Cogito v2 Preview Llama 109B MoE
Cogito v2 Preview Llama 109B MoE is a released agents and json / tool use model with open-weight; evaluate it while provider pricing coverage matures.
Use it for
- Teams evaluating agents and json / tool use
Do not use it for
- Cost-sensitive launches that need sourced token pricing
- Vision or document-understanding workloads
- Teams that need a tracked hosted API route today
- Family
- Cogito
- Released
- 2025-07-31
- Parameters
- 109B
- Architecture
- Mixture of Experts
- Knowledge cutoff
- 2023-12
- Specialization
- general
- Openness
- Open weights
- License
- Llama 3 CommunityCommercial use: conditional
- Training
- Fine-tuned
Building general superintelligence through advanced reasoning and iterative self-improvement.
No tracked provider token pricing is available yet.
About
Cogito v2 Preview Llama 109B MoE is a 109B Mixture-of-Experts hybrid reasoning model from Deep Cogito, fine-tuned from a Llama MoE base using Iterated Distillation and Amplification (IDA). Released July 2025. License not confirmed from primary sources.
Cogito v2 Preview Llama 109B MoE is an open-weight model in the Cogito family. The structured metadata tracks reasoning, function calling, and tool use. No headline benchmark score is tracked for Cogito v2 Preview Llama 109B MoE yet.
Top use-case fit: coding, agents, and build tasks
Agents
Included by capability and metadata signals in the decision map.
JSON / Tool use
Included by capability and metadata signals in the decision map.
Provider price ladder
No tracked provider token pricing is available for this model yet.
Capabilities
Benchmark peer barsfor Agents
No task-mapped benchmark peers are available for this model yet.
Migration checks
No linked migration route is available for this model yet.
Building general superintelligence through advanced reasoning and iterative self-improvement.
No tracked provider token pricing is available yet.