Xiaomi language model
MiMo V2.6 Flash
Xiaomi's open-weights omnimodal model, a 309B-total, 15B-active mixture-of-experts. It is the small sibling of MiMo V2.6 Pro and replaces MiMo V2.5, adding audio and video input on a 1M window.
01
Price
Input tokens
Output tokens
Cached input
Per 1M tokens. Octomind bills the listed provider price, with no markup, on every plan, including the free one (pay as you go from credits).
- Xiaomi lists a batch API tier at half the real-time rate.
- Cache writes are free for a limited time; Xiaomi gives no end date.
02
What real work costs
| Workload | Cost |
|---|---|
| One chat reply 3,000 tokens in, 500 out | $0.00056 |
| Summarise a 100-page report 50,000 tokens in, 1,500 out, one request | $0.0074 |
| 1,000 classification calls 500 tokens in, 20 out, per call | $0.08 |
| Coding-agent session 2M tokens in across ~60 turns, 60,000 out, no cache | $0.30 |
| Same session, cached 85% of input read from the prompt cache, the rest written to it | $0.06 |
At the listed rate. Token counts are typical sizes, not measurements.
03
Specs
- Provider
- Xiaomi
- Context window
- 1M tokens — ≈ 1,500 pages of prose or 100,000 lines of code
- Max output
- 128k tokens
- Input
- Text, Images, Video, Audio
- Output
- Text
- Structured output
- Yes — JSON schema
- Reasoning mode
- Yes
- Prompt caching
- Yes — cache hits at $0.003/M
- Weights
- Open — MIT
- Released
- September 2026
- Status
- Live
- Model ID
mimo-v2.6-flash
Integration notes
- Thinking is on by default and switched with thinking.type enabled or disabled; there is no effort ladder.
- With thinking on, temperature and top_p are fixed upstream at 1.0 and 0.95.
- Tool-call turns must send back their reasoning_content or the API returns 400; structured output is json_object only, not json_schema.
04
Benchmarks
As published by the maker; not measured by Octomind.
05
When to pick it
Pick it if
- you want the cheapest 1M-window model with image, video and audio input
- you run high-volume agent or coding loops where cached prefixes dominate the bill
- you want MIT-licensed weights you can self-host
Skip it if
- you need the strongest MiMo results on security and exploit benchmarks; Pro scores higher there
06
Where it sits on price
Blended price $0.175/M at 3 input tokens per output token: 3 live language models cost less, 39 cost more.
- Muse Spark 1.3 Contributor $0.125/M
- Mercury 3 $0.163/M
- MiMo V2.6 Flash $0.175/M
- Claude Haiku 5.5 $0.2/M
- Gemma 4 31B $0.2/M
07
Use MiMo V2.6 Flash in Octomind
One OctoHub login reaches every model in the catalog. Pick this one per run, per session, or as your default.
octomind login
octomind run -m octohub:mimo-v2.6-flash/model octohub:mimo-v2.6-flash[model]
name = "octohub:mimo-v2.6-flash"08
Compare MiMo V2.6 Flash
09
Similar models
Nearest live models by listed input price.
- GLM-5.3 Flash $0.15/M input
- MiniMax M3.1 Flash $0.15/M input
- Qwen3.8 Omni Flash $0.15/M input
- Claude Haiku 5.5 $0.1/M input
10
MiMo V2.6 Flash FAQ
How much does MiMo V2.6 Flash cost?
MiMo V2.6 Flash lists at $0.14/M input, $0.28/M output, $0.003/M cached input per 1M tokens. A typical coding-agent session (2M tokens in, 60,000 out) comes to $0.30, or $0.06 when 85% of the input is read from the prompt cache. Octomind bills the listed provider price, with no markup, on every plan, including the free one (pay as you go from credits).
What is the context window of MiMo V2.6 Flash?
1M tokens, ≈ 1,500 pages of prose or 100,000 lines of code. A single reply can run to 128k tokens.
Does MiMo V2.6 Flash accept images?
Yes. It takes text, images, video and audio as input and returns text.
Is MiMo V2.6 Flash open source?
Its weights are open under MIT, so it can also be self-hosted.
When was MiMo V2.6 Flash released?
September 2026, by Xiaomi.
Is MiMo V2.6 Flash free?
No. MiMo V2.6 Flash bills per token at $0.14/M input, $0.28/M output, $0.003/M cached input per 1M. Octomind's free plan reaches it pay as you go from credits, so you pay only for the tokens you use, at the provider price. Credits carry a 3% top-up fee.
How do I use MiMo V2.6 Flash in Octomind?
Run octomind login once, then octomind run -m octohub:mimo-v2.6-flash. Inside a running session, /model octohub:mimo-v2.6-flash switches to it without losing context.
Use MiMo V2.6 Flash in Octomind
Choose a model when you start, then switch mid-session when the work changes.