LLM·Dex
Newsletter
ProprietaryOpenAIsmalltextvision

GPT-5 nano

OpenAI's smallest GPT-5 variant, built for ultra-low-cost classification, routing, and high-volume inference.

Updated

Quick facts

Released
Aug 2025
Context
400K tokens
Output / 1M
$0.40 / 1M tokens
License
Proprietary

About GPT-5 nano

GPT-5 nano targets the same niche that text-embedding and tiny chat models compete in: blazing-fast, ultra-cheap inference for classification, routing, and small-decision agent steps.

It's not a chat model in the conventional sense, quality on creative tasks lags noticeably behind mini and full. But for a router that picks one of five paths, or an extractor that pulls a known field, nano is often the right answer at a tenth the cost.

The nano tier is most often used as the inner step inside larger agent pipelines where the outer steps run on more capable models.

Benchmarks

Published scores from OpenAI's model card or independent leaderboards. We do not publish numbers we cannot source, see methodology.

HumanEval
,
Python coding pass@1
MMLU
,
Broad academic knowledge
GPQA
,
Graduate-level reasoning
SWE-bench
,
Real software-engineering tasks
Benchmark scores not yet available. We only publish numbers we can source from official model cards or independent leaderboards, see methodology.

Capabilities

Strengths

  • Lowest-cost OpenAI model with vision support
  • Fast P99 latency
  • Good enough for routing and classification

Tracked weaknesses

  • Visible quality gap on open-ended tasks
  • Limited reasoning capability

Pricing

Per-million-token rates as published by OpenAI.

TierPriceNotes
Input$0.050 / 1M tokensTokens you send to the model
Output$0.40 / 1M tokensTokens the model generates
Context400K tokensMax combined input + output

Call GPT-5 nano from your code

Drop-in snippet for the OpenAI SDK. Set your API key in the environment and run.

typescript
import OpenAI from "openai";

const client = new OpenAI({
  // Use OPENAI_API_KEY for OpenAI, or your provider's key + baseURL.
  apiKey: process.env.OPENAI_API_KEY,
});

const completion = await client.chat.completions.create({
  model: "gpt-5-nano",
  messages: [
    { role: "user", content: "What's the time complexity of quicksort?" },
  ],
});

console.log(completion.choices[0].message.content);

Best for

Tasks where GPT-5 nano ranks among LLMDex's top picks.

Compare GPT-5 nano with…

Frequently asked

  • How much does GPT-5 nano cost per million tokens?
    GPT-5 nano is priced at $0.050 / 1M tokens for input tokens and $0.40 / 1M tokens for output tokens via the official OpenAI API at the time of writing.
  • What is GPT-5 nano's context window?
    GPT-5 nano supports a context window of 400K tokens with up to 128K output tokens per response.
  • Is GPT-5 nano open source?
    No. GPT-5 nano is a closed-weight model, you can use it via OpenAI's API but the model weights are not publicly downloadable.
  • When was GPT-5 nano released?
    GPT-5 nano was released on Aug 7, 2025 by OpenAI.
  • What is GPT-5 nano's knowledge cutoff?
    GPT-5 nano's training data has a knowledge cutoff of Sep 2024. For information after that date you'll need a tool-use or web-search wrapper.
Friday digest

Intelligence, distilled weekly.

One short email every Friday, new model launches, leaderboard moves, and pricing drops. Curated by hand. Free, no spam.