MiMo-V2.6-Flash vs solar-mini vs Solar Mini 4
MiMo-V2.6-Flash comes out ahead, 80 to 64 and 50 on our weighted score, though solar-mini is 14% cheaper per token.
- Our pick
XiaomiMiMo-V2.6-Flash
80/100- ECI—
- Price$0.14 / $0.28
- Context1.05M
Upstagesolar-mini
50/100- ECI—
- Price$0.15 / $0.15
- Context33K
- Upstage
Solar Mini 4
64/100- ECI—
- Price$0.10 / $0.40
- Context524K
MiMo-V2.6-Flash is our pick
MiMo-V2.6-Flash is the better all-round choice, scoring 80/100 against Solar Mini 4 (64) and solar-mini (50). It leads on inputs & features and context window. solar-mini wins on price. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
- CapabilityNot enough dataNo independent benchmark covers every model here yet
- Lowest pricesolar-minisolar-mini $0.15 · MiMo-V2.6-Flash $0.175 · Solar Mini 4 $0.175 per 1M tokens (3:1 blend)
- Longest contextMiMo-V2.6-FlashMiMo-V2.6-Flash 1,048,576 · Solar Mini 4 524,288 · solar-mini 32,768 tokens
- Widest inputsMiMo-V2.6-FlashMiMo-V2.6-Flash: Text, Images, Audio, Video · solar-mini: Text · Solar Mini 4: Text
- Self-hostingMiMo-V2.6-FlashPublishes downloadable weights
| Measure | Weight | MiMo-V2.6-Flash | solar-mini | Solar Mini 4 |
|---|---|---|---|---|
| Price | 50% | 82 | 85 | 82 |
| Inputs & features | 30% | 90 | 25 | 45 |
| Context window | 20% | 61 | 0 | 49 |
| Overall | 100% | 80/100 | 50/100 | 64/100 |
Left out because at least one model lacks the data: capability. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | MiMo-V2.6-FlashXiaomi | solar-miniUpstage | Solar Mini 4Upstage |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.14 | $0.15 | $0.10 (best) |
| Output | $0.28 | $0.15 (best) | $0.40 |
| Cached input | $0.0028 (best) | — | $0.01 |
| Blended (3:1) | $0.175 | $0.15 (best) | $0.175 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Xiaomi API | Official Upstage API | Official Upstage API |
| Limits | |||
| Context window | 1,048,576 tokens (best) | 32,768 tokens | 524,288 tokens |
| Max output | 131,072 tokens (best) | 4,096 tokens | 131,072 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | No | No |
| PDFs | No | No | No |
| Audio | Yes | No | No |
| Video | Yes | No | No |
| Reasoning | Yes | No | Yesminimal · low · medium · high · xhigh · max |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | No | Yes |
| Availability | |||
| Weights | Open | Proprietary | Proprietary |
| API model ID | mimo-v2.6-flash | solar-mini | solar-mini4 |
| API providers | 23 (best) | 1 | 4 |
| Released | Sep 22, 2026 | Jun 12, 2024 | Sep 22, 2026 |
| Knowledge cutoff | — | Sep 2024 | Feb 2026 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- MiMo-V2.6-Flash$1.96
- solar-mini$1.80
- Solar Mini 4$1.80
Which should you choose?
Which is better: MiMo-V2.6-Flash, solar-mini or Solar Mini 4?
MiMo-V2.6-Flash is the better all-round choice, scoring 80/100 against Solar Mini 4 (64) and solar-mini (50). It leads on inputs & features and context window. solar-mini wins on price. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
Which is cheaper, MiMo-V2.6-Flash, solar-mini or Solar Mini 4?
solar-mini is cheaper at $0.15 input / $0.15 output per million tokens (official Upstage API price). MiMo-V2.6-Flash costs $0.14 input / $0.28 output per million tokens (official Xiaomi API price); Solar Mini 4 costs $0.10 input / $0.40 output per million tokens (official Upstage API price). At a typical mix of three input tokens to one output token, that is $0.15 per million tokens for solar-mini versus $0.175 for MiMo-V2.6-Flash (1.2× as much) and $0.175 for Solar Mini 4 (1.2× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. MiMo-V2.6-Flash has not been scored yet, solar-mini has not been scored yet and Solar Mini 4 has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for MiMo-V2.6-Flash, solar-mini and Solar Mini 4 yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. All three support tool calling for agent workflows.
Which has the bigger context window?
MiMo-V2.6-Flash has the largest context window at 1,048,576 tokens, against 524,288 for Solar Mini 4 and 32,768 for solar-mini. Maximum output per response: MiMo-V2.6-Flash up to 131,072, solar-mini up to 4,096, Solar Mini 4 up to 131,072 tokens.
Which can read images, PDFs, audio or video?
MiMo-V2.6-Flash accepts text, images, audio and video; solar-mini accepts text; Solar Mini 4 accepts text. MiMo-V2.6-Flash handles the widest range of inputs.
Are any of these open source?
MiMo-V2.6-Flash publishes its weights and can be self-hosted; solar-mini and Solar Mini 4 is proprietary.
Which is newer?
MiMo-V2.6-Flash is the newest, released Sep 22, 2026. Solar Mini 4 came out Sep 22, 2026; solar-mini came out Jun 12, 2024. Knowledge cutoff: solar-mini Sep 2024, Solar Mini 4 Feb 2026.
How do you decide the winner?
Each model gets a 0–100 score on capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Nov 2, 2026.
