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
24
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.

33 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
Boundless
mimo-v2.6-flash
1,048,576131,072$0.14 / $0.28YesYes—
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
1,048,576131,072$0.12 / $0.25YesYes—
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$0.10 / $0.28YesYesYes
View
LLM Gateway
deepinfra/mimo-v2.6-flash
1,048,57665,536$0.14 / $0.28YesYesYes
View
LLM Gateway
consensusprotocol/mimo-v2.6-flash
1,048,576131,072$0.12 / $0.25YesYesYes
View
LLM Gateway
xiaomi/mimo-v2.6-flash
1,000,000131,072$0.14 / $0.28YesYesNo
View
NaN
mimo-v2.6-flash
1,048,576131,072$0.00 / $0.00YesYes—
View
NanoGPT
xiaomi/mimo-v2.6-flash
1,048,576131,072$0.14 / $0.28YesYesYes
View
Novita AI
xiaomimimo/mimo-v2.6-flash
1,048,576131,072$0.14 / $0.28YesYesYes
View
OpenCode
mimo-v2.6-flash-free
200,00032,000$0.00 / $0.00YesYes—
View
OpenCode Go
mimo-v2.6-flash
1,048,576131,072$0.14 / $0.28YesYes—
View
Darkbloomvia OpenRouter
xiaomi/mimo-v2.6-flash
fp4
1,048,576131,072$0.10 / $0.28YesYesYes
View
DeepInfravia OpenRouter
xiaomi/mimo-v2.6-flash
fp8
1,048,576943,718$0.14 / $0.28YesYesYes
View
GMICloudvia OpenRouter
xiaomi/mimo-v2.6-flash
bf16
1,050,000945,000$0.14 / $0.28YesYesYes
View
Io Netvia OpenRouter
xiaomi/mimo-v2.6-flash
fp8
1,048,320131,072$0.26 / $0.41YesYesYes
View
Makoravia OpenRouter
xiaomi/mimo-v2.6-flash
fp8
1,048,576131,072$0.13 / $0.28YesYesYes
View
Novitavia OpenRouter
xiaomi/mimo-v2.6-flash
fp8
1,048,576131,072$0.14 / $0.28YesYesNo
View
Venicevia OpenRouter
xiaomi/mimo-v2.6-flash
fp8
1,000,000131,072$0.175 / $0.35YesYesYes
View
Xiaomivia OpenRouter
xiaomi/mimo-v2.6-flash
fp8
1,048,576131,072$0.14 / $0.28YesYesYes
View
Requesty
mimo-v2.6-flash
1,048,576131,072$0.14 / $0.28YesYesYes
View
Tempr Gateway
xiaomi-mimo/mimo-v2.6-flash
1,048,576131,072$0.14 / $0.28YesYes—
View
Venice AI
xiaomi-mimo-v2-6-flash
1,000,000131,072$0.175 / $0.35YesYesYes
View
Vercel AI Gateway
xiaomi/mimo-v2.6-flash
1,048,576131,072$0.14 / $0.28YesYes—
View
Vultr
mimo-v2.6-flash-rl
1,048,576131,072$0.10 / $0.25YesYes—
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 offers33Across 24 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 · 8 lowest-priced configurations
InputOutput
Darkbloomdarkbloom/fp4
$0.10$0.28
Makoramakora/fp8
$0.13$0.28
DeepInfradeepinfra/fp8
$0.14$0.28
GMICloudgmicloud/bf16
$0.14$0.28
Novitanovita/fp8
$0.14$0.28
Xiaomixiaomi/fp8
$0.14$0.28
Venicevenice/fp8
$0.175$0.35
Io Netio-net/fp8
$0.26$0.41
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
Darkbloomdarkbloom/fp4$0.10$0.28$0.05—
DeepInfradeepinfra/fp8$0.14$0.28$0.0028—
GMICloudgmicloud/bf16$0.14$0.28$0.003—
Io Netio-net/fp8$0.26$0.41$0.025—
Makoramakora/fp8$0.13$0.28$0.002—
Novitanovita/fp8$0.14$0.28$0.0028—
Venicevenice/fp8$0.175$0.35$0.00375—
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 · 6 endpoints
P50P75P90P99
Darkbloomdarkbloom/fp4
1,712–21,522.36 ms
DeepInfradeepinfra/fp8
950–10,536.31 ms
GMICloudgmicloud/bf16
5,224–62,067 ms
Io Netio-net/fp8
727–3,731.68 ms
Makoramakora/fp8
527–11,521.43 ms
Novitanovita/fp8
4,263.5–41,164.4 ms
All latency percentiles 8 endpoints
EndpointP50P75P90P99
Darkbloomdarkbloom/fp41,712 ms5,418 ms10,972.8 ms21,522.36 ms
DeepInfradeepinfra/fp8950 ms2,178.25 ms3,243.1 ms10,536.31 ms
GMICloudgmicloud/bf165,224 ms7,785.75 ms9,895.5 ms62,067 ms
Io Netio-net/fp8727 ms991.5 ms1,594.8 ms3,731.68 ms
Makoramakora/fp8527 ms905 ms1,766 ms11,521.43 ms
Novitanovita/fp84,263.5 ms7,686 ms12,273.7 ms41,164.4 ms
Venicevenice/fp81,139.5 ms2,048.75 ms4,179 ms16,631.25 ms
Xiaomixiaomi/fp85,136.5 ms10,095.25 ms22,576.5 ms86,642.26 ms

Output throughput · tokens per second

Throughput distributionRolling 30-minute snapshot · 6 endpoints
P50P75P90P99
Darkbloomdarkbloom/fp4
17–26.68 t/s
DeepInfradeepinfra/fp8
37–90.16 t/s
GMICloudgmicloud/bf16
26–89 t/s
Io Netio-net/fp8
137–689.92 t/s
Makoramakora/fp8
156–676.8 t/s
Novitanovita/fp8
30–103.09 t/s
All throughput percentiles 8 endpoints
EndpointP50P75P90P99
Darkbloomdarkbloom/fp417 t/s19.25 t/s23 t/s26.68 t/s
DeepInfradeepinfra/fp837 t/s57 t/s66.8 t/s90.16 t/s
GMICloudgmicloud/bf1626 t/s34 t/s50 t/s89 t/s
Io Netio-net/fp8137 t/s231 t/s371.1 t/s689.92 t/s
Makoramakora/fp8156 t/s243 t/s363 t/s676.8 t/s
Novitanovita/fp830 t/s42 t/s62 t/s103.09 t/s
Venicevenice/fp825 t/s39 t/s60 t/s108.25 t/s
Xiaomixiaomi/fp828 t/s40 t/s58 t/s101 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 · 8 endpoints
Endpoint5 minutes30 minutes24 hours
Darkbloomdarkbloom/fp4
DeepInfradeepinfra/fp8
GMICloudgmicloud/bf16
Io Netio-net/fp8
Makoramakora/fp8
Novitanovita/fp8
Venicevenice/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
xiaomi/mimo-v2.6-flashObserved
Benchmark profileArtificial Analysis · shared source scale from 0 to 40
Intelligence37.9

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

Detailed evaluations

Evaluation scoresAccuracy or item F1 · higher is better
gpqa diamondXiaomi: MiMo-V2.6-Flash
75.084%
tau bench verified airlineXiaomi: MiMo-V2.6-Flash
79.667%
EvaluationConfigurationSourceResultsDetails
Composite indicesMiMo-V2.6-Flashxiaomi/mimo-v2.6-flash-20260921Artificial AnalysisIntelligence 37.9 · Coding — · Agentic —
Details
gpqa diamondXiaomi: MiMo-V2.6-Flashxiaomi/mimo-v2.6-flash-20260921OpenRouter75.084%
Details
tau bench verified airlineXiaomi: MiMo-V2.6-Flashxiaomi/mimo-v2.6-flash-20260921OpenRouter79.667%
Details

Sources: Artificial Analysis, Design Arena and OpenRouter. Evaluation configurations and scales differ; results are not interchangeable. Updated Oct 15, 2026.

Apps & session costs

Compare observed median session costs for applications using this model, grouped by conversation length.

30-day sample · through Oct 11, 2026
ApplicationModel routeTurnsMedian cost / sessionDetails
Claude Codexiaomi/mimo-v2.6-flash-2026092110–49 turns
$0.035972
Details
Kilo Codexiaomi/mimo-v2.6-flash-2026092110–49 turns
$0.036211
Details
Kilo Codexiaomi/mimo-v2.6-flash-2026092150+ turns
$0.183805
Details
Claude Codexiaomi/mimo-v2.6-flash-2026092150+ turns
$0.188719
Details
Claude Codexiaomi/mimo-v2.6-flash-202609211 turn
$0.002356
Details
Kilo Codexiaomi/mimo-v2.6-flash-202609212–9 turns
$0.011461
Details
Hermes Agentxiaomi/mimo-v2.6-flash-2026092110–49 turns
$0.029569
Details
Hermes Agentxiaomi/mimo-v2.6-flash-202609212–9 turns
$0.003583
Details
Claude Codexiaomi/mimo-v2.6-flash-202609212–9 turns
$0.007352
Details
Hermes Agentxiaomi/mimo-v2.6-flash-202609211 turn
$0.001079
Details
Hermes Agentxiaomi/mimo-v2.6-flash-2026092150+ turns
$0.178262
Details

Source: OpenRouter, as of Oct 13, 2026. Published under CC BY 4.0. These are observed costs per session, not token prices or a forecast for your workload. Apps are compared separately.

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 usage31,374,207,169,415 reported tokens · 23 days with observations
Jul 17, 2026Oct 14, 2026
Daily observations · 23 days
Date (UTC)Reported tokensReported routes
Oct 14, 20261,531,870,757,0211
Oct 13, 20261,659,004,761,7431
Oct 12, 20261,599,516,527,7501
Oct 11, 20261,441,967,357,9441
Oct 10, 20261,716,490,188,6481
Oct 9, 20261,761,276,599,5641
Oct 8, 20261,750,823,318,7801
Oct 7, 20261,681,413,844,0191
Oct 6, 20261,586,449,582,3841
Oct 5, 20261,518,957,374,3331
Oct 4, 20261,319,163,685,9111
Oct 3, 20261,313,166,812,9741
Oct 2, 20261,336,416,469,9171
Oct 1, 20261,340,271,290,7001
Sep 30, 20261,460,529,646,9331
Sep 29, 20261,428,245,402,6821
Sep 28, 20261,427,697,417,2921
Sep 27, 20261,228,958,683,0031
Sep 26, 20261,159,762,918,2021
Sep 25, 20261,291,458,541,7571
Sep 24, 20261,105,679,845,7861
Sep 23, 2026566,971,371,5371
Sep 22, 2026148,114,770,5351

Source: OpenRouter (openrouter.ai/rankings), as of Oct 15, 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
1,050,000
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
  • logprobs
  • max_tokens
  • min_p
  • presence_penalty
  • reasoning
  • repetition_penalty
  • response_format
  • seed
  • stop
  • structured_outputs
  • temperature
  • tool_choice
  • tools
  • top_k
  • top_logprobs
  • 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 33 cataloged offers across 24 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