Skip to main content
TokenCost logoTokenCost

MiMo-V2.6-Pro

Last verified October 4, 2026 · Xiaomi pricing ↗

$0.435/1M input · $0.870/1M output · 1.0M context · Xiaomi

MiMo-V2.6-Pro costs $0.435 per 1M input tokens and $0.870 per 1M output tokens from Xiaomi, with a 1.0M-token context window. A typical chat reply (1,500 tokens in, 400 out) costs $0.0010, or $10.01 per 10,000 requests. On that workload it is cheaper than 126 of the 179 other buyable models tracked here.

Count Tokens

—
Tokens
—
Input Cost
—
Output Cost

Estimate Monthly Cost

Monthly Cost Estimator

Quick:
<$0.0001/mo

Pick a preset above or enter custom usage

What MiMo-V2.6-Pro Costs Per Request

At $0.435 per 1M input and $0.870 per 1M output tokens, before caching or batch discounts.

WorkloadInput / output tokensPer requestPer 10,000 requests
Chat reply1,500 / 400$0.0010$10.01
RAG answer over retrieved docs8,000 / 600$0.0040$40.02
Coding-agent step30,000 / 2,000$0.015$147.90

MiMo-V2.6-Pro vs Similarly Priced Models

Nearest buyable models by price, with the RAG answer above (8,000 in / 600 out) priced on each.

ModelInput /1MOutput /1MContextRAG answer
MiMo-V2.6-Pro Xiaomi$0.435$0.8701.0M$0.0040
MiMo-V2.5-Pro Xiaomi$0.435$0.8701.0M$0.0040
Inkling 2 Small Thinking Machines$0.300$1.00256K$0.0030
Qwen3-Next-80B-A3B-Thinking Alibaba$0.150$1.20262K$0.0019

Alternatives to MiMo-V2.6-Pro

Pricing Details

XiaomiOpen weights (MIT), 1.02T total / 42B active MoE. Same card as MiMo-V2.5-Pro: $0.435 input, $0.0036 cache hit, $0.87 output (CNY 3 / 0.025 / 6). Flat across the full 1M context, no long-context tier. Cache writes free for a limited time. UltraSpeed variant $4.35 / $0.036 / $8.70. Also on Novita, DeepInfra, PrimaLabs and GMICloud at the same price. Artificial Analysis Intelligence Index v4.3 (read 2026-10-04): 46.32, $206.66 to run the index, 143.7M output tokens, about 40 tok/s on Xiaomi's endpoint. Xiaomi-reported: DeepSWE v1.1 71.9, Terminal Bench 4.0 34.9, OSWorld-Verified 82.0.
Input / 1M tokens
$0.435
Output / 1M tokens
$0.87
Context Window
1.0M
Max Output
131K

Price History

No price change recorded since 2026-10-04, when this site started tracking this model; it launched on 2026-09-22.

Frequently Asked Questions

Common questions about MiMo-V2.6-Pro pricing and usage

How much does MiMo-V2.6-Pro cost?
MiMo-V2.6-Pro costs $0.435 per 1 million input tokens and $0.87 per 1 million output tokens. This pricing is set by Xiaomi.
What tokenizer does MiMo-V2.6-Pro use?
MiMo-V2.6-Pro uses the cl100k_base tokenizer. This tokenizer has a vocabulary of ~100,000 tokens and is widely used across many models.
What is MiMo-V2.6-Pro's context window?
MiMo-V2.6-Pro supports a context window of 1.0M tokens (1,048,576 tokens). The maximum output length is 131K tokens.
How does MiMo-V2.6-Pro compare to other models?
On an 8,000-token-in, 600-token-out RAG answer, MiMo-V2.6-Pro costs $0.0040 per request. The nearest-priced alternatives cost: MiMo-V2.5-Pro (Xiaomi) $0.0040, Inkling 2 Small (Thinking Machines) $0.0030, Qwen3-Next-80B-A3B-Thinking (Alibaba) $0.0019. The table above lists their full rates and context windows.
How do I count tokens for MiMo-V2.6-Pro?
Use the token counter at the top of this page or visit the homepage calculator. Paste your text and it will show the exact token count and cost for MiMo-V2.6-Pro using the cl100k_base tokenizer.

Read More About MiMo-V2.6-Pro