Benchmarks

Mistral: Mistral Nemo

mistralai/mistral-nemo

A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese,...

Prompt $/1M
$0.019
Completion $/1M
$0.030
Context
131,072 tok
Best provider
34 tok/s · DeepInfra

Specs

Model id
mistralai/mistral-nemo
Display name
Mistral: Mistral Nemo
Modality
text->text
Tokenizer
Mistral
Instruct type
mistral
Context length
131,072
Max completion
16,384
Prompt $/1M
$0.019
Completion $/1M
$0.030
Free tier
no

Capabilities

  • Function callingno
  • JSON modeno
  • System promptyes
  • 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
DeepInfrafastest34
Mistral32
DekaLLM28
Novita22
Mistral: Mistral Nemo - Benchmarks, Pricing and Speed | TryAii