TTPI$3.27+15.43%TCPI$3.130.00%Frontier Premium×1.1+0.64%Z.ai: GLM 5.2cached$0.103$0.121+17.20%Muse Glimmer 30Bout$1.10$1.20+9.10%Nemotron 3.5 Lightningin$0.080$0.070−12.50%Qwen3 VL 30B A3B Instructout$0.600$0.520−13.30%Nemotron 3 Nano 30B A3Bout$0.200$0.240+20.00%MoonshotAI: Kimi K3cached$0.303$0.300−0.90%Z.ai: GLM 5.3 Flashcached$0.014$0.018+28.60%Mistral Small 3.2 24Bout$0.200$0.250+25.00%MoonshotAI: Kimi K2.7 Codecached$0.150$0.180+20.00%Llama 4 Maverickout$0.600$0.652+8.80%Nemotron 3 Superout$0.400$0.450+12.50%Z.ai: GLM 5.3cached$0.203$0.260+28.20%

TTPI$3.27+15.43%TCPI$3.130.00%Frontier Premium×1.1+0.64%Z.ai: GLM 5.2cached$0.103$0.121+17.20%Muse Glimmer 30Bout$1.10$1.20+9.10%Nemotron 3.5 Lightningin$0.080$0.070−12.50%Qwen3 VL 30B A3B Instructout$0.600$0.520−13.30%Nemotron 3 Nano 30B A3Bout$0.200$0.240+20.00%MoonshotAI: Kimi K3cached$0.303$0.300−0.90%Z.ai: GLM 5.3 Flashcached$0.014$0.018+28.60%Mistral Small 3.2 24Bout$0.200$0.250+25.00%MoonshotAI: Kimi K2.7 Codecached$0.150$0.180+20.00%Llama 4 Maverickout$0.600$0.652+8.80%Nemotron 3 Superout$0.400$0.450+12.50%Z.ai: GLM 5.3cached$0.203$0.260+28.20%

BETA

← Back to prices

xiaomi

MultimodalAUTO PROFILELIVE PRICING

MiMo-V2.6-Pro

text+image+audio+video->text

MiMo-V2.6-Pro sits in the frontier tier, built for high-capability reasoning, tool use, and long-form output where capability outweighs cost. Available via xiaomi. 1,048,576-token context. Efficient pricing.

MiMo-V2.6-Pro is a multimodal AI model from xiaomi. It costs $0.435 per million input tokens and $0.870 per million output tokens (blended $0.566/M), with a 1,048,576-token context window.

Modalities text, vision, audio, videoPricing source ↗Compare with another model →Estimate monthly cost →

INPUT

$0.435/M

per million input tokens

OUTPUT

$0.870/M

per million output tokens

BLENDED 70/30

$0.566/M

unchanged since 3 May

default reference rate · how it is calculated →

CONTEXT

1,048,576

tokens

What it is good at

Strong general reasoning
Tool use & function calling
Long-form writing
Production-grade reliability
Multimodal: handles images alongside text

Typical use cases

Production assistants
Long-document analysis
Multi-step agent workflows
Engineering copilots

Benchmarks

No published benchmark scores tracked for this model yet. Frontier and reasoning models from major providers have scores; smaller models and inference-host variants typically inherit the underlying open-weights score.

More from xiaomi

MiMo-V2.6-Pro-UltraSpeed

text+image+audio+video->text · 1,048,576 ctx

in $4.350/Mout $8.700/M

MiMo-V2.6-Flash

text+image+audio+video->text · 1,048,576 ctx

in $0.140/Mout $0.280/M

text->text · 1,050,000 ctx

in $0.435/Mout $0.870/M

text+image+audio+video->text · 1,050,000 ctx

in $0.140/Mout $0.280/M

Frequently asked questions

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

MiMo-V2.6-Pro costs $0.435 per million input tokens and $0.870 per million output tokens, for a blended reference rate of $0.566 per million tokens.

What is MiMo-V2.6-Pro's context window?

MiMo-V2.6-Pro supports up to 1,048,576 tokens of context in a single request.

What is MiMo-V2.6-Pro best for?

MiMo-V2.6-Pro is well suited to Strong general reasoning, Tool use & function calling and Long-form writing.

Who makes MiMo-V2.6-Pro?

MiMo-V2.6-Pro is developed and served by xiaomi.

Terms used on this page

Full glossary →

Token Input tokens Output tokens Price per million tokens Context window Prompt caching Batch API Blended cost