Mistral Small 3.2 24B
text+image->text
Mistral's 24B small model — open-weights, fast, and strong on instruction following for its size.
Mistral Small 3.2 24B is a multimodal AI model from Mistral. It costs $0.075 per million input tokens and $0.200 per million output tokens (blended $0.112/M), with a 128K-token context window.
Profile inherited from upstream Mistral Small 3.2 ↗ — this is a hosted variant of the same open-weights model.
INPUT
$0.075/M
per million input tokens
OUTPUT
$0.200/M
per million output tokens
CONTEXT
128K
128,000 tokens
What it's good at
- Open weights (Apache 2.0)
- Single-GPU friendly
- 128K context
Typical use cases
- Self-hosted production chat
- Cheap European-hosted inference
Benchmarks
vs. best public score
Scores inherited from
Mistral Small 3.2 — this is a hosted variant of the same open-weights model, so the underlying benchmark scores are identical.
MMLU71%
Multitask academic knowledge across 57 subjects.
HumanEval68%
Python function synthesis from docstrings.
LMArena Elo1175 Elo
Crowd-sourced head-to-head preference Elo rating.
Hand-curated from each provider's published reports and public leaderboards. Methodology varies across sources — treat as directional rather than authoritative.
Frequently asked questions
How much does Mistral Small 3.2 24B cost?
Mistral Small 3.2 24B costs $0.075 per million input tokens and $0.200 per million output tokens, for a blended reference rate of $0.112 per million tokens.
What is Mistral Small 3.2 24B's context window?
Mistral Small 3.2 24B supports up to 128K tokens of context (128,000 tokens).
What is Mistral Small 3.2 24B best for?
Mistral Small 3.2 24B is well suited to Open weights (Apache 2.0), Single-GPU friendly and 128K context.
Who makes Mistral Small 3.2 24B?
Mistral Small 3.2 24B is developed and served by Mistral.
