoning controls, and API identifiers for each OpenRouter route.

Current route specifications
xiaomi/mimo-v2.6-flashObserved
Context
1,048,576
Maximum output
131,072
Tokenizer
Other
Input
text, image, video, audio
Output
text
Moderation
No
Added to OpenRouter
2026-09-21
Base URLhttps://openrouter.ai/api/v1
Model IDxiaomi/mimo-v2.6-flash
Version IDxiaomi/mimo-v2.6-flash-20260921
Weights IDXiaomiMiMo/MiMo-V2.6-Flash-RL

Reasoning

Required
No
Enabled by default
Not reported
Default effort
—
Supported efforts
—

Supported parameters

  • frequency_penalty
  • include_reasoning
  • logit_bias
  • max_tokens
  • min_p
  • presence_penalty
  • reasoning
  • repetition_penalty
  • response_format
  • seed
  • stop
  • structured_outputs
  • temperature
  • tool_choice
  • tools
  • top_k
  • top_p

Default parameters

top p
0.95
temperature
1
frequency penalty
0

Frequently asked questions

Answers based on the model metadata and serving offers currently in the catalog.

How much does MiMo-V2.6-Flash cost?

Listed rates start at $0.00 per million input tokens and $0.00 per million output tokens. Prices vary by provider and configuration; see Pricing for details.

Which providers offer MiMo-V2.6-Flash?

There are 18 cataloged offers across 17 providers. Compare model IDs, prices and limits in Providers.

What is the context window?

The cataloged model context is 1,048,576 tokens. Each serving endpoint may apply a different limit.

Does it support tools and structured output?

Tool calling: Yes. Structured output: Not reported. Support can vary by endpoint.

Resources

Catalog history · 2 recorded revisions

Metadata observations since this model was first cataloged. These are not model release versions.

  • · 837959ef9a30
  • · b12c674259ab