Benchmarks

Meta: Llama 3.1 70B Instruct

meta-llama/llama-3.1-70b-instruct

Llama 3.1 70B Instruct is a 70B open-weight model, ranking #202 of 235 on the TryAii Score. Its best showing is #4 on GSM8K. It's served by 3 independent hosts from $0.4/$0.4 per million input/output tokens — a little under the going rate for its score class.

Prompt $/1M
$0.400
Completion $/1M
$0.400
Context
131,072 tok
Best provider
45 tok/s · WandB

Specs

Model id
meta-llama/llama-3.1-70b-instruct
Display name
Meta: Llama 3.1 70B Instruct
Modality
text->text
Tokenizer
Llama3
Instruct type
llama3
Context length
131,072
Max completion
16,384
Prompt $/1M
$0.400
Completion $/1M
$0.400
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
WandBfastest45
CoreWeavefastest43
Amazon Bedrock30
DeepInfra16
Artificial Analysis0