OpenAI

GPT 5.4 Nano

Name: GPT 5.4 Nano
Brand: OpenAI
Price: 0.2 USD
Availability: InStock

GPT 5.4 Nano is a reasoning model by OpenAI with vision, function calling, web search, prompt caching, structured output — designed for complex, multi-step problem solving where accuracy matters more than speed. It supports a 272K token context window with up to 128K tokens of output. Priced at $0.2 per million input tokens and $1.25 per million output tokens, it is one of the most cost-efficient options in its class. Access GPT 5.4 Nano through Inworld Router with OpenAI SDK compatibility, built-in failover, and intelligent routing across providers.

→Function CallingWeb SearchReasoningPrompt CachingResponse SchemaVisionreasoningCapability

Use This Model

Step 1 — Create Router

curl --location 'https://api.inworld.ai/router/v1/routers' \
--header 'Authorization: Basic <your-api-key>' \
--header 'Content-Type: application/json' \
--data '{
  "name": "compare-frontier-models",
  "defaultRoute": {
    "route_id": "default",
    "variants": [
      {
        "variant": {
          "variant_id": "openai/gpt-5.4-nano-a",
          "model_id": "openai/gpt-5.4-nano"
        },
        "weight": 33
      },
      {
        "variant": {
          "variant_id": "openai/gpt-3.5-turbo-b",
          "model_id": "openai/gpt-3.5-turbo"
        },
        "weight": 33
      },
      {
        "variant": {
          "variant_id": "openai/gpt-4.1-c",
          "model_id": "openai/gpt-4.1"
        },
        "weight": 34
      }
    ]
  }
}'

import requests

response = requests.post(
    "https://api.inworld.ai/router/v1/routers",
    headers={
        "Authorization": "Basic <your-api-key>",
        "Content-Type": "application/json",
    },
    json={
        "name": "compare-frontier-models",
        "defaultRoute": {
            "route_id": "default",
            "variants": [
                {
                    "variant": {
                        "variant_id": "openai/gpt-5.4-nano-a",
                        "model_id": "openai/gpt-5.4-nano"
                    },
                    "weight": 33
                },
                {
                    "variant": {
                        "variant_id": "openai/gpt-3.5-turbo-b",
                        "model_id": "openai/gpt-3.5-turbo"
                    },
                    "weight": 33
                },
                {
                    "variant": {
                        "variant_id": "openai/gpt-4.1-c",
                        "model_id": "openai/gpt-4.1"
                    },
                    "weight": 34
                }
            ]
        }
    },
)
print(response.json())

const response = await fetch(
  "https://api.inworld.ai/router/v1/routers",
  {
    method: "POST",
    headers: {
      Authorization: "Basic <your-api-key>",
      "Content-Type": "application/json",
    },
    body: JSON.stringify({
      name: "compare-frontier-models",
      defaultRoute: {
        route_id: "default",
        variants: [
          {
            variant: {
              variant_id: "openai/gpt-5.4-nano-a",
              model_id: "openai/gpt-5.4-nano",
            },
            weight: 33,
          },
          {
            variant: {
              variant_id: "openai/gpt-3.5-turbo-b",
              model_id: "openai/gpt-3.5-turbo",
            },
            weight: 33,
          },
          {
            variant: {
              variant_id: "openai/gpt-4.1-c",
              model_id: "openai/gpt-4.1",
            },
            weight: 34,
          },
        ],
      },
    }),
  }
);
const data = await response.json();
console.log(data);

Step 2 — Chat Completion

curl --location 'https://api.inworld.ai/v1/chat/completions' \
--header 'Authorization: Basic <your-api-key>' \
--header 'Content-Type: application/json' \
--data '{
  "model": "inworld/compare-frontier-models",
  "messages": [{"role": "user", "content": "Hello!"}]
}'

GPT 5.4 Nano pricing and providers

Access GPT 5.4 Nano through OpenAI via Inworld Router or Realtime API. By using the AI provider(s) below you acknowledge you reviewed and agree to their terms listed in the Legal section under the AI provider's name.

					Capabilities	Input modalities	Output modalities
OpenAI	272K	128K	$0.20	$1.25	+4

Other OpenAI models available through Inworld

Compare GPT 5.4 Nano with other OpenAI models available through Inworld Router or Realtime API.

					Capabilities
GPT 3.5 Turbo	16.4K	4.1K	$0.50	$1.50
GPT 4.1	1M	32.8K	$2.00	$8.00	+2
GPT 4.1 Mini	1M	32.8K	$0.40	$1.60	+2
GPT 4.1 Nano	1M	32.8K	$0.10	$0.40	+1
GPT 4.1 Nano 2025 04 14	1M	32.8K	$0.10	$0.40	+1
GPT 4o	128K	16.4K	$2.50	$10.00	+1
GPT 4o 2024 08 06	128K	16.4K	$2.50	$10.00	+1
GPT 4o Mini	128K	16.4K	$0.15	$0.60	+1
GPT 4o Mini 2024 07 18	128K	16.4K	$0.15	$0.60	+1
GPT 4o Mini Audio Preview	—	—	$0.15	$0.60	—
GPT 5 Mini	272K	128K	$0.25	$2.00	+4
GPT 5 Nano	272K	128K	$0.05	$0.40	+4
GPT 5.2	272K	128K	$1.75	$14.00	+4
GPT 5.4	1.1M	128K	$2.50	$15.00	+3
GPT 5.4 Mini	272K	128K	$0.75	$4.50	+4
GPT 5.5	1.1M	128K	$5.00	$30.00	+4
GPT Audio Mini	128K	16.4K	$0.60	$2.40
Openai/gpt Oss 120b	131.1K	131.1K	$0.039	$0.19	+2
Openai/gpt Oss 120b Turbo	—	—	$0.15	$0.60	—
Openai/gpt Oss 20b	131.1K	32.8K	$0.075	$0.30	+2
Openai/gpt Oss Safeguard 20b	131.1K	65.5K	$0.075	$0.30	+2

View all models

Start building with GPT 5.4 Nano

Access GPT 5.4 Nano and every other model through Inworld Router or Realtime API. Create your free account and start routing in minutes.

Get Started Free Contact Sales