GPT-5 Nano

The fastest and lowest-cost tier of the GPT-5 family, built for high-volume, low-latency tasks such as summarization and classification.

Context: 400K tokens
Max output: 128K
Cutoff: May 2024
Released: Aug 2025

Visit OpenAI Compare vs other LLMs →

Hosted API price

List price via OpenAI · per 1M tokens

USD

Input: $0.05 /1M
Output: $0.40 /1M
Hosted by: 4 providers

Hosted API pricing

How we price

Order

Providers are listed cheapest input rate first, then by output rate, a tie going to the creator's own listing. A provider that lists the model without a published rate sits at the end.

Prices

Base-tier, on-demand rates in USD per 1M tokens, converted at ECB reference rates where a provider publishes in another currency. Cached-input and batch rates show only where a provider publishes them. "Cheapest" marks the one provider with the lowest input and output pair; a tie wears no badge.

Cost

Input rate times the input tokens plus output rate times the output tokens, at the monthly volume set above the table. Cached-input, batch, long-context and reasoning-token billing are not modelled.

Transparency and funding

Affiliates: Affiliate links are marked. We may earn a commission if you click them, but commissions never affect the order.

Every provider serving GPT-5 Nano, cheapest input first. Set your monthly volume to see what each would bill.

Input M Output M

Every provider serving GPT-5 Nano, with its price per 1M input and output tokens and what the volume above would cost
Provider	Input /1M	Output /1M	Cached input /1M	Cost at 10M in + 2M out	Link
OpenAI Creator	$0.05	$0.40	$0.005	$1.30	Visit website
DigitalOcean	$0.05	$0.40	$0.005	$1.30	Visit website
Azure	$0.05	$0.40	$0.005	$1.30	Visit website
Replicate	$0.05	$0.40		$1.30	Visit website

Heads up: Base-tier, on-demand rates per 1M tokens; cached, batch and long-context tiers excluded. A provider may serve a shorter context or a quantized build than the creator's release. Verify before provisioning. More on how we price.

Similarly priced models

The models nearest GPT-5 Nano by blended rate, each at its own cheapest provider.

Models priced nearest GPT-5 Nano per 1M tokens, each at its cheapest provider
Model	Blended /1M	Input /1M	Output /1M	Context	Cutoff	vs GPT-5 Nano
Qwen3-Coder-30B-A3B Alibaba Cloud	$0.0917	$0.06	$0.25	262K		−15%
Llama 3.2 3B Meta	$0.0983	$0.051	$0.335	128K	Dec 2023	−9%
Qwen3-30B-A3B FP8 Alibaba Cloud	$0.0983	$0.051	$0.335	33K		−9%
Ministral 3 3B Mistral	$0.10	$0.10	$0.10	256K		−8%
GLM-5.3-Flash Z.AI	$0.1042	$0.075	$0.25	1M		−4%
GPT-5 Nano This model OpenAI	$0.1083	$0.05	$0.40	400K	May 2024
Qwen3.5-35B-A3B Alibaba Cloud	$0.124	$0.057	$0.459	262K		+14%
Qwen3.6-35B-A3B Alibaba Cloud	$0.1283	$0.07	$0.42	262K		+18%
Gemma 3 27B Instruct Google Cloud	$0.1333	$0.10	$0.30	128K	Aug 2024	+23%
Gemma 4 26B A4B Google Cloud	$0.1333	$0.10	$0.30	256K	Jan 2025	+23%
Qwen3-32B FP8 Alibaba Cloud	$0.1333	$0.10	$0.30	33K		+23%

USD per 1M tokens at each model's cheapest listed provider. Blended is the cost of 10M input plus 2M output tokens, spread over the 12M.

Salad

Access 60,000+ daily active GPUs across 191 countries, from $0.02/hour

Run RTX 50-series and 40-series cards without datacenter pricing

Pick a priority level to balance cost against interruptions

Per-second billing, with no charge for cold starts or image pulls

View Pricing

Capabilities

What GPT-5 Nano accepts and can do, as published by OpenAI.

Image Accepts images as input alongside text.
Text Accepts and generates natural-language text.
Reasoning Thinks before it answers, always on or as a switchable mode.
Function calling Connect to external tools, APIs, and systems.
Structured output Return responses in structured formats like JSON.
Web search Search the web for up-to-date information.
Code execution Write and execute code in a sandboxed environment.
File upload Process uploaded documents, spreadsheets, and other files.
MCP Connect to services via Model Context Protocol.
Image generation Generate and edit images from text prompts.

Common questions

What is GPT-5 Nano good for?

Summarization, classification and other high-volume tasks, at the lower-cost end of OpenAI's lineup.

When is GPT-5 Nano not a good fit?

Open-ended reasoning or agent work, which suit the larger GPT-5 tiers, and audio input, which it lacks. OpenAI recommends GPT-5.6 Luna for new speed- and cost-sensitive work and plans to shut down the API model in December 2026.

What is the cheapest way to run GPT-5 Nano?

The cheapest hosted rate is $0.05 / $0.40 per 1M tokens via OpenAI.

How does GPT-5 Nano compare with GPT-5.4 Nano?

OpenAI says GPT-5.4 Nano brings GPT-5.4-class ability to its smallest tier, aimed at classification, data extraction, ranking and coding subagents where GPT-5 Nano was pitched at summarization and classification, and adds context compaction. Same 400K-token context and text and image input. GPT-5 Nano lists at 75% less per 1M input tokens and 68% less per 1M output tokens than GPT-5.4 Nano. It came out 7 months earlier and has an older knowledge cutoff (May 2024 against August 2025).

Can I self-host GPT-5 Nano?

No. OpenAI does not publish the weights; GPT-5 Nano is available only through hosted APIs.