Ministral 14B vs Sarvam 105B vs Trinity Nano Preview
Ministral 14B comes out ahead, 45 to 31 and 25 on our weighted score, though Sarvam 105B is 2.4× cheaper per token.
- Our pick
Mistral AIMinistral 14B
45/100- ECI—
- Price$0.20 / $0.20
- Context262K
Sarvam AI
Sarvam 105B
31/100- ECI—
- Price$0.047 / $0.186
- Context131K
Arcee AITrinity Nano Preview
25/100- ECI—
- Price—
- Context131K
Ministral 14B is our pick
Ministral 14B is the better all-round choice, scoring 45/100 against Sarvam 105B (31) 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 priceSarvam 105BSarvam 105B $0.082 · Ministral 14B $0.20 per 1M tokens (3:1 blend) · Trinity Nano Preview unpriced
- Longest contextMinistral 14BMinistral 14B 262,144 · Sarvam 105B 131,072 · Trinity Nano Preview 131,072 tokens
- Widest inputsMinistral 14BMinistral 14B: Text, Images · Sarvam 105B: Text · Trinity Nano Preview: Text
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | Ministral 14B | Sarvam 105B | Trinity Nano Preview |
|---|---|---|---|---|
| Inputs & features | 60% | 50 | 35 | 25 |
| Context window | 40% | 37 | 24 | 24 |
| Overall | 100% | 45/100 | 31/100 | 25/100 |
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 | Ministral 14BMistral AI | Sarvam 105BSarvam AI | Trinity Nano PreviewArcee AI |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.20 | $0.047 (best) | — |
| Output | $0.20 | $0.186 (best) | — |
| Cached input | — | — | — |
| Blended (3:1) | $0.20 | $0.082 (best) | — |
| Long-context rate | Same rate | Same rate | — |
| Price source | Median of 1 providers | Median of 2 providers | — |
| Limits | |||
| Context window | 262,144 tokens (best) | 131,072 tokens | 131,072 tokens |
| Max output | 262,144 tokens (best) | 131,072 tokens | 131,072 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | No | No |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | No | Yes · low · medium · high | No |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | OpenApache-2.0 | Open | OpenOpenMDW-1.1 |
| API model ID | — | sarvam-105b | — |
| API providers | 1 | 3 (best) | — |
| Released | Dec 2, 2025 | Sep 1, 2025 | Dec 1, 2025 |
| 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.
- Ministral 14B$2.40
- Sarvam 105B$0.842
- Trinity Nano Preview—
Which should you choose?
Which is better: Ministral 14B, Sarvam 105B or Trinity Nano Preview?
Ministral 14B is the better all-round choice, scoring 45/100 against Sarvam 105B (31) 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, Ministral 14B, Sarvam 105B or Trinity Nano Preview?
Sarvam 105B is cheaper at $0.047 input / $0.186 output per million tokens (median across 2 API providers). Ministral 14B costs $0.20 input / $0.20 output per million tokens (median across 1 API provider). At a typical mix of three input tokens to one output token, that is $0.082 per million tokens for Sarvam 105B versus $0.20 for Ministral 14B (2.4× 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. Ministral 14B has not been scored yet, Sarvam 105B has not been scored yet and Trinity Nano Preview has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Ministral 14B, Sarvam 105B and Trinity Nano Preview 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?
Ministral 14B has the largest context window at 262,144 tokens, against 131,072 for Sarvam 105B and 131,072 for Trinity Nano Preview. Maximum output per response: Ministral 14B up to 262,144, Sarvam 105B up to 131,072, Trinity Nano Preview up to 131,072 tokens.
Which can read images, PDFs, audio or video?
Ministral 14B accepts text and images; Sarvam 105B accepts text; Trinity Nano Preview accepts text. Ministral 14B handles the widest range of inputs.
Are any of these open source?
Yes, all three publish their weights (Apache-2.0 and OpenMDW-1.1), so you can self-host them.
Which is newer?
Ministral 14B is the newest, released Dec 2, 2025. Trinity Nano Preview came out Dec 1, 2025; Sarvam 105B came out Sep 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.
