GPT-5 Nano

gpt-5-nano by OpenAI Released August 8, 2025
ReasoningFunction callingStructured outputPrompt cachingWeb searchComputer useImage inputFile inputAudio inputVideo inputEU hostingFree endpointUp to % off
Input from
$0.05 / 1M
Output from
$0.4 / 1M
Cached input from
$0.005 / 1M
Context window
400K
Endpoints
6
from 3 providers
Regions
Global, Europe, United States

About GPT-5 Nano

GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments.

GPT-5 Nano is a chat model by OpenAI, available on Eden AI through 6 endpoints from 3 providers, from $0.05 per million input tokens and $0.4 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-nano
Global
272K
$0.05$0.05
$0.4
$0.005
ReasoningToolsJSONCacheVisionWeb
Databricks (Europe)Official−%databricks/databricks-gpt-5-nano@eu
Europe
272K
$0.05$0.05
$0.4
$0.005
ReasoningToolsJSONCacheVisionWeb
DatabricksOfficial−%databricks/databricks-gpt-5-nano
Global
272K
$0.05$0.05
$0.4
$0.005
ReasoningToolsJSONCacheVisionWeb
OpenAIOfficial−%openai/gpt-5-nano
Global
400K
$0.05$0.05
$0.4
$0.005
ReasoningToolsJSONCacheVisionWeb
Microsoft Azure (Europe)Official−%azure/gpt-5-nano@eu
Europe
272K
$0.055$0.055
$0.44
$0.0055
ReasoningToolsJSONCacheVisionWeb
Microsoft Azure (United States)Official−%azure/gpt-5-nano@us
United States
272K
$0.055$0.055
$0.44
$0.0055
ReasoningToolsJSONCacheVisionWeb

Performance

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

Fastest first token
0.58 s
Databricks (Europe)
Lowest latency
0.72 s
OpenAI
Highest throughput
118.04 tok/s
Microsoft Azure (Europe)
Best availability
100%
Databricks (Europe)
Endpoint
First token
Latency p50
Latency p95
Throughput
Availability
Cache hits
Tool errors
JSON errors
Microsoft Azure
7.77 s
5.57 s
21.67 s
117.49 tok/s
99.66%
22.89%
0%
1.04%
Databricks (Europe)
0.58 s
1.05 s
9.44 s
62.11 tok/s
100%
50.12%
0%
0%
Databricks
0.58 s
1.06 s
9.44 s
62.11 tok/s
100%
49.87%
0%
0%
OpenAI
1.53 s
0.72 s
4.43 s
34.12 tok/s
100%
0.54%
0%
0.03%
Microsoft Azure (Europe)
8.52 s
5.73 s
21.58 s
118.04 tok/s
99.63%
23.29%
0%
1.06%
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 Nano 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 Nano

On Eden AI, prices for this model start at $0.05 per million input tokens and $0.4 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 0.58 s (Databricks (Europe)) and the highest throughput was 118.04 tokens per second (Microsoft Azure (Europe)).