Laguna XS 2.1 vs Ling 3.0 Flash Fin vs Mercury 2.5
Too close to call on our weighted score (Mercury 2.5 71, Laguna XS 2.1 68, Ling 3.0 Flash Fin 65). The right pick depends on what you value most.
PoolsideLaguna XS 2.1
68/100- ECI—
- Price$0.06 / $0.12
- Context262K
inclusionAILing 3.0 Flash Fin
65/100- ECI—
- Price$0.075 / $0.22
- Context262K
InceptionMercury 2.5
71/100- ECI—
- Price$0.04 / $0.15
- Context260K
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, Ling 3.0 Flash Fin 65/100), so choose by what matters most for your work: Mercury 2.5 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 priceMercury 2.5Mercury 2.5 $0.068 · Laguna XS 2.1 $0.075 · Ling 3.0 Flash Fin $0.111 per 1M tokens (3:1 blend)
- Longest contextAbout the sameLaguna XS 2.1 262,144 · Ling 3.0 Flash Fin 262,144 · Mercury 2.5 260,000 tokens
- Widest inputsSame inputsLaguna XS 2.1: Text · Ling 3.0 Flash Fin: Text · Mercury 2.5: Text
- Self-hostingLaguna XS 2.1Publishes downloadable weights
| Measure | Weight | Laguna XS 2.1 | Ling 3.0 Flash Fin | Mercury 2.5 |
|---|---|---|---|---|
| Price | 50% | 100 | 95 | 100 |
| Inputs & features | 30% | 35 | 35 | 45 |
| Context window | 20% | 37 | 37 | 36 |
| Overall | 100% | 68/100 | 65/100 | 71/100 |
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 | Ling 3.0 Flash FininclusionAI | Mercury 2.5Inception |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.06 | $0.075 | $0.04 (best) |
| Output | $0.12 (best) | $0.22 | $0.15 |
| Cached input | — | — | $0.004 |
| Blended (3:1) | $0.075 | $0.111 | $0.068 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 1 providers | Median of 1 providers | Official Inception API |
| Limits | |||
| Context window | 262,144 tokens (best) | 262,144 tokens (best) | 260,000 tokens |
| Max output | 32,768 tokens | 32,768 tokens | 65,536 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 | Yeslow · medium · high |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | No | Yes |
| Availability | |||
| Weights | Open | Proprietary | Proprietary |
| API model ID | poolside/laguna-xs-2.1 | — | mercury-2.5 |
| API providers | 4 (best) | 2 | 1 |
| Released | Jul 2, 2026 | Aug 27, 2026 | Sep 8, 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
- Ling 3.0 Flash Fin$1.19
- Mercury 2.5$0.70
Which should you choose?
Which is better: Laguna XS 2.1, Ling 3.0 Flash Fin or Mercury 2.5?
It is close. Our weighted score puts them within 3 points (Mercury 2.5 71/100, Laguna XS 2.1 68/100, Ling 3.0 Flash Fin 65/100), so choose by what matters most for your work: Mercury 2.5 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, Laguna XS 2.1, Ling 3.0 Flash Fin or Mercury 2.5?
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); Ling 3.0 Flash Fin costs $0.075 input / $0.22 output per million tokens (median across 1 API provider). 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 $0.111 for Ling 3.0 Flash Fin (1.6× 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, Ling 3.0 Flash Fin has not been scored yet and Mercury 2.5 has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Laguna XS 2.1, Ling 3.0 Flash Fin and Mercury 2.5 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?
Their context windows are effectively the same size: Laguna XS 2.1 262,144, Ling 3.0 Flash Fin 262,144 and Mercury 2.5 260,000 tokens. Maximum output per response: Laguna XS 2.1 up to 32,768, Ling 3.0 Flash Fin up to 32,768, Mercury 2.5 up to 65,536 tokens.
Which can read images, PDFs, audio or video?
Laguna XS 2.1 accepts text; Ling 3.0 Flash Fin accepts text; Mercury 2.5 accepts text. They handle the same number of input types.
Are any of these open source?
Laguna XS 2.1 publishes its weights and can be self-hosted; Ling 3.0 Flash Fin and Mercury 2.5 is proprietary.
Which is newer?
Mercury 2.5 is the newest, released Sep 8, 2026. Ling 3.0 Flash Fin came out Aug 27, 2026; Laguna XS 2.1 came out Jul 2, 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.
