GPT-4

gpt-4 by OpenAI Released May 28, 2023
ReasoningFunction callingStructured outputPrompt cachingWeb searchComputer useImage inputFile inputAudio inputVideo inputEU hostingFree endpointUp to % off
Input from
$30 / 1M
Output from
$60 / 1M
Cached input from
$ / 1M
Context window
8K
Endpoints
2
from 2 providers
Regions
Monde, États-Unis

About GPT-4

Le modèle phare d'OpenAI, GPT-4, est un modèle linguistique multimodal à grande échelle capable de résoudre des problèmes complexes avec une plus grande précision que les modèles précédents, grâce à ses connaissances générales plus étendues et à son raisonnement avancé…

GPT-4 est un modèle conversationnel développé par OpenAI, disponible sur Eden AI via 2 endpoints chez 2 fournisseurs, à partir de 30 $ par million de tokens en entrée et 60 $ par million de tokens en sortie, avec une fenêtre de contexte allant jusqu'à 8K tokens.

Providers and prices

2 endpoints from 2 providers, cheapest first, in USD per million tokens. Every one is called with the same Eden AI key: pin one with its endpoint ID, or let Eden AI route for you. .

Endpoint
Region
Context
Input / 1M
Output / 1M
Cached / 1M
Supports
Microsoft AzureOfficial−%microsoft/gpt-4
Monde
8K
$30$30
$60
$
ReasoningToolsJSONCacheVisionWeb
OpenAI (États-Unis)Official−%openai/gpt-4
États-Unis
8K
$30$30
$60
$
ReasoningToolsJSONCacheVisionWeb

Performance

Measured on real Eden AI traffic over the last 30 days. Endpoints with too little traffic are not shown.

Fastest first token
0.66 s
OpenAI (États-Unis)
Lowest latency
1.05 s
OpenAI (États-Unis)
Highest throughput
14.52 tok/s
OpenAI (États-Unis)
Best availability
100%
Microsoft Azure
Endpoint
First token
Latency p50
Latency p95
Throughput
Availability
Cache hits
Tool errors
JSON errors
Microsoft Azure
1.06 s
1.23 s
2.05 s
3.62 tok/s
100%
0%
0%
0%
OpenAI (États-Unis)
0.66 s
1.05 s
3.69 s
14.52 tok/s
97.7%
75.39%
1.47%
0%

Estimate your monthly cost

Enter your expected volume to compare every endpoint at once.

Call GPT-4 with Eden AI

Use the model ID to let Eden AI pick an endpoint, or an endpoint ID from the table above to pin one.

import requests

response = requests.post(
    "https://api.edenai.run/v3/chat/completions",
    headers={"Authorization": "Bearer YOUR_EDENAI_API_KEY"},
    json={
        "model": "",
        "messages": [{"role": "user", "content": "Hello!"}],
    },
)
print(response.json())

Questions about GPT-4

On Eden AI, prices for this model start at $30 per million input tokens and $60 per million output tokens. Prices differ by endpoint; the providers table lists each one. .

Up to 8K tokens, depending on the endpoint.

2 endpoints from 2 providers, available in: Monde, États-Unis. All of them are called with the same Eden AI API key.

Yes. At least one endpoint is hosted in Europe; pin it with its endpoint ID from the providers table to keep requests in the EU.

Over the last 30 days, the fastest first token was 0.66 s (OpenAI (États-Unis)) and the highest throughput was 14.52 tokens per second (OpenAI (États-Unis)).