GPT-5.4 Mini

gpt-5.4-mini by OpenAI Released March 18, 2026
ReasoningFunction callingStructured outputPrompt cachingWeb searchComputer useImage inputFile inputAudio inputVideo inputEU hostingFree endpointUp to % off
Input from
$0.75 / 1M
Output from
$4.5 / 1M
Cached input from
$0.075 / 1M
Context window
400K
Endpoints
6
from 3 providers
Regions
Monde, Europe, États-Unis

About GPT-5.4 Mini

GPT-5.4 mini intègre les fonctionnalités essentielles de GPT-5.4 dans un modèle plus rapide et plus efficace, optimisé pour les charges de travail à haut débit.

GPT-5.4 Mini est un modèle conversationnel développé par OpenAI, disponible sur Eden AI via 6 endpoints chez 3 fournisseurs, à partir de 0,75 $ par million de tokens en entrée et 4,5 $ par million de tokens en sortie, avec une fenêtre de contexte allant jusqu'à 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 AzureOfficial−%azure/gpt-5.4-mini
Monde
272K
$0.75$0.75
$4.5
$0.075
ReasoningToolsJSONCacheVisionWeb
Databricks (Europe)Official−%databricks/databricks-gpt-5-4-mini@eu
Europe
272K
$0.75$0.75
$4.5
$0.075
ReasoningToolsJSONCacheVisionWeb
DatabricksOfficial−%databricks/databricks-gpt-5-4-mini
Monde
272K
$0.75$0.75
$4.5
$0.075
ReasoningToolsJSONCacheVisionWeb
OpenAI (États-Unis)Official−%openai/gpt-5.4-mini
États-Unis
400K
$0.75$0.75
$4.5
$0.075
ReasoningToolsJSONCacheVisionWeb
Microsoft Azure (Europe)Official−%azure/gpt-5.4-mini@eu
Europe
272K
$0.825$0.825
$4.95
$0.0825
ReasoningToolsJSONCacheVisionWeb
Microsoft Azure (États-Unis)Official−%azure/gpt-5.4-mini@us
États-Unis
272K
$0.825$0.825
$4.95
$0.0825
ReasoningToolsJSONCacheVisionWeb

Performance

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

Fastest first token
0.46 s
Databricks (Europe)
Lowest latency
1.05 s
Databricks (Europe)
Highest throughput
97.32 tok/s
Databricks (Europe)
Best availability
100%
Databricks (Europe)
Endpoint
First token
Latency p50
Latency p95
Throughput
Availability
Cache hits
Tool errors
JSON errors
Microsoft Azure
0.75 s
1.29 s
12.4 s
73.46 tok/s
98.56%
64.05%
6.06%
24.11%
Databricks (Europe)
0.46 s
1.05 s
2.07 s
97.32 tok/s
100%
68.81%
8.47%
0%
Databricks
0.46 s
1.05 s
2.07 s
97.32 tok/s
100%
68.81%
11.48%
0%
OpenAI (États-Unis)
0.91 s
2.03 s
17.92 s
66.03 tok/s
100%
3.8%
3.66%
0.55%
Microsoft Azure (Europe)
0.76 s
1.27 s
12.81 s
73.19 tok/s
98.5%
64.25%
6.08%
24.11%
Microsoft Azure (États-Unis)
s
s
s
tok/s
%
%
%
%

Estimate your monthly cost

Enter your expected volume to compare every endpoint at once.

Call GPT-5.4 Mini 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 Mini

On Eden AI, prices for this model start at $0.75 per million input tokens and $4.5 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: Monde, Europe, 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 0.46 s (Databricks (Europe)) and the highest throughput was 97.32 tokens per second (Databricks (Europe)).