Skip to content
OpenKey

GPT-3.5 Turbo Instruct

OpenAIReleased Sep 28, 2023

This model is a variant of GPT-3.5 Turbo tuned for instructional prompts and omitting chat-related optimizations. Training data: up to Sep 2021.

Try in playground
Context window
4K tokens
Max output
4K tokens
Input
text
Output
text
Tokenizer
GPT
Knowledge cutoff
Sep 30, 2021
Released
Sep 28, 2023

Pricing

Per 1M tokens. The provider price and our flat 3% fee are separate columns — what you pay is their sum.

Per 1M tokensProvider+ 3% feeYou pay
Input$1.50$0.045$1.54
Output$2.00$0.060$2.06

Supported parameters

  • frequency_penalty
  • logit_bias
  • logprobs
  • max_tokens
  • presence_penalty
  • response_format
  • seed
  • stop
  • structured_outputs
  • temperature
  • top_logprobs
  • top_p

Call it

OpenAI-compatible: point your SDK at api.openkey.ai/v1 and use model openai/gpt-3.5-turbo-instruct.

Code sample language
curl https://api.openkey.ai/v1/chat/completions \
  -H "Authorization: Bearer $OPENKEY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-3.5-turbo-instruct",
    "messages": [{"role": "user", "content": "Hello"}]
  }'
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.openkey.ai/v1",
    api_key=os.environ["OPENKEY_API_KEY"],
)

completion = client.chat.completions.create(
    model="openai/gpt-3.5-turbo-instruct",
    messages=[{"role": "user", "content": "Hello"}],
)
print(completion.choices[0].message.content)
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.openkey.ai/v1",
  apiKey: process.env.OPENKEY_API_KEY,
});

const completion = await client.chat.completions.create({
  model: "openai/gpt-3.5-turbo-instruct",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);

Questions

How much does GPT-3.5 Turbo Instruct cost via API?
Through OpenKey, GPT-3.5 Turbo Instruct costs $1.54 per 1M input tokens and $2.06 per 1M output tokens. That is the provider price ($1.50 / $2.00) plus a flat 3% fee — nothing else.
What is GPT-3.5 Turbo Instruct's context window?
GPT-3.5 Turbo Instruct accepts up to 4K tokens of context and returns up to 4K tokens per request.
Is GPT-3.5 Turbo Instruct OpenAI-compatible?
Yes. Send requests to OpenKey's /v1/chat/completions endpoint with model "openai/gpt-3.5-turbo-instruct" using any OpenAI SDK — only the base URL and API key change.
What inputs does GPT-3.5 Turbo Instruct support?
GPT-3.5 Turbo Instruct accepts text input and produces text output. Its knowledge cutoff is Sep 30, 2021.

More from OpenAI

All OpenAI models →