Trinity Nano Preview vs Ministral 14B vs Nova 2 Lite
Nova 2 Lite comes out ahead, 72 to 45 and 25 on our weighted score, though Ministral 14B is 4.7× cheaper per token.
Arcee AITrinity Nano Preview
25/100- ECI—
- Price—
- Context131K
Mistral AIMinistral 14B
45/100- ECI—
- Price$0.20 / $0.20
- Context262K
- Our pick
AmazonNova 2 Lite
72/100- ECI—
- Price$0.33 / $2.75
- Context1M
Nova 2 Lite is our pick
Nova 2 Lite is the better all-round choice, scoring 72/100 against Ministral 14B (45) and Trinity Nano Preview (25). It leads on inputs & features and context window. The score weighs inputs & features 60%, context window 40%. 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 priceMinistral 14BMinistral 14B $0.20 · Nova 2 Lite $0.935 per 1M tokens (3:1 blend) · Trinity Nano Preview unpriced
- Longest contextNova 2 LiteNova 2 Lite 1,000,000 · Ministral 14B 262,144 · Trinity Nano Preview 131,072 tokens
- Widest inputsNova 2 LiteTrinity Nano Preview: Text · Ministral 14B: Text, Images · Nova 2 Lite: Text, Images, PDFs, Video
- Self-hostingTrinity Nano Preview and Ministral 14BPublishes downloadable weights (OpenMDW-1.1 and Apache-2.0)
| Measure | Weight | Trinity Nano Preview | Ministral 14B | Nova 2 Lite |
|---|---|---|---|---|
| Inputs & features | 60% | 25 | 50 | 80 |
| Context window | 40% | 24 | 37 | 60 |
| Overall | 100% | 25/100 | 45/100 | 72/100 |
Left out because at least one model lacks the data: capability and price. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | Trinity Nano PreviewArcee AI | Ministral 14BMistral AI | Nova 2 LiteAmazon |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | — | $0.20 (best) | $0.33 |
| Output | — | $0.20 (best) | $2.75 |
| Cached input | — | — | $0.083 |
| Blended (3:1) | — | $0.20 (best) | $0.935 |
| Long-context rate | — | Same rate | Same rate |
| Price source | — | Median of 1 providers | Official Amazon Bedrock API |
| Limits | |||
| Context window | 131,072 tokens | 262,144 tokens | 1,000,000 tokens (best) |
| Max output | 131,072 tokens | 262,144 tokens (best) | 65,536 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | Yes |
| PDFs | No | No | Yes |
| Audio | No | No | No |
| Video | No | No | Yes |
| Reasoning | No | No | Yeslow · medium · high |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | OpenOpenMDW-1.1 | OpenApache-2.0 | Proprietary |
| API model ID | — | — | amazon.nova-2-lite-v1:0 |
| API providers | — | 1 | 2 (best) |
| Released | Dec 1, 2025 | Dec 2, 2025 | Dec 2, 2025 |
| Knowledge cutoff | — | — | Oct 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 Nano Preview—
- Ministral 14B$2.40
- Nova 2 Lite$8.80
Which should you choose?
Which is better: Trinity Nano Preview, Ministral 14B or Nova 2 Lite?
Nova 2 Lite is the better all-round choice, scoring 72/100 against Ministral 14B (45) and Trinity Nano Preview (25). It leads on inputs & features and context window. The score weighs inputs & features 60%, context window 40%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
Which is cheaper, Trinity Nano Preview, Ministral 14B or Nova 2 Lite?
Ministral 14B is cheaper at $0.20 input / $0.20 output per million tokens (median across 1 API provider). Nova 2 Lite costs $0.33 input / $2.75 output per million tokens (official Amazon Bedrock API price). At a typical mix of three input tokens to one output token, that is $0.20 per million tokens for Ministral 14B versus $0.935 for Nova 2 Lite (4.7× as much). Trinity Nano Preview has no published per-token price.
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Trinity Nano Preview has not been scored yet, Ministral 14B has not been scored yet and Nova 2 Lite has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Trinity Nano Preview, Ministral 14B and Nova 2 Lite 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?
Nova 2 Lite has the largest context window at 1,000,000 tokens, against 262,144 for Ministral 14B and 131,072 for Trinity Nano Preview. Maximum output per response: Trinity Nano Preview up to 131,072, Ministral 14B up to 262,144, Nova 2 Lite up to 65,536 tokens.
Which can read images, PDFs, audio or video?
Trinity Nano Preview accepts text; Ministral 14B accepts text and images; Nova 2 Lite accepts text, images, PDFs and video. Nova 2 Lite handles the widest range of inputs.
Are any of these open source?
Trinity Nano Preview and Ministral 14B publishes its weights (OpenMDW-1.1 and Apache-2.0) and can be self-hosted; Nova 2 Lite is proprietary.
Which is newer?
Ministral 14B is the newest, released Dec 2, 2025. Nova 2 Lite came out Dec 2, 2025; Trinity Nano Preview came out Dec 1, 2025. Knowledge cutoff: Nova 2 Lite Oct 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.
