One agent session
1M input tokens and 100K output tokens, no caching.
- Input1M x $0.14 = $0.14
- Output0.1M x $0.28 = $0.028
$0.168per session
Xiaomi MiMo - Open weights
MiMo-V2.6-Flash pricing and specs
MiMo-V2.6-Flash is an open-weights model from Xiaomi MiMo that costs $0.14 per 1M input tokens and $0.28 per 1M output tokens on the first-party API, with a 1M-token context window.
Last verified from mimo.mi.com. All sources
- Input / 1M
- $0.14
- Output / 1M
- $0.28
- Context
- 1M tokens
- Weights
- Open
Pricing per 1M tokens
| Item | Price / 1M tokens |
|---|---|
| Input | $0.14 |
| Output | $0.28 |
| Cache read | $0.0028 |
| Batch inputBatch requests | $0.07 |
| Batch outputBatch requests | $0.14 |
Note: Overseas USD prices (the China region is billed separately in RMB). Cache writes are listed as limited-time free, so cache write is not stated. Batch API also lists a cache-hit input price of $0.0014 per 1M (no schema field). The model page states context 1M tokens and max output 128K tokens; the deprecation page gives the exact default max_completion_tokens for mimo-v2.6-flash as 131072, recorded as max output. context window 1000000 follows the stated 1M (the gateway lists 1048576). Input: text, image, video, audio; output: text. In thinking mode temperature and top_p are fixed at 1.0 and 0.95. mimo-v2.5 requests auto-route here since 2026-10-14 and that id stops working 2026-10-21. Weights are the MiMo-V2.6-Flash-RL checkpoint (309B total / 15B active per the HF card). Gateway marks this model's pricing as varying by provider; the dataset records first-party prices.
Specs
- Context window
- 1,000,000 tokens
- Max output
- 131,072 tokens
- Release date
- Provider
- Xiaomi MiMo
- API model id
mimo-v2.6-flash- Vercel AI Gateway id
xiaomi/mimo-v2.6-flash- Weights
- Open weights
- License
- MIT (Hugging Face license tag: mit)
- Weights download
- huggingface.co
What MiMo-V2.6-Flash costs in practice
Worked from the standard list rates above, with the math shown so you can swap in your own token counts.
A chat app
10,000 requests a day at 2K input and 500 output tokens each.
- Input20M x $0.14 = $2.80
- Output5M x $0.28 = $1.40
$4.20per day
$126.00 per 30-day month
The same session at a 90% cache hit
90% of the input is read from the prompt cache. The one-time cache write premium is not included.
- Cached input0.9M x $0.0028 = $0.0025
- Uncached input0.1M x $0.14 = $0.014
- Output0.1M x $0.28 = $0.028
$0.0445per session
Compare with
| Model | Input / 1M | Output / 1M |
|---|---|---|
| MiMo-V2.6-Flash (this page) | $0.14 | $0.28 |
| Hy-MT2-PlusTencent | $0.074 | $0.295 |
| Hy-MT2-ProTencent | $0.074 | $0.295 |
| Step 3.5 FlashStepFun | $0.10 | $0.30 |
| Step 3.5 Flash 2603StepFun | $0.10 | $0.30 |
| MiMo-V2.6-ProXiaomi MiMo | $0.435 | $0.87 |
FAQ
How much does MiMo-V2.6-Flash cost per million tokens?
MiMo-V2.6-Flash costs $0.14 per 1M input tokens and $0.28 per 1M output tokens on Xiaomi MiMo's first-party API, per mimo.mi.com on October 17, 2026. Per 1M tokens, cache reads cost $0.0028, and the batch rate is $0.07 input and $0.14 output.
What is MiMo-V2.6-Flash's context window?
MiMo-V2.6-Flash has a 1,000,000-token context window and returns up to 131,072 output tokens per response.
Are MiMo-V2.6-Flash's weights open?
Yes. MiMo-V2.6-Flash's weights are published at https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL under the MIT (Hugging Face license tag: mit).
When was MiMo-V2.6-Flash released?
Xiaomi MiMo released MiMo-V2.6-Flash on September 22, 2026.
Sources
Last verified from mimo.mi.com.
Newsletter
Get model price changes as they ship
One email per week. New model releases, price cuts and what they mean for your bill.