Trinity Large Thinking vs Mistral Small 4 vs Mercury Edit 2
Mistral Small 4 comes out ahead, 64 to 55 and 35 on our weighted score, and it is the cheaper option too.
Arcee AITrinity Large Thinking
55/100- ECI—
- Price$0.25 / $0.80
- Context524K
- Our pick
Mistral AIMistral Small 4
64/100- ECI—
- Price$0.15 / $0.60
- Context256K
InceptionMercury Edit 2
35/100- ECI—
- Price$0.25 / $0.75
- Context32K
Mistral Small 4 is our pick
Mistral Small 4 is the better all-round choice, scoring 64/100 against Trinity Large Thinking (55) and Mercury Edit 2 (35). It leads on price and 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 priceMistral Small 4Mistral Small 4 $0.263 · Mercury Edit 2 $0.375 · Trinity Large Thinking $0.388 per 1M tokens (3:1 blend)
- Longest contextTrinity Large ThinkingTrinity Large Thinking 524,288 · Mistral Small 4 256,000 · Mercury Edit 2 32,000 tokens
- Widest inputsMistral Small 4Trinity Large Thinking: Text · Mistral Small 4: Text, Images · Mercury Edit 2: Text
- Self-hostingTrinity Large Thinking and Mistral Small 4Publishes downloadable weights (OpenMDW-1.1)
| Measure | Weight | Trinity Large Thinking | Mistral Small 4 | Mercury Edit 2 |
|---|---|---|---|---|
| Price | 50% | 69 | 77 | 70 |
| Inputs & features | 30% | 35 | 60 | 0 |
| Context window | 20% | 49 | 36 | 0 |
| Overall | 100% | 55/100 | 64/100 | 35/100 |
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 | Trinity Large ThinkingArcee AI | Mistral Small 4Mistral AI | Mercury Edit 2Inception |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.25 | $0.15 (best) | $0.25 |
| Output | $0.80 | $0.60 (best) | $0.75 |
| Cached input | $0.06 | $0.015 (best) | $0.025 |
| Blended (3:1) | $0.388 | $0.263 (best) | $0.375 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Arcee API | Official Mistral API | Official Inception API |
| Limits | |||
| Context window | 524,288 tokens (best) | 256,000 tokens | 32,000 tokens |
| Max output | 262,144 tokens (best) | 256,000 tokens | 8,192 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | No |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | Yes | Yeshigh | No |
| Tool calling | Yes | Yes | No |
| Structured output | No | No | No |
| Availability | |||
| Weights | OpenOpenMDW-1.1 | Open | Proprietary |
| API model ID | trinity-large-thinking | mistral-small-2603 | mercury-edit-2 |
| API providers | 6 | 16 (best) | 1 |
| Released | Apr 1, 2026 | Mar 16, 2026 | Mar 30, 2026 |
| Knowledge cutoff | — | Jun 2025 | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Trinity Large Thinking$4.10
- Mistral Small 4$2.70
- Mercury Edit 2$4.00
Which should you choose?
Which is better: Trinity Large Thinking, Mistral Small 4 or Mercury Edit 2?
Mistral Small 4 is the better all-round choice, scoring 64/100 against Trinity Large Thinking (55) and Mercury Edit 2 (35). It leads on price and 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, Trinity Large Thinking, Mistral Small 4 or Mercury Edit 2?
Mistral Small 4 is cheaper at $0.15 input / $0.60 output per million tokens (official Mistral API price). Mercury Edit 2 costs $0.25 input / $0.75 output per million tokens (official Inception API price); 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 $0.263 per million tokens for Mistral Small 4 versus $0.375 for Mercury Edit 2 (1.4× as much) and $0.388 for Trinity Large Thinking (1.5× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Trinity Large Thinking has not been scored yet, Mistral Small 4 has not been scored yet and Mercury Edit 2 has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Trinity Large Thinking, Mistral Small 4 and Mercury Edit 2 yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Mercury Edit 2 does not support tool calling, which most coding agents need.
Which has the bigger context window?
Trinity Large Thinking has the largest context window at 524,288 tokens, against 256,000 for Mistral Small 4 and 32,000 for Mercury Edit 2. Maximum output per response: Trinity Large Thinking up to 262,144, Mistral Small 4 up to 256,000, Mercury Edit 2 up to 8,192 tokens.
Which can read images, PDFs, audio or video?
Trinity Large Thinking accepts text; Mistral Small 4 accepts text and images; Mercury Edit 2 accepts text. Mistral Small 4 handles the widest range of inputs.
Are any of these open source?
Trinity Large Thinking and Mistral Small 4 publishes its weights (OpenMDW-1.1) and can be self-hosted; Mercury Edit 2 is proprietary.
Which is newer?
Trinity Large Thinking is the newest, released Apr 1, 2026. Mercury Edit 2 came out Mar 30, 2026; Mistral Small 4 came out Mar 16, 2026. Knowledge cutoff: Mistral Small 4 Jun 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.
