RealRelay.ai
OpenAI

GPT-4 (0613)

The 0613 snapshot of OpenAI's GPT-4, an older high-intelligence text model usable for chat completions.

Starting at
Input
$30.00/ 1M
Output
$60.00/ 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-4-0613
Input
$30.00 USD per 1M tokens
Output
$60.00 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-4-0613

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-4-0613",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-4-0613",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-4-0613",6    "messages": [{ "role": "user", "content": "Hello" }]7  }'

Prices and availability as published on Oct 12, 2026.

Capabilities

GPT-4 (0613) reads text and returns text, with a context window of 8,192 tokens and up to 8,192 output tokens per request.

It is used through chat-style requests. Its knowledge cutoff is December 1, 2023, and OpenAI lists a second dated snapshot beside it for locking in a model version.

Input
Text
Output
Text

Overview

GPT-4 (0613) is a dated snapshot of OpenAI's GPT-4, which OpenAI describes as an older high-intelligence GPT model usable in Chat Completions. It takes text input and returns text output, and the snapshot lets an integration stay on one fixed version of the model.

GPT-4 (0613) has a context window of 8,192 tokens and can generate up to 8,192 output tokens. It accepts text input and returns text output. Its knowledge cutoff is December 1, 2023.

Pricing

GPT-4 (0613) is billed per token: $30.00 per 1M input tokens and $60.00 per 1M output tokens. GPT-4 (0613) is available through RealRelay's OpenAI-compatible API.

Use cases

Use GPT-4 (0613) for text-only chat and reasoning-style question answering in applications that were validated against this exact snapshot and need its behavior to remain fixed.

With a window of 8,192 tokens, it suits focused prompts such as answering questions, drafting messages or analyzing short documents, rather than very long inputs.

Frequently asked questions

What is GPT-4 (0613)?
GPT-4 (0613) is a dated snapshot of OpenAI's GPT-4, which OpenAI describes as an older high-intelligence GPT model usable in Chat Completions. It takes text input and returns text output, and the snapshot lets an integration stay on one fixed version of the model.
How much does GPT-4 (0613) cost?
GPT-4 (0613) costs $30.00 per 1M input tokens and $60.00 per 1M output tokens.
What is the context window of GPT-4 (0613)?
GPT-4 (0613) has a context window of 8,192 tokens and can generate up to 8,192 output tokens.
What inputs and outputs does GPT-4 (0613) support?
GPT-4 (0613) accepts text input and returns text output.
What is the knowledge cutoff of GPT-4 (0613)?
The knowledge cutoff of GPT-4 (0613) is December 1, 2023.
How do I call GPT-4 (0613) through the API?
To call GPT-4 (0613), send a request to RealRelay's OpenAI-compatible API with the model ID openai/gpt-4-0613.

More from OpenAI

All 42 OpenAI models