Benchmarks

Mistral: Devstral 2 2512

mistralai/devstral-2512

Devstral 2 2512 is Mistral's budget option at $0.4/$2 per million input/output tokens, with a 262K-token context. It sits mid-board on capability, at #166 of 262 on the TryAii Score. It's reasonably quick at about 94 tokens/sec.

Prompt $/1M
$0.400
Completion $/1M
$2.000
Context
262,144 tok
Best provider
94 tok/s · Mistral

Specs

Model id
mistralai/devstral-2512
Display name
Mistral: Devstral 2 2512
Modality
text+file->text
Tokenizer
Mistral
Instruct type
—
Context length
262,144
Max completion
209,715
Prompt $/1M
$0.400
Completion $/1M
$2.000
Free tier
no

Capabilities

  • Function callingno
  • 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
Mistralfastest94