Sarvam 105B vs Ministral 14B
Too close to call on our weighted score (Sarvam 105B 65, Ministral 14B 64). The right pick depends on what you value most.
Sarvam AI
Sarvam 105B
65/100- ECI—
- Price$0.047 / $0.186
- Context131K
Mistral AIMinistral 14B
64/100- ECI—
- Price$0.20 / $0.20
- Context262K
Add a model
Make it a three-way comparison.
Too close to call
It is close. Our weighted score puts them within 2 points (Sarvam 105B 65/100, Ministral 14B 64/100), so choose by what matters most for your work: Sarvam 105B on price and Ministral 14B 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 priceSarvam 105BSarvam 105B $0.082 · Ministral 14B $0.20 per 1M tokens (3:1 blend)
- Longest contextMinistral 14BMinistral 14B 262,144 · Sarvam 105B 131,072 tokens
- Widest inputsMinistral 14BSarvam 105B: Text · Ministral 14B: Text, Images
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | Sarvam 105B | Ministral 14B |
|---|---|---|---|
| Price | 50% | 100 | 83 |
| Inputs & features | 30% | 35 | 50 |
| Context window | 20% | 24 | 37 |
| Overall | 100% | 65/100 | 64/100 |
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 | Sarvam 105BSarvam AI | Ministral 14BMistral AI |
|---|---|---|
| Capability | ||
| Capabilities Index (ECI) | — | — |
| ECI rank | — | — |
| Price per million tokens | ||
| Input | $0.047 (best) | $0.20 |
| Output | $0.186 (best) | $0.20 |
| Cached input | — | — |
| Blended (3:1) | $0.082 (best) | $0.20 |
| Long-context rate | Same rate | Same rate |
| Price source | Median of 2 providers | Median of 1 providers |
| Limits | ||
| Context window | 131,072 tokens | 262,144 tokens (best) |
| Max output | 131,072 tokens | 262,144 tokens (best) |
| Inputs and features | ||
| Text | Yes | Yes |
| Images | No | Yes |
| PDFs | No | No |
| Audio | No | No |
| Video | No | No |
| Reasoning | Yes · low · medium · high | No |
| Tool calling | Yes | Yes |
| Structured output | No | No |
| Availability | ||
| Weights | Open | OpenApache-2.0 |
| API model ID | sarvam-105b | — |
| API providers | 3 (best) | 1 |
| Released | Sep 1, 2025 | Dec 2, 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.
- Sarvam 105B$0.842
- Ministral 14B$2.40
Which should you choose?
Which is better: Sarvam 105B or Ministral 14B?
It is close. Our weighted score puts them within 2 points (Sarvam 105B 65/100, Ministral 14B 64/100), so choose by what matters most for your work: Sarvam 105B on price and Ministral 14B 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, Sarvam 105B or Ministral 14B?
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).
Which scores higher on benchmarks?
There is no independent benchmark that covers both models yet. Sarvam 105B has not been scored yet and Ministral 14B has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Sarvam 105B and Ministral 14B yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Both 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. Maximum output per response: Sarvam 105B up to 131,072, Ministral 14B up to 262,144 tokens.
Which can read images, PDFs, audio or video?
Sarvam 105B accepts text; Ministral 14B accepts text and images. Ministral 14B handles the widest range of inputs.
Are any of these open source?
Yes, both publish their weights (Apache-2.0), so you can self-host them.
Which is newer?
Ministral 14B is the newest, released Dec 2, 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.
