Skip to content
OpenKey

GPT-4 Turbo

OpenAIReleased Apr 9, 2024

The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling. Training data: up to December 2023.

Try in playground
Context window
128K tokens
Max output
4K tokens
Input
text, image
Output
text
Tokenizer
GPT
Knowledge cutoff
Dec 31, 2023
Released
Apr 9, 2024

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$10.00$0.300$10.30
Output$30.00$0.900$30.90

Benchmarks

Artificial Analysis

Intelligence index
Coding index
21.5
Agentic index

Supported parameters

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

Call it

OpenAI-compatible: point your SDK at api.openkey.ai/v1 and use model openai/gpt-4-turbo.

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-4-turbo",
    "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-4-turbo",
    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-4-turbo",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);

Questions

How much does GPT-4 Turbo cost via API?
Through OpenKey, GPT-4 Turbo costs $10.30 per 1M input tokens and $30.90 per 1M output tokens. That is the provider price ($10.00 / $30.00) plus a flat 3% fee — nothing else.
What is GPT-4 Turbo's context window?
GPT-4 Turbo accepts up to 128K tokens of context and returns up to 4K tokens per request.
Is GPT-4 Turbo OpenAI-compatible?
Yes. Send requests to OpenKey's /v1/chat/completions endpoint with model "openai/gpt-4-turbo" using any OpenAI SDK — only the base URL and API key change.
What inputs does GPT-4 Turbo support?
GPT-4 Turbo accepts text, image input and produces text output. Its knowledge cutoff is Dec 31, 2023.

More from OpenAI

All OpenAI models →