OpenAI: GPT-4 Turbo Preview

openai/gpt-4-turbo-preview

Created Jan 25, 2024128,000 context
$10/M input tokens$30/M output tokens

The preview GPT-4 model with improved instruction following, JSON mode, reproducible outputs, parallel function calling, and more. Training data: up to Dec 2023.

Note: heavily rate limited by OpenAI while in preview.

Providers for GPT-4 Turbo Preview

OpenRouter routes requests to the best providers that are able to handle your prompt size and parameters, with fallbacks to maximize uptime.

Context
128K
Max Output
4K
Input
$10
Output
$30

Apps using GPT-4 Turbo Preview

Top public apps this week using this model

1.
Favicon for https://github.com/Calcium-Ion/new-api
New API
new
2.54Mtokens
2.
Favicon for https://github.com/mibexx/mbxai
MBX AI
new
650Ktokens
3.
Favicon for https://cbminformatica.com.br/
Cbm-Informatica
new
359Ktokens
4.
Favicon for https://www.usemynt.com/
Mynt
Free AI writing done right
156Ktokens
5.
Favicon for https://Agent37.ai/
agent37.ai
new
149Ktokens
6.
Favicon for https://github.com/alonsosilvaallende/chatplotlib-openrouter
github.com/alonsosilvaallende/chatplotlib-openrouter
new
124Ktokens
7.
Favicon for https://sillytavern.app/
SillyTavern
LLM frontend for power users
68Ktokens
8.
Favicon for https://github.com/OpenRouterTeam/openrouter-examples
github.com/OpenRouterTeam/openrouter-examples
new
67Ktokens
9.
Favicon for https://apipie.ai/
APIpie.ai
new
30Ktokens
10.
Favicon for https://biokea.ai/
BioKEA Paper Reviewer
new
29Ktokens
11.
Favicon for https://script.4cg.fr/
script.4cg.fr
new
23Ktokens
12.
Favicon for https://github.com/opnpumar/api_ofs25
OFS25 Marine Route Forecast
new
22Ktokens
13.
Favicon for https://realaitools.replit.app/
AI Chat Assistant
new
20Ktokens
14.
Favicon for https://openrouter.ai/chat
OpenRouter: Chatroom
Chat with multiple LLMs at once
19Ktokens
15.
Favicon for https://github.com/chrisboden
Chris Boden's Bookmark Manager
new
17Ktokens
16.
Favicon for https://zp1v56uxy8rdx5ypatb0ockcb9tr6a-oci3-50mil198--5173--4d9fd228.local-credentialless.webcontainer-api.io/
PSL Predictor App
new
17Ktokens
17.
Favicon for https://github.com/carsten-frey/schreibhorst
Schreibhorst
new
16Ktokens
18.
Favicon for https://schreibhorst.com/
Schreibhorst Analyzer
new
12Ktokens
19.
Favicon for https://novelcrafter.com/
novelcrafter
Your personal novel writing toolbox. Plan, write and tinker with your story.
9Ktokens
20.
Favicon for https://xenocrm.io/
xenoCRM
new
8Ktokens

Recent activity on GPT-4 Turbo Preview

Tokens processed per day

Feb 11Feb 17Feb 23Mar 1Mar 7Mar 13Mar 19Mar 25Mar 31Apr 6Apr 12Apr 18Apr 24Apr 30May 6May 1203.5M7M10.5M14M

Uptime stats for GPT-4 Turbo Preview

Uptime stats for GPT-4 Turbo Preview on the only provider

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it.

Learn more about our load balancing and customization options.

Sample code and API for GPT-4 Turbo Preview

OpenRouter normalizes requests and responses across providers for you.

OpenRouter provides an OpenAI-compatible completion API to 300+ models & providers that you can call directly, or using the OpenAI SDK. Additionally, some third-party SDKs are available.

In the examples below, the OpenRouter-specific headers are optional. Setting them allows your app to appear on the OpenRouter leaderboards.

from openai import OpenAI

client = OpenAI(
  base_url="https://openrouter.ai/api/v1",
  api_key="<OPENROUTER_API_KEY>",
)

completion = client.chat.completions.create(
  extra_headers={
    "HTTP-Referer": "<YOUR_SITE_URL>", # Optional. Site URL for rankings on openrouter.ai.
    "X-Title": "<YOUR_SITE_NAME>", # Optional. Site title for rankings on openrouter.ai.
  },
  extra_body={},
  model="openai/gpt-4-turbo-preview",
  messages=[
    {
      "role": "user",
      "content": "What is the meaning of life?"
    }
  ]
)
print(completion.choices[0].message.content)

Using third-party SDKs

For information about using third-party SDKs and frameworks with OpenRouter, please see our frameworks documentation.

See the Request docs for all possible fields, and Parameters for explanations of specific sampling parameters.

More models from OpenAI

    GPT-4 Turbo Preview - API, Providers, Stats | OpenRouter