Benchmarks

Prime Intellect: INTELLECT-3

prime-intellect/intellect-3

INTELLECT-3 is an open-weight model from Prime Intellect, ranking #147 of 236 on the TryAii Score. It's served by 1 independent host from $0.2/$1.1 per million input/output tokens — about half of what models at its level usually charge. It's reasonably quick at about 58 tokens/sec.

Prompt $/1M
$0.200
Completion $/1M
$1.100
Context
131,072 tok
Best provider
58 tok/s · Nebius

Specs

Model id
prime-intellect/intellect-3
Display name
Prime Intellect: INTELLECT-3
Modality
text->text
Tokenizer
Other
Instruct type
Context length
131,072
Max completion
131,072
Prompt $/1M
$0.200
Completion $/1M
$1.100
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
Nebiusfastest58
prime-intellectfastest
Artificial Analysis0