How much does GPT-5 Nano (batch) cost?

$0.025 per million input tokens and $0.20 per million output tokens; cached input costs $0.0025 per million. Prices as of Oct 21, 2026.

What is the context window of GPT-5 Nano (batch)?

400K tokens, with up to 128K output tokens per response.

Images as input: yes. Tool calling: yes. Structured (JSON) output: yes. Reasoning mode: yes.

Models with the same key capabilities for at least 20% less include Qwen3.7 Flash ($0.03 / $0.13).

OpenAI

$0.025 per 1M input tokens and $0.20 per 1M output tokens · 400K context · vision, tools, reasoning, JSON.

Prices checked Oct 21, 2026 · tracked by LLM Cost Index since Oct 21, 2026

$0.025

input / 1M tokens

$0.20

output / 1M tokens

$0.0025

cached input / 1M

400K

context window

128K

max output

Artificial Analysis intelligence index

Estimated monthly bill for typical workloads, using the cached-input price for repeated context. Try your own numbers in the cost calculator.

Workload	Per month
Customer chatbot 1,000 conversations a day, 8 turns each	$20.94
Document Q&A (RAG) 500 questions a day over retrieved documents	$3.55
Coding / tool-using agent 200 tasks a day, long tool-heavy contexts	$7.73
Content generation 30 long articles a day	$0.518
Classification / extraction 100,000 short items a day	$31.50

We started tracking GPT-5 Nano (batch) on Oct 21, 2026; the chart appears as soon as there is a second data point. See all recent price changes.

Models with the same tool calling, image input, structured output for at least 20% less (3:1 input/output mix), most capable first.

Cheaper alternatives to GPT-5 Nano (batch)
Model	Input / 1M	Output / 1M	Context	Capabilities
Qwen3.7 Flash Qwen	$0.03	$0.13	1M	visiontoolsreasoningJSON

For a customer chatbot (1,000 conversations a day, 8 turns each) that costs $25.80 a month at list price without caching:

Option	Per month	You save
Move to Qwen3.7 Flash (similar capabilities)	$16.54	$9.26 (36%)
Use prompt caching (60% of input cached)	$20.94	$4.86 (19%)

How much does GPT-5 Nano (batch) cost?: $0.025 per million input tokens and $0.20 per million output tokens; cached input costs $0.0025 per million. Prices as of Oct 21, 2026.
What is the context window of GPT-5 Nano (batch)?: 400K tokens, with up to 128K output tokens per response.
Does GPT-5 Nano (batch) support images, tools and structured output?: Images as input: yes. Tool calling: yes. Structured (JSON) output: yes. Reasoning mode: yes.
What are cheaper alternatives to GPT-5 Nano (batch)?: Models with the same key capabilities for at least 20% less include Qwen3.7 Flash ($0.03 / $0.13).