GPT-5.4 Nano

gpt-5.4-nano by OpenAI Released March 18, 2026

ReasoningFunction callingStructured outputPrompt cachingWeb searchComputer useImage inputFile inputAudio inputVideo inputEU hostingFree endpointUp to % off

Input from

$0.2 / 1M

Output from

$1.25 / 1M

Cached input from

$0.02 / 1M

Context window

400K

Endpoints

from 3 providers

Regions

Monde, Europe, États-Unis

About GPT-5.4 Nano

GPT-5.4 nano est la variante la plus légère et la plus économique de la gamme GPT-5.4, optimisée pour les tâches où la vitesse est essentielle et celles à haut volume.

GPT-5.4 Nano est un modèle conversationnel développé par OpenAI, disponible sur Eden AI via 5 endpoints chez 3 fournisseurs, à partir de 0,2 $ par million de tokens en entrée et 1,25 $ par million de tokens en sortie, avec une fenêtre de contexte allant jusqu'à 400K tokens.

Providers and prices

5 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-nano

Monde

272K

$0.2$0.2

$1.25

$0.02

ReasoningToolsJSONCacheVisionWeb

Databricks (Europe)Official−%databricks/databricks-gpt-5-4-nano@eu

Europe

272K

$0.2$0.2

$1.25

$0.02

ReasoningToolsJSONCacheVisionWeb

DatabricksOfficial−%databricks/databricks-gpt-5-4-nano

Monde

272K

$0.2$0.2

$1.25

$0.02

ReasoningToolsJSONCacheVisionWeb

OpenAI (États-Unis)Official−%openai/gpt-5.4-nano

États-Unis

400K

$0.2$0.2

$1.25

$0.02

ReasoningToolsJSONCacheVisionWeb

Microsoft Azure (États-Unis)Official−%azure/gpt-5.4-nano@us

États-Unis

272K

$0.22$0.22

$1.375

$0.022

ReasoningToolsJSONCacheVisionWeb

Performance

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

Fastest first token

0.52 s

Databricks (Europe)

Lowest latency

1.03 s

OpenAI (États-Unis)

Highest throughput

83.69 tok/s

Databricks (Europe)

Best availability

100%

Microsoft Azure

Endpoint

First token

Latency p50

Latency p95

Throughput

Availability

Cache hits

Tool errors

JSON errors

Microsoft Azure

0.76 s

1.27 s

17.93 s

36.93 tok/s

100%

70.63%

Databricks (Europe)

0.52 s

1.34 s

3.3 s

83.69 tok/s

99.99%

44.48%

0.42%

Databricks

0.52 s

1.34 s

3.32 s

83.67 tok/s

99.99%

44.47%

0.42%

OpenAI (États-Unis)

0.55 s

1.03 s

4.53 s

77.16 tok/s

100%

14.36%

Microsoft Azure (États-Unis)

tok/s

Estimate your monthly cost

Enter your expected volume to compare every endpoint at once.

Call GPT-5.4 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())

curl https://api.edenai.run/v3/chat/completions \
  -H "Authorization: Bearer YOUR_EDENAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "", "messages": [{"role": "user", "content": "Hello!"}]}'

const response = await fetch("https://api.edenai.run/v3/chat/completions", {
  method: "POST",
  headers: {
    Authorization: "Bearer YOUR_EDENAI_API_KEY",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "",
    messages: [{ role: "user", content: "Hello!" }],
  }),
});
console.log(await response.json());

Questions about GPT-5.4 Nano

How much does GPT-5.4 Nano cost?

On Eden AI, prices for this model start at $0.2 per million input tokens and $1.25 per million output tokens. Prices differ by endpoint; the providers table lists each one. .

What is the context window of GPT-5.4 Nano?

Up to 400K tokens, depending on the endpoint.

Which providers serve GPT-5.4 Nano?

5 endpoints from 3 providers, available in: Monde, Europe, États-Unis. All of them are called with the same Eden AI API key.

Can I run GPT-5.4 Nano 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-5.4 Nano?

Over the last 30 days, the fastest first token was 0.52 s (Databricks (Europe)) and the highest throughput was 83.69 tokens per second (Databricks (Europe)).

About GPT-5.4 Nano

Providers and prices

Performance

Estimate your monthly cost

Call GPT-5.4 Nano with Eden AI

Questions about GPT-5.4 Nano

More from OpenAI