GPT 5.4 pricing for customer support bot

Quick start

Call GPT 5.4 with the OpenAI Python SDK:

from openai import OpenAI

client = OpenAI()
response = client.chat.completions.create(
    model="gpt-5.4",
    max_tokens=1000,
    messages=[{"role": "user", "content": "Your prompt here"}]
)
# Cost: ~$0.0225 per call at standard rates
# Input:  $2.50/MTok
# Output: $15.00/MTok

How GPT 5.4 compares on cost

Per-call cost for all models scoring 50+ on customer support bot benchmarks. Hover for details.

Cheapest viable option: GPT 5.6 Luna at $0.001800/call (92% less, 85/100 quality).

What drives customer support bot cost

Support bots combine RAG's retrieved context with a chatbot's growing history, so they carry both cost curves at once. Volume is high and margins per conversation are thin, which makes the per-call rate matter more than in almost any other use case here. Caching the knowledge base and product context is the single highest-leverage change.

For GPT 5.4 specifically, that means output tokens cost 6.0x more than input, at $15.00 vs $2.50 per MTok. At this use case’s 3,000/1,000 token split, output accounts for 67% of the $0.0225 per-call cost.

GPT 5.4 quality benchmarks for customer support bot

Performance across all task types

GPT 5.4 scores by task type. Customer Support Bot highlighted.

Confidence scores are a third-party benchmark snapshot from week 29 of 2026. This snapshot is 8 weeks old, so treat the scores as directional and validate against your own evals.

About GPT 5.4

Other models from GPT

You can compare GPT 5.4 head-to-head against any other model on our model comparison pages, or track how pricing has changed over time on the pricing history tracker.

Frequently asked questions