Laguna XS 2.1 vs Nemotron 3.5 Lightning 30B A3B vs Trinity Large Thinking
Nemotron 3.5 Lightning 30B A3B comes out ahead, 71 to 68 and 55 on our weighted score, though Laguna XS 2.1 is 14% cheaper per token.
PoolsideLaguna XS 2.1
68/100- ECI—
- Price$0.06 / $0.12
- Context262K
- Our pick
NVIDIANemotron 3.5 Lightning 30B A3B
71/100- ECI—
- Price$0.05 / $0.20
- Context262K
Arcee AITrinity Large Thinking
55/100- ECI—
- Price$0.25 / $0.80
- Context524K
Nemotron 3.5 Lightning 30B A3B is our pick
Nemotron 3.5 Lightning 30B A3B is the better all-round choice, scoring 71/100 against Laguna XS 2.1 (68) and Trinity Large Thinking (55). It leads on inputs & features. Trinity Large Thinking wins on context window. 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 priceLaguna XS 2.1Laguna XS 2.1 $0.075 · Nemotron 3.5 Lightning 30B A3B $0.087 · Trinity Large Thinking $0.388 per 1M tokens (3:1 blend)
- Longest contextTrinity Large ThinkingTrinity Large Thinking 524,288 · Laguna XS 2.1 262,144 · Nemotron 3.5 Lightning 30B A3B 262,144 tokens
- Widest inputsSame inputsLaguna XS 2.1: Text · Nemotron 3.5 Lightning 30B A3B: Text · Trinity Large Thinking: Text
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | Laguna XS 2.1 | Nemotron 3.5 Lightning 30B A3B | Trinity Large Thinking |
|---|---|---|---|---|
| Price | 50% | 100 | 100 | 69 |
| Inputs & features | 30% | 35 | 45 | 35 |
| Context window | 20% | 37 | 37 | 49 |
| Overall | 100% | 68/100 | 71/100 | 55/100 |
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 | Laguna XS 2.1Poolside | Nemotron 3.5 Lightning 30B A3BNVIDIA | Trinity Large ThinkingArcee AI |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.06 | $0.05 (best) | $0.25 |
| Output | $0.12 (best) | $0.20 | $0.80 |
| Cached input | — | — | $0.06 |
| Blended (3:1) | $0.075 (best) | $0.087 | $0.388 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 1 providers | Median of 9 providers | Official Arcee API |
| Limits | |||
| Context window | 262,144 tokens | 262,144 tokens | 524,288 tokens (best) |
| Max output | 32,768 tokens | 262,144 tokens (best) | 262,144 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | No | No |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | Yes | Yes | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | Yes | No |
| Availability | |||
| Weights | Open | Open | OpenOpenMDW-1.1 |
| API model ID | poolside/laguna-xs-2.1 | nvidia/nemotron-3.5-lightning-30b-a3b | trinity-large-thinking |
| API providers | 4 | 12 (best) | 6 |
| Released | Jul 2, 2026 | Aug 11, 2026 | Apr 1, 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.
- Laguna XS 2.1$0.84
- Nemotron 3.5 Lightning 30B A3B$0.90
- Trinity Large Thinking$4.10
Which should you choose?
Which is better: Laguna XS 2.1, Nemotron 3.5 Lightning 30B A3B or Trinity Large Thinking?
Nemotron 3.5 Lightning 30B A3B is the better all-round choice, scoring 71/100 against Laguna XS 2.1 (68) and Trinity Large Thinking (55). It leads on inputs & features. Trinity Large Thinking wins on context window. 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, Laguna XS 2.1, Nemotron 3.5 Lightning 30B A3B or Trinity Large Thinking?
Laguna XS 2.1 is cheaper at $0.06 input / $0.12 output per million tokens (median across 1 API provider; free on Poolside). Nemotron 3.5 Lightning 30B A3B costs $0.05 input / $0.20 output per million tokens (median across 9 API providers; free on Nvidia); Trinity Large Thinking costs $0.25 input / $0.80 output per million tokens (official Arcee API price). At a typical mix of three input tokens to one output token, that is $0.075 per million tokens for Laguna XS 2.1 versus $0.087 for Nemotron 3.5 Lightning 30B A3B (1.2× as much) and $0.388 for Trinity Large Thinking (5.2× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Laguna XS 2.1 has not been scored yet, Nemotron 3.5 Lightning 30B A3B has not been scored yet and Trinity Large Thinking has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Laguna XS 2.1, Nemotron 3.5 Lightning 30B A3B and Trinity Large Thinking 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?
Trinity Large Thinking has the largest context window at 524,288 tokens, against 262,144 for Laguna XS 2.1 and 262,144 for Nemotron 3.5 Lightning 30B A3B. Maximum output per response: Laguna XS 2.1 up to 32,768, Nemotron 3.5 Lightning 30B A3B up to 262,144, Trinity Large Thinking up to 262,144 tokens.
Which can read images, PDFs, audio or video?
Laguna XS 2.1 accepts text; Nemotron 3.5 Lightning 30B A3B accepts text; Trinity Large Thinking accepts text. They handle the same number of input types.
Are any of these open source?
Yes, all three publish their weights (OpenMDW-1.1), so you can self-host them.
Which is newer?
Nemotron 3.5 Lightning 30B A3B is the newest, released Aug 11, 2026. Laguna XS 2.1 came out Jul 2, 2026; Trinity Large Thinking came out Apr 1, 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.
