Xiaomi language model
MiMo V2.6 Pro UltraSpeed
The API-only UltraSpeed tier of MiMo V2.6 Pro, billed at ten times the Pro rate. Same 1M window and omnimodal input; Xiaomi publishes no separate UltraSpeed weights and sells it real-time only, with no batch tier.
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).
- Real-time only: Xiaomi lists no batch tier for UltraSpeed.
- 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 | $0.02 |
| Summarise a 100-page report 50,000 tokens in, 1,500 out, one request | $0.23 |
| 1,000 classification calls 500 tokens in, 20 out, per call | $2.35 |
| Coding-agent session 2M tokens in across ~60 turns, 60,000 out, no cache | $9.22 |
| Same session, cached 85% of input read from the prompt cache, the rest written to it | $1.89 |
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 $0.036/M
- Weights
- Closed
- Released
- September 2026
- Status
- Live
- Model ID
mimo-v2.6-pro-ultraspeed
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
When to pick it
Pick it if
- a person is waiting on the reply and latency is worth ten times Pro's price
- you want Pro-family omnimodal input on a 1M window
Skip it if
- you run background or batch work; standard Pro costs a tenth as much
05
Where it sits on price
Blended price $5.438/M at 3 input tokens per output token: 37 live language models cost less, 5 cost more.
- Gemini 3.1 Pro $4.5/M
- GPT 5.6 Terra $4.5/M
- MiMo V2.6 Pro UltraSpeed $5.438/M
- Kimi K3 $6/M
- Claude Opus 5.5 $8/M
06
Use MiMo V2.6 Pro UltraSpeed 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-pro-ultraspeed/model octohub:mimo-v2.6-pro-ultraspeed[model]
name = "octohub:mimo-v2.6-pro-ultraspeed"07
Compare MiMo V2.6 Pro UltraSpeed
08
Similar models
Nearest live models by listed input price.
View all models →09
MiMo V2.6 Pro UltraSpeed FAQ
How much does MiMo V2.6 Pro UltraSpeed cost?
MiMo V2.6 Pro UltraSpeed lists at $4.35/M input, $8.7/M output, $0.036/M cached input per 1M tokens. A typical coding-agent session (2M tokens in, 60,000 out) comes to $9.22, or $1.89 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 Pro UltraSpeed?
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 Pro UltraSpeed accept images?
Yes. It takes text, images, video and audio as input and returns text.
Is MiMo V2.6 Pro UltraSpeed open source?
No. MiMo V2.6 Pro UltraSpeed is a closed-weights model, available only through Xiaomi's API and hosted gateways such as OctoHub.
When was MiMo V2.6 Pro UltraSpeed released?
September 2026, by Xiaomi.
Is MiMo V2.6 Pro UltraSpeed free?
No. MiMo V2.6 Pro UltraSpeed bills per token at $4.35/M input, $8.7/M output, $0.036/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 Pro UltraSpeed in Octomind?
Run octomind login once, then octomind run -m octohub:mimo-v2.6-pro-ultraspeed. Inside a running session, /model octohub:mimo-v2.6-pro-ultraspeed switches to it without losing context.
Use MiMo V2.6 Pro UltraSpeed in Octomind
Choose a model when you start, then switch mid-session when the work changes.