GPT-5.4

gpt-5.4 by OpenAI Released March 6, 2026
ReasoningFunction callingStructured outputPrompt cachingWeb searchComputer useImage inputFile inputAudio inputVideo inputEU hostingFree endpointUp to % off
Input from
$2.5 / 1M
Output from
$15 / 1M
Cached input from
$0.25 / 1M
Context window
1.05M
Endpoints
8
from 4 providers
Regions
Global, Europe, United States

About GPT-5.4

GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system.

GPT-5.4 is a chat model by OpenAI, available on Eden AI through 8 endpoints from 4 providers, from $2.5 per million input tokens and $15 per million output tokens, with a context window of up to 1.05M tokens.

Providers and prices

8 endpoints from 4 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. Above 272K tokens: $5 input / $22.5 output per 1M.

Endpoint
Region
Context
Input / 1M
Output / 1M
Cached / 1M
Supports
Microsoft AzureOfficial−%azure/gpt-5.4
Global
922K
$2.5$2.5
$15
$0.25
ReasoningToolsJSONCacheVisionWeb
Databricks (Europe)Official−%databricks/databricks-gpt-5-4@eu
Europe
922K
$2.5$2.5
$15
$0.25
ReasoningToolsJSONCacheVisionWeb
DatabricksOfficial−%databricks/databricks-gpt-5-4
Global
922K
$2.5$2.5
$15
$0.25
ReasoningToolsJSONCacheVisionWeb
OpenAIOfficial−%openai/gpt-5.4
Global
1.05M
$2.5$2.5
$15
$0.25
ReasoningToolsJSONCacheVisionWeb
Amazon Web ServicesOfficial−%amazon/openai.gpt-5.4
Global
1M
$2.75$2.75
$16.5
$0.275
ReasoningToolsJSONCacheVisionWeb
Amazon Web Services (United States)Official−%amazon/openai.gpt-5.4@us
United States
1M
$2.75$2.75
$16.5
$0.275
ReasoningToolsJSONCacheVisionWeb
Microsoft Azure (Europe)Official−%azure/gpt-5.4@eu
Europe
922K
$2.75$2.75
$16.5
$0.275
ReasoningToolsJSONCacheVisionWeb
Microsoft Azure (United States)Official−%azure/gpt-5.4@us
United States
922K
$2.75$2.75
$16.5
$0.275
ReasoningToolsJSONCacheVisionWeb

Performance

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

Fastest first token
0.48 s
Microsoft Azure (Europe)
Lowest latency
1.23 s
Microsoft Azure (Europe)
Highest throughput
56.62 tok/s
Databricks (Europe)
Best availability
100%
Microsoft Azure (Europe)
Endpoint
First token
Latency p50
Latency p95
Throughput
Availability
Cache hits
Tool errors
JSON errors
Microsoft Azure
0.49 s
1.52 s
7.55 s
28 tok/s
99.99%
57.02%
4.78%
0%
Databricks (Europe)
0.72 s
2.72 s
65.03 s
56.62 tok/s
100%
61.29%
0%
0%
Databricks
0.72 s
2.74 s
65.03 s
56.62 tok/s
100%
61.3%
0%
0%
OpenAI
0.97 s
1.97 s
25.31 s
32.05 tok/s
99.99%
73.45%
0.08%
0%
Amazon Web Services
s
s
s
tok/s
%
%
%
%
Amazon Web Services (United States)
s
s
s
tok/s
%
%
%
%
Microsoft Azure (Europe)
0.48 s
1.23 s
12.52 s
41.72 tok/s
100%
64.85%
5.17%
0%
Microsoft Azure (United States)
s
s
s
tok/s
%
%
%
%

Estimate your monthly cost

Enter your expected volume to compare every endpoint at once.

Call GPT-5.4 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-5.4

On Eden AI, prices for this model start at $2.5 per million input tokens and $15 per million output tokens. Prices differ by endpoint; the providers table lists each one. Above 272K tokens: $5 input / $22.5 output per 1M.

Up to 1.05M tokens, depending on the endpoint.

8 endpoints from 4 providers, available in: Global, Europe, United States. 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 0.48 s (Microsoft Azure (Europe)) and the highest throughput was 56.62 tokens per second (Databricks (Europe)).