GPT 5 pricing for intent detection

Quick start

Call GPT 5 with the OpenAI Python SDK:

from openai import OpenAI

client = OpenAI()
response = client.chat.completions.create(
    model="gpt-5",
    max_tokens=100,
    messages=[{"role": "user", "content": "Your prompt here"}]
)
# Cost: ~$0.001375 per call at standard rates
# Input:  $1.25/MTok
# Output: $10.00/MTok

How GPT 5 compares on cost

Per-call cost for all models scoring 50+ on intent detection benchmarks. Hover for details.

Cheapest viable option: GPT 5.6 Luna at $0.000180/call (87% less, 91/100 quality).

What drives intent detection cost

Intent classification sits in the hot path of a conversational product, so latency constrains model choice more than price does: batch processing is not available to you when the user is waiting. That makes the fast tier the natural fit on both axes. The intent list is constant and belongs in the cached prefix.

For GPT 5 specifically, that means output tokens cost 8.0x more than input, at $10.00 vs $1.25 per MTok. At this use case’s 300/100 token split, output accounts for 73% of the $0.001375 per-call cost.

GPT 5 quality benchmarks for intent detection

Benchmark data for intent detection is pending for GPT 5. Test against your own evaluation suite before moving to production.

Performance across all task types

GPT 5 scores by task type. Intent Detection highlighted.

Confidence scores are a third-party benchmark snapshot from week 29 of 2026. This snapshot is 10 weeks old, so treat the scores as directional and validate against your own evals.

About GPT 5

Backfilled on 2026-09-23. Prices confirmed by the provider pricing page and the LiteLLM cross-check. Release date not published in a machine-readable source. Not yet benchmarked, so never recommended.

Other models from GPT

You can compare GPT 5 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