LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

MiMo-V2.6-Pro

xiaomi·xiaomi/mimo-v2.6-pro·GA·Open weights·mimo series·NEW
Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution

Specs & pricing

Input / output per 1M tokens
Official price·Xiaomi
$0.44 / $0.87
Blended $0.54 · Cache read $0.0036
Lowest paid·NeuralwattGateway
$0.28 / $0.57
Blended $0.35 · 14.1× spread
Context
1,048,576
Output limit
131,072
Knowledge cutoff
—
Released / updated
2026-09-22 / 2026-09-22
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ Temperature✓ Attachments
Modalities
TextImageAudioVideo
Weights
Hugging Face

MiMo-V2.6-Pro by xiaomi is offered by 32 providers on this page. Public prices are shown for 29 of them. Its official list price is $0.435 per 1M input tokens and $0.87 per 1M output tokens. The lowest paid channel is Neuralwatt at $0.283 / $0.566 per 1M, about 1.5× below the list price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it. It also has 3 covered by a paid subscription; free tiers usually carry rate limits, and subscription-covered access bills $0 per token only after the subscription fee.

Artificial Analysis rates it 29.9 on the Intelligence Index, with 46.9 for Strategy & Ops, its strongest domain. Against its lowest blended price of $0.353 per 1M, that is roughly 85 index points per dollar, which is the value ratio the leaderboards rank on. Median output speed is 53 tokens per second, with 3.44s to the first token. Running one task of the Artificial Analysis suite costs about $0.2572, which reflects how many tokens its reasoning consumes rather than the unit price alone.

The context window is 1,048,576 tokens at the reference host, but hosts report different limits, from 1,000,000 to 1,050,000, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. Accepted input modalities are Text, Image, Audio, and Video. The weights are open, so it can also be self-hosted or served through a gateway of your choice.

Quality & performanceArtificial Analysis · Intelligence Index v5

Intelligence29.9
Value85
Engineering34.3
Finance & Accounting38.9
Legal35
Healthcare & Medical35.8
Strategy & Ops46.9
Economics36.1
Output speed53 tok/s
TTFT3.44 s
Cost per task$0.26
Value formulaIQ 29.9 ÷ min blended $0.353 = 85

Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.

Available at 32 providers29 with public prices · 3 subscription-covered

  • ProviderInput / Output
  • Xiaomi Token Plan (Singapore)Gateway
    Subscription
    Cache read $0Context 1,048,576Output limit 131,072
  • Xiaomi Token Plan (China)Gateway
    Subscription
    Cache read $0Context 1,048,576Output limit 131,072
  • Xiaomi Token Plan (Europe)Gateway
    Subscription
    Cache read $0Context 1,048,576Output limit 131,072
  • NeuralwattGateway
    mimo-v2.6-pro-flex
    $0.28 / $0.57
    Cache read $0.0023Context 1,048,560 ⚠Output limit 393,216
  • VultrCloud
    mimo-v2.6-pro-rl
    $0.40 / $0.80
    Context 1,048,576Output limit 131,072
  • Standard ComputeGateway
    $0.43 / $0.87
    Cache read $0.0036Context 1,048,576Output limit 50,000
  • Deep InfraCloud
    XiaomiMiMo/MiMo-V2.6-Pro
    $0.43 / $0.87
    Cache read $0.0036Context 1,048,576Output limit 131,072
  • RequestyGateway
    $0.43 / $0.87
    Cache read $0.0036Context 1,048,576Output limit 131,072
  • XiaomiOfficialFirst-party
    $0.44 / $0.87
    Cache read $0.0036Context 1,048,576Output limit 131,072
  • Kilo GatewayGateway
    $0.44 / $0.87
    Cache read $0.004Context 1,048,576Output limit 131,072
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
Xiaomi Token Plan (Singapore)GatewaySubscription$0—1,048,576131,072
Xiaomi Token Plan (China)GatewaySubscription$0—1,048,576131,072
Xiaomi Token Plan (Europe)GatewaySubscription$0—1,048,576131,072
Neuralwatt
mimo-v2.6-pro-flex
Gateway$0.28$0.57$0.0023—1,048,560 ⚠393,216
Vultr
mimo-v2.6-pro-rl
Cloud$0.40$0.80——1,048,576131,072
Standard ComputeGateway$0.43$0.87$0.0036—1,048,57650,000
Deep Infra
XiaomiMiMo/MiMo-V2.6-Pro
Cloud$0.43$0.87$0.0036—1,048,576131,072
RequestyGateway$0.43$0.87$0.0036—1,048,576131,072
XiaomiOfficialFirst-party$0.44$0.87$0.0036—1,048,576131,072
Kilo GatewayGateway$0.44$0.87$0.004—1,048,576131,072

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Reasoning control

Toggle (on / off)effort = noneeffort = highbudget_tokenseffort = loweffort = mediumeffort = maxeffort = minimaleffort = xhigh

Interleaved thinking (reasoning between tool calls) is declared by 12 of 32 providers.

2 / 32 providers expose no reasoning control (reasoning_options: []).

Your usage cost

Common scenarios
1Neuralwatt$51.18
2Standard Compute$78.33
3Deep Infra$78.33
4Requesty$78.33
5Xiaomi · Official$78.73
6DevPass (LLM Gateway)$78.73

3 more channels offer $0 (Xiaomi Token Plan (Singapore), Xiaomi Token Plan (China), Xiaomi Token Plan (Europe)); free tiers usually have rate limits and no SLA, excluded from ranking.

Switch to Neuralwatt to save $27.56/mo (35%)
Note: this is a gateway; verify availability and rate limits yourself.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$0.87$02026-09-222026-11-15
2026-11-15Input list $0.44Output list $0.87Min blended $0.35

Benchmark17 items

NameConditionsScoreMetricSource
DeepSWEvariant: MiMo-V2.6 Pro comparison column · v1.171.9scoreSource ↗
ProgramBenchvariant: MiMo-V2.6 Pro comparison column26.5scoreSource ↗
MiMo Code Benchvariant: MiMo-V2.6 Pro comparison column63.2scoreSource ↗
AutomationBenchvariant: MiMo-V2.6 Pro comparison column · v1.0.653.1scoreSource ↗
Toolathlon-Verifiedvariant: MiMo-V2.6 Pro comparison column76.9scoreSource ↗
GDPval-AAvariant: MiMo-V2.6 Pro comparison column · v2.11673EloSource ↗
Agents' Last Examvariant: MiMo-V2.6 Pro comparison column31.6scoreSource ↗
Terminal-Benchvariant: MiMo-V2.6 Pro comparison column · v4.034.9scoreSource ↗
Terminal-Benchvariant: MiMo-V2.6 Pro comparison column · v2.189.9scoreSource ↗
OSWorld-Verifiedvariant: MiMo-V2.6 Pro comparison column82scoreSource ↗
JobBenchvariant: MiMo-V2.6 Pro comparison column62scoreSource ↗
CyberGymvariant: MiMo-V2.6 Pro comparison column94scoreSource ↗
MiMo Cyber Benchvariant: MiMo-V2.6 Pro comparison column80.2scoreSource ↗
ExploitGymvariant: MiMo-V2.6 Pro comparison column17.8scoreSource ↗
ExploitBenchvariant: MiMo-V2.6 Pro comparison column47.9scoreSource ↗
SEC-Bench Provariant: MiMo-V2.6 Pro comparison column66.3scoreSource ↗
MiMo VisualCodingvariant: MiMo-V2.6 Pro comparison column72.3scoreSource ↗

The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.

Artificial Analysis evaluations23 items

Humanity's Last Exam49.4%
HLE-Diamond15.2%
CritPt26.6%
CritPt v2 Hard34.0%
SciCode60.9%
FrontierCode45.4%
FrontierCode 2.024.0%
Terminal-Bench 4.034.8%
Terminal-Bench-Science5.7%
AutomationBench-AA58.6%
AA-AnalystAgent37.5%
AA-Briefcase1512
GDPval-AA1692
GDP.pdf19.2%
AA-LCR86.3%
MLCR-AA12.8%
AA-Omniscience Index-4.5
AA-Omniscience Accuracy34.8%
AA-Omniscience Non-Hallucination39.8%
AA-3D983
Code2Video-AA1052
mka0.3732
vials-aa0.4348

Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and scale (percent correct, points or an index), so rows are not comparable with one another.

Related models

OrcaCyber MiMo V2.6 Flashsame series—MiMo V2.6 Flash Uncensoredsame series—MiMo V2.6 Flash Uncensored Thinkingsame series—GLM-5.3-Flashcheaper alternative$0.15 / $0.50DeepSeek V4.1 Flash 1017cheaper alternative$0.15 / $0.60Claude Haiku 5.5cheaper alternative$0.10 / $0.50GPT-6 Lunacheaper alternative$0.10 / $0.50MiMo-V2.6-Pro-UltraSpeedsame lab$4.35 / $8.70
Data partly from models.dev (MIT) · Xiaomi official docs ↗