Identity
- Status
- active
- Developer ID
command-a-reasoning-08-2025- Released
- Aug 21, 2025
- Version
- Command A Reasoning
- License
- Unknown
CohereCommand A Reasoning
Command A Reasoning is Cohere's enterprise reasoning model for multilingual agents, RAG, and tool use.
- Token context
- 256K tokens
- Inputs
- Text
- Outputs
- Text
- Released
- Aug 21, 2025
Providers & Pricing
1 current hosted offerings
No Directly Sourced Provider Price Yet
API pricing is provider-specific and stays unknown until a serving provider publishes an exact offering for this model version.
Benchmarks
All benchmark results →| ToneBench2026-10-17-10-task-e9c76358afb2 | 52.73 | 1,916 | 50 | Cohere Command A Reasoning (thinking on)average per case | Original sourcenot winner eligible | Third-party benchmark |
At a Glance
Model Facts
Capacity
- Token context
- 256K tokens
- Maximum output
- 32K tokens
- Total parameters
- 111B
- Active parameters
- Unknown
- Knowledge cutoff
- Jun 1, 2024
Interface and Access
- Inputs
- Text
- Outputs
- Text
- API available
- Yes
- Open weights
- No
- Self-hostable
- No
- Reasoning
- Yes
- Vision
- No
- Tool calling
- Yes
- Capabilities
- agents, chat, citations, reasoning, rag, structured outputs, tools
This page represents one developer model product. Dated API snapshots, serving endpoints, pricing, regions, quantizations, and service tiers attach as versioned aliases or provider details and never create duplicate public model records.
Version Lineage
PredecessorUnknown
SuccessorsUnknown
Aliasescommand-a-reasoning-08-2025
Explicit Unknowns
- Architecture
- Tokenizer
- Provider pricing
Primary Evidence
Sources and Observation Date
Comparable Peers
Related Model Comparisons
| A | Pair | B | Context |
|---|---|---|---|
Command A ReasoningCohere | vs |  DeepSeek V4.1 FlashDeepSeek | cross-developer peerstext |
Command A ReasoningCohere | vs |  Qwen3.8 MaxQwen | cross-developer peerstext |
Command A ReasoningCohere | vs |  GLM 5.3Z.ai | cross-developer peerstext |
Command A ReasoningCohere | vs | family variantstext | |
Command A ReasoningCohere | vs |  ERNIE 5.1Baidu | cross-developer peerstext |
Command A ReasoningCohere | vs | cross-developer peerstext | |
Command A ReasoningCohere | vs | ERNIE X1.1Baidu | cross-developer peerstext |
Command A ReasoningCohere | vs | Command ACohere | family variantstext |
Command A ReasoningCohere | vs | Command A TranslateCohere | family variantstext |
Command A ReasoningCohere | vs | Command A VisionCohere | family variantstext |
Command A ReasoningCohere | vs |  Sonar Deep ResearchPerplexity | cross-developer peerstext |
Command A ReasoningCohere | vs | Sonar Reasoning ProPerplexity | cross-developer peerstext |
Questions
Command A Reasoning FAQs
What is Command A Reasoning?+
Command A Reasoning is Cohere's enterprise reasoning model for multilingual agents, RAG, and tool use. It is developed by Cohere and its current sourced lifecycle status is active.
What inputs and outputs does Command A Reasoning support?+
Command A Reasoning's current record lists Text as input and Text as output.
How much context does Command A Reasoning support?+
The current record lists a 256K-token context window and a maximum output of 32K tokens.
Is Command A Reasoning available through an API?+
Command A Reasoning is marked as API-available. The directly sourced provider records currently include Cohere.
How large is Command A Reasoning?+
The current record lists 111B total parameters and an unknown active parameter count. Its architecture is not reported.
What capabilities and tasks does Command A Reasoning support?+
Command A Reasoning's recorded capabilities are agents, chat, citations, reasoning, rag, structured outputs, and tools. Its supported tasks are reasoning and text.
How much does Command A Reasoning cost through an API?+
No directly sourced token price is currently attached to Command A Reasoning. Missing prices remain unknown rather than being inferred from another model or provider.
Can Command A Reasoning be self-hosted?+
Command A Reasoning is not marked as an open-weight model. Self-hosting is marked as unsupported, with no license recorded.
Does Command A Reasoning have related versions or aliases?+
No predecessor is recorded. No successor is recorded. Recorded aliases are command-a-reasoning-08-2025.
Which models can Command A Reasoning be compared with?+
The current compatible peer set includes DeepSeek V4.1 Flash, Qwen3.8 Max, GLM 5.3, Command A Plus 05 2026 BF16, and ERNIE 5.1. Compatibility requires shared sourced modalities and tasks; it does not imply that one model is better. Browse model comparisons →