openai Vision Reasoning

GPT-5.4 Nano pricing & benchmarks

Released Mar 17, 2026 · served by 2 providers · ranked #34 by intelligence in our index

Input / 1M tokens$0.100
Output / 1M tokens$0.625
Context window400K
Cached input$0.020
Intelligence index38.2
Coding index56.1
Agentic index27.5
1M in + 300K out$0.29

What GPT-5.4 Nano is

GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency...

Providers and prices for GPT-5.4 Nano

The same model costs different amounts depending on who serves it. Prices are per 1M tokens, cheapest first. Uptime and throughput are OpenRouter's rolling measurements, not vendor claims.

ProviderInputOutputContext QuantUptime 24hThroughput
OpenAIcheapest $0.100 $0.625 400K 96.8%
Azure $0.200 $1.25 400K 100.0%

Cheaper models in the same class

Models scoring within 4 points of GPT-5.4 Nano on the Intelligence Index, but with a lower output price.

FAQ

How much does the GPT-5.4 Nano API cost?

$0.100 per 1M input tokens and $0.625 per 1M output tokens. A typical workload of 1M input + 300K output tokens costs about $0.29.

Is GPT-5.4 Nano free?

No. It is a paid model starting at $0.100 per 1M input tokens, though some providers offer trial credits.

Which provider is cheapest for GPT-5.4 Nano?

OpenAI at $0.100 input / $0.625 output per 1M tokens.

Can I self-host GPT-5.4 Nano?

No. GPT-5.4 Nano is closed-weight and only available through hosted APIs.