Xiaomi · Released Sep 22, 2026MiMo-V2.6-Flash
MiMo Flash model for multimodal coding agents and long-context automation.
- Capability
- —No ECI score yet
- Input
- $0.14per 1M tokens
- Output
- $0.28per 1M tokens
- Context
- 1.05M131K max output
What it costs
- Input
- $0.14per million tokens
- Output
- $0.28per million tokens
- Cached input
- $0.0028per million tokens
- Blended (3:1)
- $0.175cheaper than 79% of priced models
Typical monthly bills
| Monthly usage | Estimated cost |
|---|---|
| Side project2M input + 0.5M output tokens | $0.42 |
| Team assistant25M input + 5M output tokens | $4.90 |
| Production app250M input + 50M output tokens | $49.00 |
Official Xiaomi API price, as listed on models.dev.
Independent benchmarks
Epoch AI has not published a Capabilities Index score for MiMo-V2.6-Flash yet.
The details
- Lab
- Xiaomi
- Released
- Sep 22, 2026
- Context window
- 1,048,576 tokens
- Max output
- 131,072 tokens
- Inputs
- Text, Images, Audio, Video
- Output
- Text
- Reasoning
- Can be switched on or off
- Tool calling
- Yes
- Structured output
- No
- Weights
- Open weights
- API model ID
mimo-v2.6-flashon Xiaomi- Availability
- 18 API providerslisted on models.dev
What Xiaomi claims
Published by the lab at launch. Settings vary, so compare these only with care.
| Benchmark | Score | Setting | Source |
|---|---|---|---|
| DeepSWE v1.1 | 67.9 | — | Source |
| ProgramBench | 26 | — | Source |
| MiMo Code Bench | 61.2 | — | Source |
| AutomationBench v1.0.6 | 52.3 | — | Source |
| Toolathlon-Verified | 73.6 | — | Source |
| Agents' Last Exam | 27.6 | — | Source |
| Terminal-Bench v4.0 | 28.8 | — | Source |
| Terminal-Bench v2.1 | 87.6 | — | Source |
| OSWorld-Verified | 80.8 | — | Source |
| JobBench | 61.2 | — | Source |
| CyberGym | 95.1 | — | Source |
| MiMo Cyber Bench | 77.2 | — | Source |
More from Xiaomi
About MiMo-V2.6-Flash
How much does MiMo-V2.6-Flash cost?
MiMo-V2.6-Flash costs $0.14 input / $0.28 output per million tokens (official Xiaomi API price). Cached input is $0.0028 per million tokens. At a 3:1 input-to-output mix that is $0.175 per million tokens, cheaper than 79% of the 360 priced models we track.
What is the context window of MiMo-V2.6-Flash?
MiMo-V2.6-Flash accepts up to 1,048,576 tokens per request and can write up to 131,072 tokens in one response.
How good is MiMo-V2.6-Flash?
Epoch AI has not published a Capabilities Index score for MiMo-V2.6-Flash yet.
Is MiMo-V2.6-Flash open source?
Yes. Xiaomi publishes the weights, so it can be downloaded and self-hosted.
What inputs does MiMo-V2.6-Flash support?
MiMo-V2.6-Flash accepts text, images, audio and video and replies in text. It is a reasoning model, supports tool calling.
When was MiMo-V2.6-Flash released?
Xiaomi released MiMo-V2.6-Flash on Sep 22, 2026.
What are the best alternatives to MiMo-V2.6-Flash?
The closest current models from other labs on capability, price and release date are Viv Fast (Vivgrid, $0.13 / $0.40), Qwen3.8 Omni Flash (Alibaba (Qwen), $0.15 / $0.47), Seed Character (ByteDance Seed, $0.119 / $0.297) and Ling 3.1 Flash (inclusionAI, $0.075 / $0.22).