OpenAI: GPT-5 Nano

OpenAI: GPT-5 Nano is a large language model from OpenAI. It costs $0.050 per million input tokens and $0.400 per million output tokens. Its context window is 400K tokens.

ReasoningTool callingStructured outputPrompt cachingBatch tierimage inputfile input

Input / 1M tokens: $0.050
Output / 1M tokens: $0.400
Cached input / 1M: $0.0050
Context window: 400K

This model also charges $0.01 per search request

That is $10.00 per 1,000 requests, billed on top of the token prices above. On a typical 1,000-in / 500-out exchange the tokens cost $0.0003, so the search fee is 40× the token cost. Per-token rankings elsewhere ignore this entirely.

Who serves it cheapest

2 hosts serve GPT-5 Nano. Same weights, same API - the price difference is pure margin and routing.

Providers serving OpenAI: GPT-5 Nano, cheapest first
Provider	Input / 1M	Output / 1M	Context	Throughput	Uptime 24h
OpenAICheapest	$0.025	$0.200	400K	-	100.0%
Azure	$0.050	$0.400	400K	-	100.0%

The spread between OpenAI and Azure is 2.0× for identical weights. Quantization and context limits differ, so check both columns before switching.

About GPT-5 Nano

GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger...

Specifications

OpenAI: GPT-5 Nano specifications
Model ID	`openai/gpt-5-nano`
Provider	OpenAI
Context window	400K tokens
Max output	128K tokens
Input modalities	text, image, file
Output modalities	text
Knowledge cutoff	2024-05-31
Open weights	No
Released	August 7, 2025

Cheaper alternatives

Models that cost less than GPT-5 Nano while keeping at least half its context window and every input modality it supports.

Muse Spark 1.3 Contributor

$0.100 in · $0.200 out

1.1× cheaper

Muse Spark 1.2 Contributor

$0.100 in · $0.200 out

1.1× cheaper

Auto Router (Beta)

$-1000000.0000 in · $-1000000.0000 out

about the same cheaper

Auto Router

$-1000000.0000 in · $-1000000.0000 out

about the same cheaper

Frequently asked

How much does OpenAI: GPT-5 Nano cost?

$0.050 per million input tokens and $0.400 per million output tokens. Cached input reads cost $0.0050 per million tokens.

What is the context window of OpenAI: GPT-5 Nano?

400K tokens, with up to 128K tokens of output per request.

Does OpenAI: GPT-5 Nano have extra fees beyond per-token pricing?

Yes. OpenAI: GPT-5 Nano charges $0.01 per search request - $10.00 per 1,000 requests - on top of $0.050 per million input tokens and $0.400 per million output tokens. On a typical 1,000-input / 500-output exchange the search fee alone is 40× the token cost.

Which provider serves OpenAI: GPT-5 Nano cheapest?

OpenAI at $0.025 per million input tokens - 2.0× cheaper than Azure, the most expensive of the 2 hosts serving it.

Confirm against the source: OpenAI official pricing.