GPT-5 Nano

GPT-5 Nano is the smallest, fastest variant in OpenAI’s GPT-5 system, succeeding GPT-4.1 Nano. It is designed for developer tools and rapid, ultra-low-latency interactions, with less reasoning depth than larger counterparts while retaining instruction-following capabilities. This positioning makes it better suited to lightweight, high-throughput applications than to tasks requiring the deepest deliberation.

In practice, the model is a fit for cost-sensitive or real-time workflows that need quick, consistent outputs, including background processing, classification-style work, and developer-facing interactions. The supplied benchmark evidence describes measurable instruction-following and scientific-reasoning performance, but also shows substantial variation across difficult reasoning and coding evaluations, reinforcing its role as a compact efficiency model rather than a heavyweight problem solver.

OpenAIgpt-5-nanogpt-nano

Open provider page Provider docs

Quick Info

Provider: OpenAI
Model key: gpt-5-nano
Release date: Aug 7, 2025
Last updated: Aug 7, 2025
Knowledge cutoff: 2024-05-30
Input modalities
Output modalities
Capabilities

Cost

Input token cost: $0.05
Output token cost: $0.40

Limits

Input tokens: 272,000 tokens
Output tokens: 128,000 tokens
Context window: 400,000 tokens

OpenCode

Model variants

Flex

Input

$0.025

per 1M tokens

Output

$0.20

per 1M tokens

Cache Read

$0.0025

per 1M tokens

Transparent token rates

Compare GPT-5 Nano pricing

Rates are shown per one million tokens. Combined means one million input plus one million output tokens.

Browse this family

Latest news about GPT-5 Nano

Abacus

Coverage

Simon Willison's coverage of GPT-5 from preview access confirms the API exposes three variants—regular, mini, and nano—each runnable at minimal, low, medium, or high reasoning levels. Nano is described alongside mini as part of the unified, tiered API offering rather than a separate product. GPT-5 in the API supports 272K input tokens and 128K output tokens, with text and image input but text-only output, applying across all variants including nano. Once usage limits are reached in ChatGPT, a mini version handles remaining queries, framing nano's role in the fallback chain.

Abacus

CoverageBenchmark

GPT-5 Nano is OpenAI's smallest, fastest variant in the GPT-5 system, according to OpenRouter's listing, succeeding GPT-4.1-nano for cost-sensitive and real-time use. It was released on August 7, 2025 with a 400K context window and a knowledge cutoff of May 2024. List pricing is $0.05 per 1M input tokens and $0.40 per 1M output tokens, with Azure and OpenAI both reaching 100% uptime on the standard route. OpenRouter Flex pricing averages around $0.025 input and $0.20 output per 1M tokens with strong token-share throughput.

OpenAI

CoverageRelease Notes

Columbia University's CUIT release notes for its CHAT service list OpenAI GPT-5 nano among the currently available models in its model picker, alongside newer OpenAI variants such as GPT-5.2 (the default), GPT-5.4, GPT-5.5, and the GPT-5.6 Sol/Terra/Luna sub-versions, plus Anthropic Claude and Google Gemini counterpart The same notes show OpenAI iterating the GPT-5 line through 2026: GPT-5.4 became available to all users on July 23, 2026, while GPT-5.5, GPT-5.6 Sol, GPT-5.6 Terra, and GPT-5.6 Luna were rolled out to all users on August 14, 2026, with Anthropic and Gemini models arriving in parallel for select users. GPT-5 nano's pers