Command is a LLM designed for instruction-following tasks, offering high-quality performance, improved reliability, and the ability to handle longer context (4096 tokens) compared to base generative models. With a focus on conversational AI, this model excels in various language tasks. Command's versatility makes it suitable for a wide range of applications, from chatbots to natural language understanding tasks. Its enhanced ability to process longer context enables more accurate responses and better language understanding in complex scenarios.
from openai import OpenAI client = OpenAI( base_url="https://api.respan.ai/api/", api_key="YOUR_RESPAN_API_KEY",) response = client.chat.completions.create( model="cohere/command", messages=[{"role": "user", "content": "Hello!"}], extra_body={ "fallback_models": ["command"], },)print(response.choices[0].message.content)from openai import OpenAI client = OpenAI( base_url="https://api.respan.ai/api/", api_key="YOUR_RESPAN_API_KEY",) response = client.chat.completions.create( model="cohere/command", messages=[{"role": "user", "content": "Hello!"}], extra_body={ "fallback_models": ["command"], },)print(response.choices[0].message.content)Gateway routes for this model on the Respan gateway, including fallback routes when configured.
Other models from the same provider available through the gateway.
ISO 27001
Respan is fully compliant with ISO 27001, the internationally recognized standard for information security management.
SOC 2
We meet SOC 2 requirements to ensure secure and compliant management of data across all our systems.
GDPR
With operations designed for global compliance, we operate under GDPR - the world's strictest standard for data privacy.
HIPAA
Respan is HIPAA compliant with a Business Associate Agreement available for healthcare organizations.