o3 pricing for security review

Quick start

Call o3 with the OpenAI Python SDK:

from openai import OpenAI

client = OpenAI()
response = client.chat.completions.create(
    model="o3",
    max_tokens=2500,
    messages=[{"role": "user", "content": "Your prompt here"}]
)
# Cost: ~$0.0320 per call at standard rates
# Input:  $2.00/MTok
# Output: $8.00/MTok

How o3 compares on cost

Per-call cost for all models scoring 50+ on security review benchmarks. Hover for details.

Cheapest viable option: Claude Sonnet 5 at $0.0370/call (-16% less, 96/100 quality).

What drives security review cost

Security review is the code task where quality is worth paying for: a missed vulnerability costs more than the entire year's inference bill. Input is large (the code plus the threat context) and output is moderate. This is the clearest case on this list for choosing a top-ranked model over the cheapest viable one, and for not batching away the latency you need in CI.

For o3 specifically, that means output tokens cost 4.0x more than input, at $8.00 vs $2.00 per MTok. At this use case’s 6,000/2,500 token split, output accounts for 63% of the $0.0320 per-call cost.

o3 quality benchmarks for security review

Benchmark data for security review is pending for o3. Test against your own evaluation suite before moving to production.

Performance across all task types

o3 scores by task type. Security Review 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 o3

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 o3 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