Question 1

What is GPT-3.5 Turbo Instruct?

Accepted Answer

GPT-3.5 Turbo Instruct is a model from OpenAI, released on Sep 18, 2023. The gpt-3.5-turbo-instruct model mirrors features found in GPT-3 era variants. Tailored for instructional prompts, it excludes optimizations for chat functions. Compatible with legacy Completions endpoints, it's unsuitable for Chat Completions.

The model has a 4,096 token context window, facilitating structured guidance scenarios. Training data for this model cuts off in September 2021.

Question 2

How much does GPT-3.5 Turbo Instruct cost?

Accepted Answer

On the Respan gateway, input starts at $1.50 per 1M tokens on every provider, and output starts at $2.00 per 1M tokens on every provider, after gateway discounts.

Question 3

Which providers serve GPT-3.5 Turbo Instruct on Respan?

Accepted Answer

2 providers serve GPT-3.5 Turbo Instruct: OpenAI and OpenRouter.

Question 4

What is GPT-3.5 Turbo Instruct's context window?

Accepted Answer

GPT-3.5 Turbo Instruct accepts up to 4K tokens of context on its largest provider route.

Question 5

How do I use GPT-3.5 Turbo Instruct 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-instruct". 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 Instruct?

Accepted Answer

Over the last 30 days of requests through the Respan gateway, the fastest provider was OpenRouter at 8 tokens per second, and the lowest response latency was 1.9 seconds on OpenRouter. Speed varies with request size and provider.

Provider	Context	Input	Output	Capabilities
OpenAI`openai/gpt-3.5-turbo-instruct`	4K	$1.50/M	$2.00/M
OpenRouter`openrouter/openai/gpt-3.5-turbo-instruct`	4K	$1.50/M	$2.00/M	—

GPT-3.5 Turbo Instruct

Providers

Certified where it counts.

Pricing

Cost by volume

Throughput and latency

Output speed

Response latency

Apps