Llama-3.1-8B-Instruct vs Ministral 14B vs Ministral 8B Instruct
Ministral 14B comes out ahead, 64 to 57 and 56 on our weighted score, though Ministral 8B Instruct is 25% cheaper per token.
Meta
Llama-3.1-8B-Instruct
56/100- ECI116.6
- Price$0.152 / $0.167
- Context128K
- Our pick
Mistral AI
Ministral 14B
64/100- ECI—
- Price$0.20 / $0.20
- Context262K
Mistral AI
Ministral 8B Instruct
57/100- ECI—
- Price$0.15 / $0.15
- Context131K
Ministral 14B is our pick
Ministral 14B is the better all-round choice, scoring 64/100 against Ministral 8B Instruct (57) and Llama-3.1-8B-Instruct (56). It leads on inputs & features and 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 priceMinistral 8B InstructMinistral 8B Instruct $0.15 · Llama-3.1-8B-Instruct $0.156 · Ministral 14B $0.20 per 1M tokens (3:1 blend)
- Longest contextMinistral 14BMinistral 14B 262,144 · Ministral 8B Instruct 131,072 · Llama-3.1-8B-Instruct 128,000 tokens
- Widest inputsMinistral 14BLlama-3.1-8B-Instruct: Text · Ministral 14B: Text, Images · Ministral 8B Instruct: Text
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | Llama-3.1-8B-Instruct | Ministral 14B | Ministral 8B Instruct |
|---|---|---|---|---|
| Price | 50% | 88 | 83 | 89 |
| Inputs & features | 30% | 25 | 50 | 25 |
| Context window | 20% | 24 | 37 | 24 |
| Overall | 100% | 56/100 | 64/100 | 57/100 |
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 | |||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 116.6 | — | — |
| ECI rank | #145 of 148 | — | — |
| GPQA DiamondGraduate-level science questions | 27.0% | — | 27.2% (best) |
| OTIS Mock AIME 2024–2025Competition mathematics | 1.7% | — | — |
| Price per million tokens | |||
| Input | $0.152 | $0.20 | $0.15 (best) |
| Output | $0.167 | $0.20 | $0.15 (best) |
| Cached input | — | — | — |
| Blended (3:1) | $0.156 | $0.20 | $0.15 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 9 providers | Median of 1 providers | Median of 1 providers |
| Limits | |||
| Context window | 128,000 tokens | 262,144 tokens (best) | 131,072 tokens |
| Max output | 4,096 tokens | 262,144 tokens (best) | 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 | No | No | No |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | Open | OpenApache-2.0 | OpenMistral Research License |
| API model ID | — | — | — |
| API providers | 9 (best) | 1 | 1 |
| Released | Jul 23, 2024 | Dec 2, 2025 | Oct 16, 2024 |
| Knowledge cutoff | Dec 2023 | — | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
Llama-3.1-8B-Instruct$1.85
Ministral 14B$2.40
Ministral 8B Instruct$1.80
Which should you choose?
Which is better: Llama-3.1-8B-Instruct, Ministral 14B or Ministral 8B Instruct?
Ministral 14B is the better all-round choice, scoring 64/100 against Ministral 8B Instruct (57) and Llama-3.1-8B-Instruct (56). It leads on inputs & features and 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, Llama-3.1-8B-Instruct, Ministral 14B or Ministral 8B Instruct?
Ministral 8B Instruct is cheaper at $0.15 input / $0.15 output per million tokens (median across 1 API provider). Llama-3.1-8B-Instruct costs $0.152 input / $0.167 output per million tokens (median across 9 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 $0.15 per million tokens for Ministral 8B Instruct versus $0.156 for Llama-3.1-8B-Instruct (1× as much) and $0.20 for Ministral 14B (1.3× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Llama-3.1-8B-Instruct has an ECI of 116.6, Ministral 14B has not been scored yet and Ministral 8B Instruct has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Llama-3.1-8B-Instruct, Ministral 14B and Ministral 8B Instruct 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 Ministral 8B Instruct and 128,000 for Llama-3.1-8B-Instruct. Maximum output per response: Llama-3.1-8B-Instruct up to 4,096, Ministral 14B up to 262,144, Ministral 8B Instruct up to 8,192 tokens.
Which can read images, PDFs, audio or video?
Llama-3.1-8B-Instruct accepts text; Ministral 14B accepts text and images; Ministral 8B Instruct 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 Mistral Research License), so you can self-host them.
Which is newer?
Ministral 14B is the newest, released Dec 2, 2025. Ministral 8B Instruct came out Oct 16, 2024; Llama-3.1-8B-Instruct came out Jul 23, 2024. Knowledge cutoff: Llama-3.1-8B-Instruct Dec 2023.
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.