Gemini 2.5 Flash-Lite Preview 09-2025 vs Apertus 8B vs Ministral 14B
Gemini 2.5 Flash-Lite Preview 09-2025 comes out ahead, 81 to 63 and 54 on our weighted score, though Apertus 8B is 25% cheaper per token.
- Our pick
GoogleGemini 2.5 Flash-Lite Preview 09-2025
81/100- ECI—
- Price$0.095 / $0.38
- Context1.05M
Swiss AI
Apertus 8B
54/100- ECI—
- Price$0.10 / $0.20
- Context66K
Mistral AIMinistral 14B
63/100- ECI—
- Price$0.175 / $0.175
- Context262K
Gemini 2.5 Flash-Lite Preview 09-2025 is our pick
Gemini 2.5 Flash-Lite Preview 09-2025 is the better all-round choice, scoring 81/100 against Ministral 14B (63) and Apertus 8B (54). It leads on inputs & features and context window. Apertus 8B wins 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 priceApertus 8BApertus 8B $0.125 · Gemini 2.5 Flash-Lite Preview 09-2025 $0.166 · Ministral 14B $0.175 per 1M tokens (3:1 blend)
- Longest contextGemini 2.5 Flash-Lite Preview 09-2025Gemini 2.5 Flash-Lite Preview 09-2025 1,048,576 · Ministral 14B 262,144 · Apertus 8B 65,536 tokens
- Widest inputsGemini 2.5 Flash-Lite Preview 09-2025Gemini 2.5 Flash-Lite Preview 09-2025: Text, Images, PDFs, Audio, Video · Apertus 8B: Text · Ministral 14B: Text, Images
- Self-hostingApertus 8B and Ministral 14BPublishes downloadable weights (Apache-2.0)
| Measure | Weight | Gemini 2.5 Flash-Lite Preview 09-2025 | Apertus 8B | Ministral 14B |
|---|---|---|---|---|
| Price | 50% | 83 | 89 | 82 |
| Inputs & features | 30% | 90 | 25 | 50 |
| Context window | 20% | 61 | 12 | 37 |
| Overall | 100% | 81/100 | 54/100 | 63/100 |
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 | Gemini 2.5 Flash-Lite Preview 09-2025Google | Apertus 8BSwiss AI | Ministral 14BMistral AI |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.095 (best) | $0.10 | $0.175 |
| Output | $0.38 | $0.20 | $0.175 (best) |
| Cached input | — | — | — |
| Blended (3:1) | $0.166 | $0.125 (best) | $0.175 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 2 providers | Median of 1 providers | Median of 2 providers |
| Limits | |||
| Context window | 1,048,576 tokens (best) | 65,536 tokens | 262,144 tokens |
| Max output | 65,536 tokens | 8,192 tokens | 262,144 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | No | Yes |
| PDFs | Yes | No | No |
| Audio | Yes | No | No |
| Video | Yes | No | No |
| Reasoning | Yes | No | No |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | Proprietary | OpenApache-2.0 | OpenApache-2.0 |
| API model ID | — | — | — |
| API providers | 2 (best) | 1 | 2 (best) |
| Released | Sep 25, 2025 | Sep 2, 2025 | Dec 2, 2025 |
| Knowledge cutoff | Jan 2025 | Sep 2025 | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Gemini 2.5 Flash-Lite Preview 09-2025$1.71
- Apertus 8B$1.40
- Ministral 14B$2.10
Which should you choose?
Which is better: Gemini 2.5 Flash-Lite Preview 09-2025, Apertus 8B or Ministral 14B?
Gemini 2.5 Flash-Lite Preview 09-2025 is the better all-round choice, scoring 81/100 against Ministral 14B (63) and Apertus 8B (54). It leads on inputs & features and context window. Apertus 8B wins 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, Gemini 2.5 Flash-Lite Preview 09-2025, Apertus 8B or Ministral 14B?
Apertus 8B is cheaper at $0.10 input / $0.20 output per million tokens (median across 1 API provider). Gemini 2.5 Flash-Lite Preview 09-2025 costs $0.095 input / $0.38 output per million tokens (median across 2 API providers); Ministral 14B costs $0.175 input / $0.175 output per million tokens (median across 2 API providers). At a typical mix of three input tokens to one output token, that is $0.125 per million tokens for Apertus 8B versus $0.166 for Gemini 2.5 Flash-Lite Preview 09-2025 (1.3× as much) and $0.175 for Ministral 14B (1.4× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Gemini 2.5 Flash-Lite Preview 09-2025 has not been scored yet, Apertus 8B 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 Gemini 2.5 Flash-Lite Preview 09-2025, Apertus 8B and Ministral 14B 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?
Gemini 2.5 Flash-Lite Preview 09-2025 has the largest context window at 1,048,576 tokens, against 262,144 for Ministral 14B and 65,536 for Apertus 8B. Maximum output per response: Gemini 2.5 Flash-Lite Preview 09-2025 up to 65,536, Apertus 8B up to 8,192, Ministral 14B up to 262,144 tokens.
Which can read images, PDFs, audio or video?
Gemini 2.5 Flash-Lite Preview 09-2025 accepts text, images, PDFs, audio and video; Apertus 8B accepts text; Ministral 14B accepts text and images. Gemini 2.5 Flash-Lite Preview 09-2025 handles the widest range of inputs.
Are any of these open source?
Apertus 8B and Ministral 14B publishes its weights (Apache-2.0) and can be self-hosted; Gemini 2.5 Flash-Lite Preview 09-2025 is proprietary.
Which is newer?
Ministral 14B is the newest, released Dec 2, 2025. Gemini 2.5 Flash-Lite Preview 09-2025 came out Sep 25, 2025; Apertus 8B came out Sep 2, 2025. Knowledge cutoff: Gemini 2.5 Flash-Lite Preview 09-2025 Jan 2025, Apertus 8B Sep 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 Nov 2, 2026.
