Activefastllm Proprietary

command

by Cohere· Released March 2023· Cutoff August 2022

Command is Cohere's flagship generative language model optimized for enterprise use cases such as text generation, summarization, and retrieval-augmented generation (RAG). It balances strong performance with cost efficiency, making it suitable for production deployments. Command is distinct for its native support of tool use and multi-step reasoning via chain-of-thought.

Official Site API Docs

Input cost

$1.00 per 1M tokens

Output cost

$2.00 per 1M tokens

Context window

4096 tokens

Max output

4096 tokens

Modalities

text

License

proprietary

Capabilities

Text GenerationSummarizationRetrieval-Augmented Generation (RAG)Tool Use / Function CallingChain-of-Thought ReasoningStreamingJSON Mode

Best For

Enterprise text generation tasks requiring reliable performance, RAG, and tool use at a competitive price.

Strengths

Strong performance on enterprise NLP tasks like summarization and Q&A
Native support for RAG and tool use
Cost-effective pricing for production workloads
Good balance of speed and quality

Limitations

Smaller context window (4096 tokens) compared to newer models
No vision or multimodal capabilities
May lag behind frontier models on complex reasoning benchmarks
Limited to text-only input and output

Use Cases

Customer support chatbots

Document summarization

Content generation for marketing

Enterprise knowledge base Q&A

Data extraction and classification

Code generation and explanation

Email drafting and response

Back to all models

Activefastllm Proprietary

command

by Cohere· Released March 2023· Cutoff August 2022

Official Site API Docs

Input cost

$1.00 per 1M tokens

Output cost

$2.00 per 1M tokens

Context window

4096 tokens

Max output

4096 tokens

Modalities

text

License

proprietary

Capabilities

Text GenerationSummarizationRetrieval-Augmented Generation (RAG)Tool Use / Function CallingChain-of-Thought ReasoningStreamingJSON Mode

Best For

Enterprise text generation tasks requiring reliable performance, RAG, and tool use at a competitive price.

Strengths

Strong performance on enterprise NLP tasks like summarization and Q&A
Native support for RAG and tool use
Cost-effective pricing for production workloads
Good balance of speed and quality

Limitations

Smaller context window (4096 tokens) compared to newer models
No vision or multimodal capabilities
May lag behind frontier models on complex reasoning benchmarks
Limited to text-only input and output

Use Cases

Customer support chatbots

Document summarization

Content generation for marketing

Enterprise knowledge base Q&A

Data extraction and classification

Code generation and explanation

Email drafting and response

Back to all models