Plain-English Summary
A Command model specialized for complex reasoning while retaining enterprise tool and retrieval features.
Command A Reasoning
A Command model specialized for complex reasoning while retaining enterprise tool and retrieval features.
Command
Reasoning LLM
GA
Open weights: No
API: Yes
Technical Notes
Reasoning-tuned text model with 256K context, 32K output, multilingual support, and tool use.
Best For
Complex enterprise analysis, planning, multilingual reasoning
Watch Out For
More latency and cost than standard Command A for routine tasks.
Model Specs
- Maker
- Cohere
- Country
- Canada
- Family
- Command
- Type
- Reasoning LLM
- Release date
- 2025-08-01
- Date confidence
- Month / model ID
- Status
- GA
- Context window
- 262,144 tokens
- Max output
- 32,768
- Parameters
- Not disclosed
- Active parameters
- Not disclosed
- Architecture
- Proprietary reasoning transformer
- Reasoning
- Yes — specialized
- Tool calling
- Yes
- Structured output
- Yes
- API available
- Yes
- Open weights
- No
- Self-hostable
- Private deployment options
- License
- Proprietary
- Inputs
- Text
- Outputs
- Text
- Approx. price
- See provider pricing
- How to access
- Provider website or API
- Model / API ID
- command-a-reasoning-08-2025
- Knowledge cutoff
- Not publicly disclosed
- Fine-tuning
- RAG, tools, private deployment
- Completeness
- 90 %
- Verified
- Jul 18, 2026
- Snapshot date
- Jul 18, 2026
- Source
- Official source