GPT-5.4 Nano

OpenAI's smallest, cheapest GPT-5.4 variant. Optimized for classification, data extraction, ranking, and coding subagents where speed and cost matter most.

Input price: $0.18list $0.20-10%
Output price: $1.125list $1.25-10%

Context: 400K
Max output: 128K

Capability: 146 (#63 of 79)
Human preference: 1372
30-day uptime: —

Released: 2026-03-17
Knowledge cutoff: 2025-08

InputTextImageOutputText

Providers

This model is served by the dedicated providers below. We pick the provider for each request, so provider preferences don’t apply, including a provider named in your request. Prices in USD per 1M tokens. Need a custom setup? Contact [email protected].

DedicatedInput$0.18-10%Output$1.125-10%Cache read$0.018-10%Context400KMax output128KThis model is served by a dedicated set of providers. We pick the provider for each request, and you pay the same price whichever one serves it.

Included providers2

SuccessTTFT
Azure AI FoundryGlobal——
OpenAIUnited States——

Pricing

Prices for this model. Each request is billed at these prices, whichever provider serves it.

Item	Standard	Batch	Price
Inputper 1M tokens	$0.18list $0.20-10%	$0.09list $0.10-10%	—
Outputper 1M tokens	$1.125list $1.25-10%	$0.5625list $0.625-10%	—
Cache readper 1M tokens	$0.018list $0.02-10%	$0.009list $0.01-10%	—
Web searchper request	—	—	$0.009list $0.01-10%

Try it

Runs on your balance and is billed like any API request.

curl https://api.ohmygpt.com/v1/chat/completions \
  -H "Authorization: Bearer $OHMYGPT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-5.4-nano",
    "messages": [
      {
        "role": "user",
        "content": "Hello"
      }
    ]
  }'

import os

from openai import OpenAI

client = OpenAI(
    api_key=os.environ["OHMYGPT_API_KEY"],
    base_url="https://api.ohmygpt.com/v1",
)

response = client.chat.completions.create(
    model="openai/gpt-5.4-nano",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.OHMYGPT_API_KEY,
  baseURL: "https://api.ohmygpt.com/v1",
});

const response = await client.chat.completions.create({
  model: "openai/gpt-5.4-nano",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(response.choices[0].message.content);

The answer streams in here.

Billed by usage

Similar models

Other models with the same output types at a similar price.

Better value: more capable, lower price
Pareto frontier
This model
Similar models

Capability scores are from Epoch AI’s Epoch Capabilities Index (CC BY 4.0, as of 2026-11-10), which combines dozens of benchmarks with GPT-5 set at 150. epoch.ai/eci

Price: our current input price per 1M tokens in USD, lowest across channels. Dated snapshots and resold copies of the same model are merged into one point; free models are not shown.

Shaded area: capability above and price below the median of all models. Pareto frontier: no other model is both cheaper and more capable.

GPT-5.4 NanoThis model

Capability: 146
Input: $0.18
Output: $1.125

GPT-5.6 Luna

Capability: 157
Input: $0.18–$0.36
Output: $1.08–$1.62

NVIDIA Nemotron 3.5 Super VL

Capability: —
Input: $0.165
Output: $0.55

Mistral Small

Capability: —
Input: $0.165
Output: $0.66

Qwen3 Coder 30B A3B Instruct

Capability: —
Input: $0.165
Output: $0.66

Human preference ratings are from the LMArena Text Arena (CC BY 4.0, as of 2026-11-09): Elo ratings from blind votes, on a different scale from capability scores. lmarena.ai/leaderboard/text