Ministral 14B vs Voxtral Small 24B 2507

Ministral 14B is the better all-round choice, scoring 63/100 against Voxtral Small 24B 2507 (55). 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.

Ministral 14B and Voxtral Small 24B 2507 cost the same: $0.175 input / $0.175 output per million tokens.

There is no independent benchmark that covers both models yet. Ministral 14B has not been scored yet and Voxtral Small 24B 2507 has not been scored yet.

There are no published SWE-bench Verified results for Ministral 14B and Voxtral Small 24B 2507 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.

Ministral 14B has the largest context window at 262,144 tokens, against 32,768 for Voxtral Small 24B 2507. Maximum output per response: Ministral 14B up to 262,144, Voxtral Small 24B 2507 up to 32,768 tokens.

Ministral 14B accepts text and images; Voxtral Small 24B 2507 accepts text and audio. They handle the same number of input types.

Yes, both publish their weights (Apache-2.0 and Apache 2.0), so you can self-host them.

Ministral 14B is the newest, released Dec 2, 2025. Voxtral Small 24B 2507 came out Jul 15, 2025.

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.