Question 1

What is GPT-3.5 Turbo?

Accepted Answer

GPT-3.5 Turbo is a model from OpenAI, released on Mar 1, 2023. The GPT-3.5 Turbo (currently points to gpt-3.5-turbo-0125.	) is OpenAI's advanced model designed for rapid performance in both understanding and generating text. Optimized for interactive chat and comprehensive text completion tasks, it seamlessly processes natural language and code.

This version of GPT-3.5 Turbo delivers enhanced accuracy in generating responses in diverse formats, effectively addressing previous encoding issues with non-English languages.

The model supports a context size of 16,385 tokens and a maximum of 4,096 output tokens, providing substantial flexibility for various applications. Training data for this model cuts off in September 2021.

For additional details on the capabilities and updates of the GPT-3.5 Turbo, you can visit OpenAI's resource [here](https://platform.openai.com/docs/models/gpt-3-5-turbo).

Question 2

How much does GPT-3.5 Turbo cost?

Accepted Answer

On the Respan gateway, input starts at $0.50 per 1M tokens on every provider, and output starts at $0.10 per 1M tokens on Azure OpenAI, after gateway discounts. Averaged across 6 providers, it costs $0.58 per 1M input tokens and $1.35 per 1M output tokens.

Question 3

Which providers serve GPT-3.5 Turbo on Respan?

Accepted Answer

6 providers serve GPT-3.5 Turbo: Azure OpenAI, OpenAI, and OpenRouter. Azure OpenAI requires your own provider API key (BYOK).

Question 4

What is GPT-3.5 Turbo's context window?

Accepted Answer

GPT-3.5 Turbo accepts up to 16K tokens of context on its largest provider route.

Question 5

How do I use GPT-3.5 Turbo with the Respan gateway?

Accepted Answer

Point any OpenAI-compatible SDK at https://api.respan.ai/api/ with your Respan API key and set the model to "openai/gpt-3.5-turbo". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Question 6

How fast is GPT-3.5 Turbo?

Accepted Answer

Over the last 30 days of requests through the Respan gateway, the fastest provider was OpenRouter at 22 tokens per second, and the lowest response latency was 0.4 seconds on OpenRouter. Speed varies with request size and provider.

Provider	Context	Input	Output
Azure OpenAIBYOK only`azure/gpt-35-turbo`	16K	$0.50/M	$0.10/M
OpenAI`openai/gpt-3.5-turbo`	16K	$0.50/M	$1.50/M
OpenAI`openai/gpt-3.5-turbo-0125`	16K	$0.50/M	$1.50/M
OpenAI`openai/gpt-3.5-turbo-1106`	16K	$0.50/M	$1.50/M
OpenRouter`openrouter/openai/gpt-3.5-turbo`	16K	$0.50/M	$1.50/M
OpenRouter`openrouter/openai/gpt-3.5-turbo-0613`	4K	$1.00/M	$2.00/M

GPT-3.5 Turbo

Providers

Certified where it counts.

Pricing

Cost by volume

Throughput and latency

Output speed

Response latency

Apps

GPT-3.5 Turbo FAQ

Works with your entire stack

Built for AI agents.
Break less.
Ship more.