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.
| Workload | Input / output tokens | Per request | Per 10,000 requests |
|---|---|---|---|
| Chat reply | 1,500 / 400 | $0.0010 | $10.01 |
| RAG answer over retrieved docs | 8,000 / 600 | $0.0040 | $40.02 |
| Coding-agent step | 30,000 / 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.
| Model | Input /1M | Output /1M | Context | RAG answer |
|---|---|---|---|---|
| MiMo-V2.6-Pro Xiaomi | $0.435 | $0.870 | 1.0M | $0.0040 |
| MiMo-V2.5-Pro Xiaomi | $0.435 | $0.870 | 1.0M | $0.0040 |
| Inkling 2 Small Thinking Machines | $0.300 | $1.00 | 256K | $0.0030 |
| Qwen3-Next-80B-A3B-Thinking Alibaba | $0.150 | $1.20 | 262K | $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.