LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

MiMo-V2.6-Pro-UltraSpeed

xiaomi·xiaomi/mimo-v2.6-pro-ultraspeed·GA·Open weights·mimo series·NEW
MiMo pro model for strong multimodal reasoning and agent execution

Specs & pricing

Input / output per 1M tokens
Official price·Xiaomi
$4.35 / $8.70
Blended $5.44 · Cache read $0.036
Lowest paid·XiaomiFirst-party
$4.35 / $8.70
Blended $5.44 · 1.2× spread
Context
1,048,576
Output limit
131,072
Knowledge cutoff
—
Released / updated
2026-09-21 / 2026-09-21
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ Temperature✓ Attachments
Modalities
TextImageAudioVideo
Weights
Hugging Face

MiMo-V2.6-Pro-UltraSpeed by xiaomi is offered by 11 providers on this page. Its official list price is $4.35 per 1M input tokens and $8.70 per 1M output tokens. No paid channel is priced below the official list price. Prices vary about 1.2× across the providers that host it.

The context window is 1,048,576 tokens at the reference host, but hosts report different limits, from 1,000,000 to 1,048,576, 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.

Available at 11 providers11 with public prices

  • ProviderInput / Output
  • XiaomiOfficialFirst-party
    $4.35 / $8.70
    Cache read $0.036Context 1,048,576Output limit 131,072
  • Kilo GatewayGateway
    $4.35 / $8.70
    Cache read $0.036Context 1,048,576Output limit 131,072
  • DevPass (LLM Gateway)Gateway
    $4.35 / $8.70
    Cache read $0.036Context 1,000,000 ⚠Output limit 131,072
  • OpenRouterGateway
    $4.35 / $8.70
    Cache read $0.036Context 1,048,576Output limit 131,072
  • LLM GatewayGateway
    $4.35 / $8.70
    Cache read $0.036Context 1,000,000 ⚠Output limit 131,072
  • Vercel AI GatewayCloud
    $4.35 / $8.70
    Cache read $0.036Context 1,048,576Output limit 131,072
  • EmpirioLabs AIGateway
    mimo-v2-6-pro-ultraspeed
    $4.35 / $8.70
    Cache read $4.35Context 1,048,576Output limit 131,072
  • NanoGPTGateway
    $4.35 / $8.70
    Cache read $0.036Context 1,048,576Output limit 131,072
  • CommandCodeGateway
    $4.35 / $8.70
    Cache read $0.036Context 1,048,576Output limit 131,072
  • AIHubMixGateway
    $4.80 / $9.60
    Cache read $0.038Context 1,048,576Output limit 131,072
  • above.devGateway
    $5.08 / $10.15
    Cache read $0.042Context 1,048,576Output limit 131,072
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
XiaomiOfficialFirst-party$4.35$8.70$0.036—1,048,576131,072
Kilo GatewayGateway$4.35$8.70$0.036—1,048,576131,072
DevPass (LLM Gateway)Gateway$4.35$8.70$0.036—1,000,000 ⚠131,072
OpenRouterGateway$4.35$8.70$0.036—1,048,576131,072
LLM GatewayGateway$4.35$8.70$0.036—1,000,000 ⚠131,072
Vercel AI GatewayCloud$4.35$8.70$0.036—1,048,576131,072
EmpirioLabs AI
mimo-v2-6-pro-ultraspeed
Gateway$4.35$8.70$4.35—1,048,576131,072
NanoGPTGateway$4.35$8.70$0.036$01,048,576131,072
CommandCodeGateway$4.35$8.70$0.036—1,048,576131,072
AIHubMixGateway$4.80$9.60$0.038—1,048,576131,072
above.devGateway$5.08$10.15$0.042—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 = loweffort = mediumeffort = minimal

Interleaved thinking (reasoning between tool calls) is declared by 3 of 11 providers.

1 / 11 providers expose no reasoning control (reasoning_options: []).

Your usage cost

Common scenarios
1Xiaomi · Official$787.32
2Kilo Gateway$787.32
3DevPass (LLM Gateway)$787.32
4OpenRouter$787.32
5LLM Gateway$787.32
6Vercel AI Gateway$787.32
The cheapest paid channel is official.

Price historyone sample accumulated per data sync

Input list $4.35Output list $8.70Min blended $5.44

Price history accumulates from each data sync; currently only 1 sample(s) (2026-09-22). Each future sync adds a point, and once accumulated a line is drawn here.

Related models

OrcaCyber MiMo V2.6 Flashsame series—MiMo V2.6 Flash Uncensoredsame series—MiMo V2.6 Flash Uncensored Thinkingsame series—GLM-5.3cheaper alternative$1.40 / $4.40GLM-5.3-Flashcheaper alternative$0.15 / $0.50DeepSeek V4.1 Flash 1017cheaper alternative$0.15 / $0.60GLM-5.2cheaper alternative$1.40 / $4.40MiMo-V2.6-Prosame lab$0.44 / $0.87
Data partly from models.dev (MIT) · Xiaomi official docs ↗