Benchmarks

Mistral: Pixtral Large 2502

mistralai/pixtral-large-2502

Pixtral Large 2502 is a Mistral model that isn't ranked on the TryAii Score yet — no benchmark results on file. It lists at $2/$6 per million input/output tokens with a 128K-token context. It's reasonably quick at about 48 tokens/sec.

Prompt $/1M
$2.000
Completion $/1M
$6.000
Context
128,000 tok
Best provider
48 tok/s · Amazon Bedrock

Specs

Model id
mistralai/pixtral-large-2502
Display name
Mistral: Pixtral Large 2502
Modality
text+image->text
Tokenizer
Mistral
Instruct type
—
Context length
128,000
Max completion
102,400
Prompt $/1M
$2.000
Completion $/1M
$6.000
Free tier
no

Capabilities

  • Function callingno
  • JSON modeno
  • System promptno
  • Visionyes
  • Moderatedyes

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
Amazon Bedrockfastest48