The GPT-3.5 Turbo-16K, currently points to the gpt-3.5-turbo-16k-0613 version, represents an enhanced iteration of OpenAI’s models, providing a substantially increased context window of 16,385 tokens. This capability allows the model to handle documents roughly equivalent to 20 pages in a single query, supporting more complex and extensive interactions. Designed for scenarios requiring deep context comprehension, this model is particularly useful in professional environments where detailed document analysis and extended dialogues are common. Training data for this model cuts off in September 2021, focusing on delivering a robust performance across a variety of tasks with enhanced accuracy and efficiency. GPT-3.5 Turbo 16K (0613) will remain in service until its planned deprecation on June 13, 2024, as part of OpenAI's ongoing model updates.
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="openrouter/openai/gpt-3.5-turbo-16k", messages=[{"role": "user", "content": "Hello!"}],)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="openrouter/openai/gpt-3.5-turbo-16k", messages=[{"role": "user", "content": "Hello!"}],)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.
Built to meet the security and privacy standards that enterprise and healthcare teams require.
ISO 27001
The internationally recognized standard for information security management.
SOC 2
Secure, compliant management of your data across all of our systems.
GDPR
Operated under GDPR, the world's strictest standard for data privacy.
HIPAA
HIPAA compliant, with a BAA available for healthcare teams.