GPT-5

gpt-5 by OpenAI Released August 8, 2025
Reasoning · Function calling · Structured output · Prompt caching · Web search · Image input · File input · EU hosting
Input from
$1.25 / 1M
Output from
$10 / 1M
Cached input from
$0.125 / 1M
Context window
400K
Endpoints
6
from 3 providers
Regions
Global, Europe, United States

About GPT-5

GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience.

GPT-5 is a chat model by OpenAI, available on Eden AI through 6 endpoints from 3 providers, from $1.25 per million input tokens and $10 per million output tokens, with a context window of up to 400K tokens.

Providers and prices

6 endpoints from 3 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 Azureazure/gpt-5
Global
272K
$1.25
$10
$0.125
Reasoning · Tools · JSON · Cache · Vision
Databricks (Europe)databricks/databricks-gpt-5@eu
Europe
272K
$1.25
$10
$0.125
Tools · Cache · Vision
Databricksdatabricks/databricks-gpt-5
Global
272K
$1.25
$10
$0.125
Tools · Cache · Vision
OpenAI (United States)openai/gpt-5
United States
400K
$1.25
$10
$0.125
Official · Reasoning · Tools · JSON · Cache · Vision · Web
Microsoft Azure (Europe)azure/gpt-5@eu
Europe
272K
$1.375
$11
$0.1375
Reasoning · Tools · JSON · Cache · Vision
Microsoft Azure (United States)azure/gpt-5@us
United States
272K
$1.375
$11
$0.1375
Reasoning · Tools · JSON · Cache · Vision

Performance

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

Fastest first token
0.56 s
Microsoft Azure (Europe)
Lowest latency
12.99 s
Microsoft Azure
Highest throughput
83.21 tok/s
Microsoft Azure (Europe)
Best availability
100%
Microsoft Azure (Europe)
Endpoint
First token
Latency p50
Latency p95
Throughput
Availability
Cache hits
Tool errors
JSON errors
Microsoft Azure
2.15 s
12.99 s
114.03 s
82.74 tok/s
100%
36.33%
0%
0%
Databricks (Europe)
23.69 s
22.07 s
80.91 s
67.62 tok/s
100%
0%
0%
0%
Databricks
23.44 s
20.56 s
78.56 s
67.38 tok/s
100%
0%
0%
0%
OpenAI (United States)
1.65 s
26.13 s
82.01 s
76.79 tok/s
100%
20.68%
0%
0%
Microsoft Azure (Europe)
0.56 s
13.75 s
134.33 s
83.21 tok/s
100%
36.44%
0%
0%

Estimate your monthly cost

Enter your expected volume to compare every endpoint at once.

Call GPT-5 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": "gpt-5",
        "messages": [{"role": "user", "content": "Hello!"}],
    },
)
print(response.json())

Questions about GPT-5

On Eden AI, prices for this model start at $1.25 per million input tokens and $10 per million output tokens. Prices differ by endpoint; the providers table lists each one.

Up to 400K tokens, depending on the endpoint.

6 endpoints from 3 providers, available in: Global, Europe, United States. All of them are called with the same Eden AI API key.

Can I run GPT-5 in the EU? 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. ‖ How fast is GPT-5? Over the last 30 days, the fastest first token was 0.56 s (Microsoft Azure (Europe)) and the highest throughput was 83.21 tokens per second (Microsoft Azure (Europe)).