GPT-5 Mini

gpt-5-mini by OpenAI Released August 8, 2025
ReasoningFunction callingStructured outputPrompt cachingWeb searchComputer useImage inputFile inputAudio inputVideo inputEU hostingFree endpointUp to % off
Input from
$0.25 / 1M
Output from
$2 / 1M
Cached input from
$0.025 / 1M
Context window
400K
Endpoints
6
from 3 providers
Regions
Global, Europe, United States

About GPT-5 Mini

GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks.

GPT-5 Mini is a chat model by OpenAI, available on Eden AI through 6 endpoints from 3 providers, from $0.25 per million input tokens and $2 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 AzureOfficial−%azure/gpt-5-mini
Global
272K
$0.25$0.25
$2
$0.025
ReasoningToolsJSONCacheVisionWeb
Databricks (Europe)Official−%databricks/databricks-gpt-5-mini@eu
Europe
272K
$0.25$0.25
$2
$0.025
ReasoningToolsJSONCacheVisionWeb
DatabricksOfficial−%databricks/databricks-gpt-5-mini
Global
272K
$0.25$0.25
$2
$0.025
ReasoningToolsJSONCacheVisionWeb
OpenAIOfficial−%openai/gpt-5-mini
Global
400K
$0.25$0.25
$2
$0.025
ReasoningToolsJSONCacheVisionWeb
Microsoft Azure (Europe)Official−%azure/gpt-5-mini@eu
Europe
272K
$0.275$0.275
$2.2
$0.0275
ReasoningToolsJSONCacheVisionWeb
Microsoft Azure (United States)Official−%azure/gpt-5-mini@us
United States
272K
$0.275$0.275
$2.2
$0.0275
ReasoningToolsJSONCacheVisionWeb

Performance

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

Fastest first token
2.63 s
Microsoft Azure
Lowest latency
6.58 s
OpenAI
Highest throughput
117.3 tok/s
Microsoft Azure
Best availability
100%
Microsoft Azure (Europe)
Endpoint
First token
Latency p50
Latency p95
Throughput
Availability
Cache hits
Tool errors
JSON errors
Microsoft Azure
2.63 s
8.14 s
16.86 s
117.3 tok/s
100%
46.24%
1.23%
0.52%
Databricks (Europe)
s
s
s
tok/s
%
%
%
%
Databricks
s
s
s
tok/s
%
%
%
%
OpenAI
4.37 s
6.58 s
22 s
79.32 tok/s
100%
22.28%
0%
0%
Microsoft Azure (Europe)
2.69 s
8.08 s
16.58 s
117.15 tok/s
100%
46.66%
1.25%
0.52%
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 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 Mini

On Eden AI, prices for this model start at $0.25 per million input tokens and $2 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.

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 2.63 s (Microsoft Azure) and the highest throughput was 117.3 tokens per second (Microsoft Azure).