/ Models

Language models

Deep Cogito: Cogito v2.1 671B

Cogito v2.1 671B MoE represents one of the strongest open models globally, matching performance of frontier closed and open models. This model is trained using self play with reinforcement learning...

Maker
Deepcogito
Context window
128K
Max output
Input / 1M
$1.25
Output / 1M
$1.25
1M in + 1M out
$2.50

Everything else

Max output
Input / 1M$1.25
Output / 1M$1.25
Cache read / 1M
Cache write / 1M
1M in + 1M out$2.50
Takestext
Returnstext
Toolsno
Reasoningoptional
Open weightsno
Released2025-11-13
Knowledge cutoff
Retires
Catalog iddeepcogito/cogito-v2.1-671b

Using it

In 00, this model is picked per agent — and per tier, so the model that answers your customers need not be the one that writes your code. Get 00.

← all models