GPT-5 Nano
Pricing & Specs

OpenAI · $0.05 input / $0.4 output per 1M tokens · 400K context window

$0.05
per 1M input tokens
$0.4
per 1M output tokens
400K
context window (tokens)

The per-token price never tells the full story. A typical task (1K input + 500 output tokens) on GPT-5 Nano costs about $0.0003 — roughly $0.25 per 1,000 runs. But if it needs 3x the tokens of a cheaper model to match quality on YOUR task, the economics flip. The only way to know is to benchmark it on your actual workload.

GPT-5 Nano API Pricing

TokensPrice
Input$0.05 / 1M tokens
Output$0.4 / 1M tokens
Cached input$0.005 / 1M tokens

Cached input tokens are billed when caching is enabled. Batch API pricing is available for this model at 50%.

What that means in practice

1x One typical task (1K input + 500 output tokens): $0.0003
1K 1,000 runs of that task: $0.25
💡 Real cost depends on how verbose the model is on YOUR prompts — benchmark to measure actual tokens, not estimates.

GPT-5 Nano Specs

SpecValue
Context window400K tokens
Max input per request272K tokens
Max output tokens128K tokens
Input modalitiestext, image
Output modalitiestext
Latency (measured by OpenMark)~1.9s median response
Reasoning modelYes
Tool / function callingYes
JSON modeYes
StreamingYes
Prompt cachingYes
Batch APIYes

Capabilities

text generation function calling structured outputs streaming

FAQ

How much does GPT-5 Nano cost?

GPT-5 Nano costs $0.05 per 1M input tokens and $0.4 per 1M output tokens ($0.005 per 1M cached input tokens).

What is GPT-5 Nano's context window?

GPT-5 Nano has a 400K-token context window. Maximum output is 128K tokens.

Can I test GPT-5 Nano on my own task?

Yes. OpenMark lets you benchmark GPT-5 Nano against 100+ models on your own task with real API calls — no API keys needed, free tier available.

Is GPT-5 Nano the right model for YOUR task?

Pricing tables can't answer that. Benchmark it against 100+ models
on your actual workload — real API calls, real costs. Free tier available.

Benchmark GPT-5 Nano — Free →