RealRelay.ai
OpenAI

GPT-3.5 Turbo (0125)

The 0125 snapshot of OpenAI's GPT-3.5 Turbo, pinned for consistent chat and text behavior.

Starting at
Input
$0.50/ 1M
Output
$1.50/ 1M
Open dashboard

Channel

Each channel is compared at its lowest input-price tier; output breaks ties. A dash means /api/pricing does not provide that rate. Selecting a channel updates the endpoints and call example below.

openai/gpt-3.5-turbo-0125
Input
$0.50 USD per 1M tokens
Output
$1.50 USD per 1M tokens
Cache read
- USD per 1M tokens
Cache write
- USD per 1M tokens

Endpoints

POST/v1/chat/completionsChat Completions

Call it

Using openai/gpt-3.5-turbo-0125

1from openai import OpenAI23client = OpenAI(4    base_url="https://www.realrelay.ai/v1",5    api_key="sk-***",6)78response = client.chat.completions.create(9    model="openai/gpt-3.5-turbo-0125",10    messages=[{"role": "user", "content": "Hello"}],11)1213print(response.choices[0].message.content)
1import OpenAI from "openai";23const client = new OpenAI({4  baseURL: "https://www.realrelay.ai/v1",5  apiKey: process.env.REALRELAY_API_KEY,6});78const response = await client.chat.completions.create({9  model: "openai/gpt-3.5-turbo-0125",10  messages: [{ role: "user", content: "Hello" }],11});1213console.log(response.choices[0].message.content);
1curl https://www.realrelay.ai/v1/chat/completions \2  -H "Authorization: Bearer $REALRELAY_API_KEY" \3  -H "Content-Type: application/json" \4  -d '{5    "model": "openai/gpt-3.5-turbo-0125",6    "messages": [{ "role": "user", "content": "Hello" }]7  }'

Prices and availability as published on Oct 12, 2026.

Capabilities

GPT-3.5 Turbo (0125) takes text input and returns text output. It handles multi-turn chat as well as non-chat natural language and code tasks within its 16,385-token context window.

Choosing the dated 0125 snapshot instead of a moving name keeps the model version fixed in your integration.

Input
Text
Output
Text

Overview

GPT-3.5 Turbo (0125) is a dated snapshot of OpenAI's GPT-3.5 Turbo, a legacy GPT model that understands and generates natural language or code. It is optimized for chat and works for non-chat tasks too. OpenAI lists it as the default snapshot behind the GPT-3.5 Turbo name, and snapshots lock in one version so behavior stays consistent.

GPT-3.5 Turbo (0125) has a context window of 16,385 tokens and can generate up to 4,096 output tokens. It accepts text input and returns text output. Its knowledge cutoff is September 1, 2021.

Pricing

GPT-3.5 Turbo (0125) is billed per token: $0.50 per 1M input tokens and $1.50 per 1M output tokens. GPT-3.5 Turbo (0125) is available through RealRelay's OpenAI-compatible API.

Use cases

Use GPT-3.5 Turbo (0125) for text chat assistants where you want a fixed snapshot, so that replies do not shift when a general model name is updated.

It also fits non-chat text jobs such as drafting or reformatting content and generating short code snippets, with up to 4,096 output tokens per request.

Frequently asked questions

What is GPT-3.5 Turbo (0125)?
GPT-3.5 Turbo (0125) is a dated snapshot of OpenAI's GPT-3.5 Turbo, a legacy GPT model that understands and generates natural language or code. It is optimized for chat and works for non-chat tasks too. OpenAI lists it as the default snapshot behind the GPT-3.5 Turbo name, and snapshots lock in one version so behavior stays consistent.
How much does GPT-3.5 Turbo (0125) cost?
GPT-3.5 Turbo (0125) costs $0.50 per 1M input tokens and $1.50 per 1M output tokens.
What is the context window of GPT-3.5 Turbo (0125)?
GPT-3.5 Turbo (0125) has a context window of 16,385 tokens and can generate up to 4,096 output tokens.
What inputs and outputs does GPT-3.5 Turbo (0125) support?
GPT-3.5 Turbo (0125) accepts text input and returns text output.
What is the knowledge cutoff of GPT-3.5 Turbo (0125)?
The knowledge cutoff of GPT-3.5 Turbo (0125) is September 1, 2021.
How do I call GPT-3.5 Turbo (0125) through the API?
To call GPT-3.5 Turbo (0125), send a request to RealRelay's OpenAI-compatible API with the model ID openai/gpt-3.5-turbo-0125.

More from OpenAI

All 42 OpenAI models