o3 pricing for document summarization

Quick start

Call o3 with the OpenAI Python SDK:

from openai import OpenAI

client = OpenAI()
response = client.chat.completions.create(
    model="o3",
    max_tokens=1000,
    messages=[{"role": "user", "content": "Your prompt here"}]
)
# Cost: ~$0.0280 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 document summarization benchmarks. Hover for details.

Cheapest viable option: GPT 5.6 Luna at $0.003200/call (89% less, 84/100 quality).

What drives document summarization cost

The archetypal input-heavy task: the entire source document goes in, a short summary comes back. Cost is almost entirely a function of document length, and the output rate barely registers. Long documents can cross a provider's long-context threshold, where the whole request is re-priced at a multiple. Check the threshold before feeding in a hundred-page PDF as one call.

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 10,000/1,000 token split, output accounts for 29% of the $0.0280 per-call cost.

o3 quality benchmarks for document summarization

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

Performance across all task types

o3 scores by task type. Document Summarization 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