These dated provider observations are not a recommendation certificate, proof of model quality or account entitlement. Use/API eligibility remains disabled for the models marked Review required. Unit prices are not workload totals or a fixed quote.
Review required describes these new facts. Historical describes earlier saved reviews or rankings; it does not mean this model has been retired. Source freshness and recommendation eligibility are separate.
Last checked: · Source freshness: Current
Provider status
Live
Canonical lifecycle
Unknown
Original release
Unknown
Document input cost
2.5
Answer output cost
10
Long documents
256000
Long answers
8000
Read images
Unknown
Audio
Unknown
Call tools
Supported
Structured output
Supported
Usage & billing conditions
Currency
USD
Billing unit
per 1M tokens
Cached input
Unknown
API
Supported
Chat
Unknown
Enterprise
Unknown
Regions
Unknown
The provider lists the exact ID as Live, not an explicit GA designation. Canonical lifecycle remains Unknown; this label cannot establish recommendation eligibility. The directory says Text while the exact-model page lists Image Inputs. Vision remains Unknown; direct audio is also unverified. No capability is inferred from the conflict.
Published API unit rates are shown above. Documented limits are 20 trial and 500 production requests/minute, not verified account entitlement. Cached-input price, production onboarding, sensitive-use restrictions and enterprise access remain separate or unverified.
For paying SaaS customers, training use depends on Data Controls opt-out; trial terms differ. Actual account controls, ZDR approval, contracts, regions and consumer-chat access were not verified.
For paying SaaS customers, the 30-day commitment covers logged prompts/generations, with legal, contractual, abuse and permitted-training exceptions—not all abuse-monitoring logs. Enterprise ZDR requires approval and does not eliminate usage-data collection.
The provider lists the exact ID as Live, not an explicit GA designation. Canonical lifecycle remains Unknown; this label cannot establish recommendation eligibility. The directory says Text while the exact-model page lists Image Inputs. Vision remains Unknown; direct audio is also unverified. No capability is inferred from the conflict.
Review required
Common family use cases
Assumption · Answer from company knowledge · Use current information or tools · Work across languages
Family limitations
Assumption · RAG quality depends heavily on retrieval, documents, and citations configuration.
Published ranking signals
Historical · 1 · User preference
Verify the exact version before choosing: capabilities, price, context limits, latency, tools, and regional availability can differ by provider access path.
Assumption · OpenGPT catalog guidance
Best for
Enterprise retrieval, governed workflows, and business-system integration.
Enterprise retrieval, agents, tools, and multilingual business workflows.
Strengths
The enterprise role emphasizes managed business and retrieval workflows.
Command A is provider-listed as the enterprise release in its model family.
Weaknesses
General availability does not guarantee identical capabilities across every product, account, or endpoint.
Verify exact capabilities, pricing, latency, context limits, tools, and regional availability with the provider.
Assumption · These points are OpenGPT decision guidance derived from provider-confirmed family, catalog role, and lifecycle information. They are not measured results for this exact version. Verify capabilities, pricing, latency, context limits, tools, and regional availability with the provider.
Model family
Family-level guidance
The following summary describes the broader model family from official positioning. It is not a measured result for this exact version.
CA
Assumption · Model family: Command
Command
Cohere's enterprise-oriented generation family for RAG, agents, tool use, and multilingual work.
Answer from company knowledgeUse current information or toolsWork across languagesRead, analyze, or write
Product line is explicitly designed around retrieval and enterprise workflows. Works with Cohere's embedding, reranking, and deployment ecosystem.
!
Family limitations
RAG quality depends heavily on retrieval, documents, and citations configuration. The family includes distinct Command versions with different capabilities.
Verify the exact version before choosing: capabilities, price, context limits, latency, tools, and regional availability can differ by provider access path.
Provider documentation and OpenGPT catalog classification are labeled separately.
Version differences
Compare two catalog model IDs from one model family. Provider IDs, sources and published ranking signals are shown; OpenGPT catalog classification is labeled separately.
OpenGPT