Cogito v2.1
Cogito v2.1 is DeepCogito's language model. A hybrid reasoning LLM from Deep Cogito trained with self-play reinforcement learning, balancing instruction following and chain-of-thought reasoning.
DeepCogito's language model. A hybrid reasoning LLM from Deep Cogito trained with self-play reinforcement learning, balancing instruction following and chain-of-thought reasoning.deepcogito-cogito-2-1-reasoning |
| Language |
| Active |
| DeepCogito |
| Text |
| Text |
24.8#73 |
72.7#46 |
0.8#17 |
0.8#60 |
0.1#61 |
0.7#41 |
0.5#75 |
0.33s#152 |
0.4#27 |
0.7#46 |
0.2#141 |
0.2#78 |
94.2#95 |
Capabilities
Input1/5
✓
·
·
·
·
Output1/5
✓
·
·
·
·
Capabilities0/13
·
·
·
·
·
·
·
·
·
·
·
·
·
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Cogito v2.1 671B | 128K | $1.25 | $1.25 | Available | |
| Cogito v2.1 | — | — | — | — | Current |
| Cogito 2 671B | — | 164K | $1.20 | $1.20 | Available |
| Cogito 2 671B P1 | — | 164K | — | — | Available |