Benchmarks

Mistral: Mistral Small 3.2 24B

mistralai/mistral-small-3.2-24b-instruct

Mistral Small 3.2 24B is a 24B open-weight model, ranking #209 of 235 on the TryAii Score. It's served by 3 independent hosts from $0.075/$0.2 per million input/output tokens — about a third of what models at its level usually charge. It's reasonably quick at roughly 34-58 tokens/sec.

Prompt $/1M
$0.075
Completion $/1M
$0.200
Context
131,072 tok
Best provider
104 tok/s · Mistral

Specs

Model id
mistralai/mistral-small-3.2-24b-instruct
Display name
Mistral: Mistral Small 3.2 24B
Modality
text+image->text
Tokenizer
Mistral
Instruct type
Context length
131,072
Max completion
16,384
Prompt $/1M
$0.075
Completion $/1M
$0.200
Free tier
no

Capabilities

  • Function callingyes
  • JSON modeno
  • System promptno
  • Visionno
  • Moderatedno

Benchmark scores

Each axis is one benchmark, normalized to the best model in the field.

No benchmark data for this model.

Speed by provider

Providertok/s
Mistralfastest104
Parasailfastest42
DeepInfra39
Venicefastest18
mistralaifastest