LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

MiMo-V2.6-Flash

xiaomi·xiaomi/mimo-v2.6-flash·GA·Open weights·mimo series·NEW
MiMo Flash model for multimodal coding agents and long-context automation

Specs & pricing

Input / output per 1M tokens
Official price·Xiaomi
$0.14 / $0.28
Blended $0.18 · Cache read $0.0028
Lowest paid·VultrCloud
$0.10 / $0.25
Blended $0.14 · 2× spread
2 more $0 channels
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
⚠ Providers report capability flags inconsistently
Modalities
TextImageAudioVideo
Weights
Hugging Face

MiMo-V2.6-Flash by xiaomi is offered by 35 providers on this page. Public prices are shown for 30 of them. Its official list price is $0.14 per 1M input tokens and $0.28 per 1M output tokens. The lowest paid channel is Vultr at $0.10 / $0.25 per 1M, about 1.3× below the list price. It also has 2 free ($0) channels and 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 26.7 on the Intelligence Index, with 45.7 for Strategy & Ops, its strongest domain. Against its lowest blended price of $0.138 per 1M, that is roughly 194 index points per dollar, which is the value ratio the leaderboards rank on. Median output speed is 38 tokens per second, with 3.26s to the first token. Running one task of the Artificial Analysis suite costs about $0.1285, 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 200,000 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. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use.

Quality & performanceArtificial Analysis · Intelligence Index v5

Intelligence26.7
Value194
Engineering31
Finance & Accounting36.9
Legal33.8
Healthcare & Medical35.1
Strategy & Ops45.7
Economics32.2
Output speed38 tok/s
TTFT3.26 s
Cost per task$0.13
Value formulaIQ 26.7 ÷ min blended $0.138 = 194

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

Available at 35 providers30 with public prices · 2 free · 3 subscription-covered

  • ProviderInput / Output
  • Xiaomi Token Plan (Singapore)Gateway
    Subscription
    Cache read $0Context 1,048,576Output limit 131,072
  • AMDCloud
    MiMo-V2.6-Flash
    Free
    Cache read $0Context 1,048,576Output limit 131,072
  • Xiaomi Token Plan (China)Gateway
    Subscription
    Cache read $0Context 1,048,576Output limit 131,072
  • OpenCodeGateway
    mimo-v2.6-flash-free
    Free
    Cache read $0Context 200,000 ⚠Output limit 32,000
  • Xiaomi Token Plan (Europe)Gateway
    Subscription
    Cache read $0Context 1,048,576Output limit 131,072
  • VultrCloud
    mimo-v2.6-flash-rl
    $0.10 / $0.25
    Context 1,048,576Output limit 131,072
  • Kilo GatewayGateway
    $0.10 / $0.28
    Cache read $0.0028Context 1,048,576Output limit 131,072
  • Pareto InferenceGateway
    $0.13 / $0.25
    Cache read $0.0025Context 1,048,576Output limit 131,072
  • DevPass (LLM Gateway)Gateway
    $0.14 / $0.27
    Cache read $0.0036Context 1,048,576Output limit 131,072
  • LLM GatewayGateway
    $0.14 / $0.27
    Cache read $0.0036Context 1,048,576Output limit 131,072
  • XiaomiOfficialFirst-party
    $0.14 / $0.28
    Cache read $0.0028Context 1,048,576Output limit 131,072
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
Xiaomi Token Plan (Singapore)GatewaySubscription$0—1,048,576131,072
AMD
MiMo-V2.6-Flash
CloudFree$0—1,048,576131,072
Xiaomi Token Plan (China)GatewaySubscription$0—1,048,576131,072
OpenCode
mimo-v2.6-flash-free
GatewayFree$0—200,000 ⚠32,000
Xiaomi Token Plan (Europe)GatewaySubscription$0—1,048,576131,072
Vultr
mimo-v2.6-flash-rl
Cloud$0.10$0.25——1,048,576131,072
Kilo GatewayGateway$0.10$0.28$0.0028—1,048,576131,072
Pareto InferenceGateway$0.13$0.25$0.0025—1,048,576131,072
DevPass (LLM Gateway)Gateway$0.14$0.27$0.0036—1,048,576131,072
LLM GatewayGateway$0.14$0.27$0.0036—1,048,576131,072
XiaomiOfficialFirst-party$0.14$0.28$0.0028—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 = higheffort = minimaleffort = loweffort = mediumeffort = xhigheffort = max

Interleaved thinking (reasoning between tool calls) is declared by 12 of 35 providers.

5 / 35 providers expose no reasoning control (reasoning_options: []).

Your usage cost

Common scenarios
1Kilo Gateway$22.34
2Pareto Inference$22.98
3DevPass (LLM Gateway)$24.87
4LLM Gateway$24.87
5Requesty$25.52
6Xiaomi · Official$25.54

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

Switch to Kilo Gateway to save $3.20/mo (13%). The gap is small, so staying on the official channel is fine.
Note: this is a gateway; verify availability and rate limits yourself.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$0.28$02026-09-222026-11-02
2026-11-02Input list $0.14Output list $0.28Min blended $0.14

Benchmark16 items

NameConditionsScoreMetricSource
DeepSWEv1.167.9scoreSource ↗
ProgramBench—26scoreSource ↗
MiMo Code Bench—61.2scoreSource ↗
AutomationBenchv1.0.652.3scoreSource ↗
Toolathlon-Verified—73.6scoreSource ↗
Agents' Last Exam—27.6scoreSource ↗
Terminal-Benchv4.028.8scoreSource ↗
Terminal-Benchv2.187.6scoreSource ↗
OSWorld-Verified—80.8scoreSource ↗
JobBench—61.2scoreSource ↗
CyberGym—95.1scoreSource ↗
MiMo Cyber Bench—77.2scoreSource ↗
ExploitGym—6scoreSource ↗
ExploitBench—25.3scoreSource ↗
SEC-Bench Pro—47.5scoreSource ↗
MiMo VisualCoding—71.5scoreSource ↗

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

Artificial Analysis evaluations20 items

Humanity's Last Exam35.1%
HLE-Diamond13.7%
MMMU-Pro73.1%
CritPt12.0%
CritPt v2 Hard29.5%
SciCode51.3%
FrontierCode42.1%
FrontierCode 2.021.6%
Terminal-Bench 4.022.7%
Terminal-Bench-Science4.3%
AutomationBench-AA64.0%
AA-Briefcase1487
GDPval-AA1614
GDP.pdf9.0%
AA-LCR74.3%
MLCR-AA11.7%
AA-Omniscience Index-10.8
AA-Omniscience Accuracy27.2%
AA-Omniscience Non-Hallucination47.8%
Code2Video-AA1052

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—Nemotron 3 Ultra 550B A55Bcheaper alternative$0 / $0Nemotron 3.5 Super VL 120B A12Bcheaper alternative$0 / $0reBeam 1.0 501B A23Bcheaper alternative$0 / $0Qwen3.7 Flashcheaper alternative$0.03 / $0.13MiMo-V2.5-TTS-VoiceDesignsame lab—
Data partly from models.dev (MIT) · Xiaomi official docs ↗