Ling 3.1 Flash vs MiMo-V2.6-Pro-UltraSpeed vs Laguna S 2.1
Laguna S 2.1 comes out ahead, 69 to 65 and 44 on our weighted score, though Ling 3.1 Flash is 11% cheaper per token.
inclusionAILing 3.1 Flash
65/100- ECI—
- Price$0.075 / $0.22
- Context262K
XiaomiMiMo-V2.6-Pro-UltraSpeed
44/100- ECI—
- Price$4.35 / $8.70
- Context1.05M
- Our pick
PoolsideLaguna S 2.1
69/100- ECI—
- Price$0.10 / $0.20
- Context1.05M
Laguna S 2.1 is our pick
Laguna S 2.1 is the better all-round choice, scoring 69/100 against Ling 3.1 Flash (65) and MiMo-V2.6-Pro-UltraSpeed (44). Ling 3.1 Flash wins on price. MiMo-V2.6-Pro-UltraSpeed wins on inputs & features. 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 priceLing 3.1 FlashLing 3.1 Flash $0.111 · Laguna S 2.1 $0.125 · MiMo-V2.6-Pro-UltraSpeed $5.44 per 1M tokens (3:1 blend)
- Longest contextMiMo-V2.6-Pro-UltraSpeed and Laguna S 2.1MiMo-V2.6-Pro-UltraSpeed 1,048,576 · Laguna S 2.1 1,048,576 · Ling 3.1 Flash 262,144 tokens
- Widest inputsMiMo-V2.6-Pro-UltraSpeedLing 3.1 Flash: Text · MiMo-V2.6-Pro-UltraSpeed: Text, Images, Audio, Video · Laguna S 2.1: Text
- Self-hostingMiMo-V2.6-Pro-UltraSpeed and Laguna S 2.1Publishes downloadable weights
| Measure | Weight | Ling 3.1 Flash | MiMo-V2.6-Pro-UltraSpeed | Laguna S 2.1 |
|---|---|---|---|---|
| Price | 50% | 95 | 15 | 93 |
| Inputs & features | 30% | 35 | 80 | 35 |
| Context window | 20% | 37 | 61 | 61 |
| Overall | 100% | 65/100 | 44/100 | 69/100 |
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 | Ling 3.1 FlashinclusionAI | MiMo-V2.6-Pro-UltraSpeedXiaomi | Laguna S 2.1Poolside |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.075 (best) | $4.35 | $0.10 |
| Output | $0.22 | $8.70 | $0.20 (best) |
| Cached input | — | $0.036 | — |
| Blended (3:1) | $0.111 (best) | $5.44 | $0.125 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 1 providers | Official Xiaomi API | Median of 4 providers |
| Limits | |||
| Context window | 262,144 tokens | 1,048,576 tokens (best) | 1,048,576 tokens (best) |
| Max output | 32,768 tokens | 131,072 tokens (best) | 32,768 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | No |
| PDFs | No | No | No |
| Audio | No | Yes | No |
| Video | No | Yes | No |
| Reasoning | Yes | Yes | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | Proprietary | Open | Open |
| API model ID | — | mimo-v2.6-pro-ultraspeed | poolside/laguna-s-2.1 |
| API providers | 3 | 9 (best) | 6 |
| Released | Sep 29, 2026 | Sep 21, 2026 | Jul 21, 2026 |
| Knowledge cutoff | — | — | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Ling 3.1 Flash$1.19
- MiMo-V2.6-Pro-UltraSpeed$60.90
- Laguna S 2.1$1.40
Which should you choose?
Which is better: Ling 3.1 Flash, MiMo-V2.6-Pro-UltraSpeed or Laguna S 2.1?
Laguna S 2.1 is the better all-round choice, scoring 69/100 against Ling 3.1 Flash (65) and MiMo-V2.6-Pro-UltraSpeed (44). Ling 3.1 Flash wins on price. MiMo-V2.6-Pro-UltraSpeed wins on inputs & features. 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, Ling 3.1 Flash, MiMo-V2.6-Pro-UltraSpeed or Laguna S 2.1?
Ling 3.1 Flash is cheaper at $0.075 input / $0.22 output per million tokens (median across 1 API provider). Laguna S 2.1 costs $0.10 input / $0.20 output per million tokens (median across 4 API providers; free on Poolside); MiMo-V2.6-Pro-UltraSpeed costs $4.35 input / $8.70 output per million tokens (official Xiaomi API price). At a typical mix of three input tokens to one output token, that is $0.111 per million tokens for Ling 3.1 Flash versus $0.125 for Laguna S 2.1 (1.1× as much) and $5.44 for MiMo-V2.6-Pro-UltraSpeed (49× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Ling 3.1 Flash has not been scored yet, MiMo-V2.6-Pro-UltraSpeed has not been scored yet and Laguna S 2.1 has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Ling 3.1 Flash, MiMo-V2.6-Pro-UltraSpeed and Laguna S 2.1 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-Pro-UltraSpeed and Laguna S 2.1 have the largest context windows (1,048,576 and 1,048,576 tokens), against 262,144 for Ling 3.1 Flash. Maximum output per response: Ling 3.1 Flash up to 32,768, MiMo-V2.6-Pro-UltraSpeed up to 131,072, Laguna S 2.1 up to 32,768 tokens.
Which can read images, PDFs, audio or video?
Ling 3.1 Flash accepts text; MiMo-V2.6-Pro-UltraSpeed accepts text, images, audio and video; Laguna S 2.1 accepts text. MiMo-V2.6-Pro-UltraSpeed handles the widest range of inputs.
Are any of these open source?
MiMo-V2.6-Pro-UltraSpeed and Laguna S 2.1 publishes its weights and can be self-hosted; Ling 3.1 Flash is proprietary.
Which is newer?
Ling 3.1 Flash is the newest, released Sep 29, 2026. MiMo-V2.6-Pro-UltraSpeed came out Sep 21, 2026; Laguna S 2.1 came out Jul 21, 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 Oct 4, 2026.
