Side-by-side comparison · models
MiMo-V2.6-Pro vs MiMo V2 Flash (Thinking)
What we have checked about each, line by line. Every value shows where it came from and when we last confirmed it.
Models
MiMo-V2.6-Pro
MiMo-V2.6-Pro is the flagship foundation model developed by Xiaomi. Built at a scale of over 1T parameters, it is designed to push the ceiling of capability for the most demanding.
Models
MiMo V2 Flash (Thinking)
MiMo flash model for fast multimodal assistance and agent workflows.
Checked facts
Line by line
| Measure | MiMo-V2.6-Pro | MiMo V2 Flash (Thinking) |
|---|---|---|
| Input price | $0.435 per million tokens | Not checked yet |
| Output price | $0.870 per million tokens | Not checked yet |
| Price on deepinfra | $0.0032 per million cached input tokens | Not checked yet |
| Price on deepinfra | $0.387 per million input tokens | Not checked yet |
| Price on deepinfra | $0.783 per million output tokens | Not checked yet |
| Price on gmicloud | $0.0030 per million cached input tokens | Not checked yet |
| Price on gmicloud | $0.326 per million input tokens | Not checked yet |
| Price on gmicloud | $0.652 per million output tokens | Not checked yet |
| Price on novita | $0.0036 per million cached input tokens | Not checked yet |
| Price on novita | $0.435 per million input tokens | Not checked yet |
| Price on novita | $0.870 per million output tokens | Not checked yet |
| Price on streamlake | $0.0043 per million cached input tokens | Not checked yet |
| Price on streamlake | $0.522 per million input tokens | Not checked yet |
| Price on streamlake | $1.04 per million output tokens | Not checked yet |
| Price on xiaomi | $0.0036 per million cached input tokens | Not checked yet |
| Price on xiaomi | $0.435 per million input tokens | Not checked yet |
| Price on xiaomi | $0.870 per million output tokens | Not checked yet |
| Latest version | xiaomi/mimo-v2.6-pro-20260921 | Not checked yet |
| Time to first token (ms) | 2,900 | Not checked yet |
| Time to first token (ms) on deepinfra | 1,021 | Not checked yet |
| Time to first token (ms) on gmicloud | 3,857 | Not checked yet |
| Time to first token (ms) on novita | 3,688 | Not checked yet |
| Time to first token (ms) on streamlake | 2,454 | Not checked yet |
| Time to first token (ms) on xiaomi | 2,919 | Not checked yet |
| Output speed (tokens a second) | 63.8 | Not checked yet |
| Output speed (tokens a second) on deepinfra | 36 | Not checked yet |
| Output speed (tokens a second) on gmicloud | 27 | Not checked yet |
| Output speed (tokens a second) on novita | 32.5 | Not checked yet |
| Output speed (tokens a second) on streamlake | 39 | Not checked yet |
| Output speed (tokens a second) on xiaomi | 38 | Not checked yet |
| Tokens served on OpenRouter in a day | 128.8B (for 10 Nov 2026) | Not checked yet |
| Tool calls on OpenRouter in a day | 615.9K (for 10 Nov 2026) | Not checked yet |
| Artificial Analysis Intelligence Index | 29.9 | Not checked yet |
| LMArena text rating (Elo) | 1,492 | Not checked yet |
| LMArena web development rating (Elo) | 1,624 | Not checked yet |
| LMArena vision rating (Elo) | 1,266 | Not checked yet |
| Design Arena rating (Elo) | 1,336 | Not checked yet |
| Apex agents | 54.4% (for 21 Sept 2026) | Not checked yet |
| Proofbench | 70% (for 21 Sept 2026) | Not checked yet |
A line appears only when at least one record has a value we confirmed from a source. Values we have not confirmed are left out, never guessed. Records of different types share fewer lines.
Add a third
Compare with one more record
How this works
Share it, or build your own
This page works for any two or three records in the directory, of any type. The link stays the same whichever order you name them in, so you can share it as it is. Change the records in the address, for example /directories/vs/claude-code-vs-cursor, or start from our editorial comparisons.