Laguna XS 2.1 vs Mercury 2.5 vs Trinity Large Thinking
Too close to call on our weighted score (Mercury 2.5 71, Laguna XS 2.1 68, Trinity Large Thinking 55). The right pick depends on what you value most.
PoolsideLaguna XS 2.1
68/100- ECI—
- Price$0.06 / $0.12
- Context262K
InceptionMercury 2.5
71/100- ECI—
- Price$0.04 / $0.15
- Context260K
Arcee AITrinity Large Thinking
55/100- ECI—
- Price$0.25 / $0.80
- Context524K
Too close to call
It is close. Our weighted score puts them within 3 points (Mercury 2.5 71/100, Laguna XS 2.1 68/100, Trinity Large Thinking 55/100), so choose by what matters most for your work: Mercury 2.5 on price and Trinity Large Thinking for long inputs. 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 priceMercury 2.5Mercury 2.5 $0.068 · Laguna XS 2.1 $0.075 · 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 · Mercury 2.5 260,000 tokens
- Widest inputsSame inputsLaguna XS 2.1: Text · Mercury 2.5: Text · Trinity Large Thinking: Text
- Self-hostingLaguna XS 2.1 and Trinity Large ThinkingPublishes downloadable weights (OpenMDW-1.1)
| Measure | Weight | Laguna XS 2.1 | Mercury 2.5 | Trinity Large Thinking |
|---|---|---|---|---|
| Price | 50% | 100 | 100 | 69 |
| Inputs & features | 30% | 35 | 45 | 35 |
| Context window | 20% | 37 | 36 | 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 | Mercury 2.5Inception | Trinity Large ThinkingArcee AI |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.06 | $0.04 (best) | $0.25 |
| Output | $0.12 (best) | $0.15 | $0.80 |
| Cached input | — | $0.004 (best) | $0.06 |
| Blended (3:1) | $0.075 | $0.068 (best) | $0.388 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 1 providers | Official Inception API | Official Arcee API |
| Limits | |||
| Context window | 262,144 tokens | 260,000 tokens | 524,288 tokens (best) |
| Max output | 32,768 tokens | 65,536 tokens | 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 | Yeslow · medium · high | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | Yes | No |
| Availability | |||
| Weights | Open | Proprietary | OpenOpenMDW-1.1 |
| API model ID | poolside/laguna-xs-2.1 | mercury-2.5 | trinity-large-thinking |
| API providers | 4 | 1 | 6 (best) |
| Released | Jul 2, 2026 | Sep 8, 2026 | Apr 1, 2026 |
| Knowledge cutoff | — | Nov 1, 2025 | — |
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
- Mercury 2.5$0.70
- Trinity Large Thinking$4.10
Which should you choose?
Which is better: Laguna XS 2.1, Mercury 2.5 or Trinity Large Thinking?
It is close. Our weighted score puts them within 3 points (Mercury 2.5 71/100, Laguna XS 2.1 68/100, Trinity Large Thinking 55/100), so choose by what matters most for your work: Mercury 2.5 on price and Trinity Large Thinking for long inputs. 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, Mercury 2.5 or Trinity Large Thinking?
Mercury 2.5 is cheaper at $0.04 input / $0.15 output per million tokens (official Inception API price). Laguna XS 2.1 costs $0.06 input / $0.12 output per million tokens (median across 1 API provider; free on Poolside); 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 $0.068 per million tokens for Mercury 2.5 versus $0.075 for Laguna XS 2.1 (1.1× as much) and $0.388 for Trinity Large Thinking (5.7× 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, Mercury 2.5 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, Mercury 2.5 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 260,000 for Mercury 2.5. Maximum output per response: Laguna XS 2.1 up to 32,768, Mercury 2.5 up to 65,536, Trinity Large Thinking up to 262,144 tokens.
Which can read images, PDFs, audio or video?
Laguna XS 2.1 accepts text; Mercury 2.5 accepts text; Trinity Large Thinking accepts text. They handle the same number of input types.
Are any of these open source?
Laguna XS 2.1 and Trinity Large Thinking publishes its weights (OpenMDW-1.1) and can be self-hosted; Mercury 2.5 is proprietary.
Which is newer?
Mercury 2.5 is the newest, released Sep 8, 2026. Laguna XS 2.1 came out Jul 2, 2026; Trinity Large Thinking came out Apr 1, 2026. Knowledge cutoff: Mercury 2.5 Nov 1, 2025.
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.
