o3 Mini pricing for sql generation

Quick start

Call o3 Mini with the OpenAI Python SDK:

from openai import OpenAI

client = OpenAI()
response = client.chat.completions.create(
    model="o3-mini",
    max_tokens=1000,
    messages=[{"role": "user", "content": "Your prompt here"}]
)
# Cost: ~$0.006050 per call at standard rates
# Input:  $1.10/MTok
# Output: $4.40/MTok

How o3 Mini compares on cost

Per-call cost for all models scoring 50+ on sql generation benchmarks. Hover for details.

Cheapest viable option: Claude Sonnet 5 at $0.0130/call (-115% less, 93/100 quality).

What drives sql generation cost

The cheapest code use case on this list. A natural-language question plus a schema fits in 1.5K tokens, and the query that comes back is under 1K. That makes SQL generation a genuine candidate for a fast-tier model: the task is well-bounded, the output is short, and the quality gap between tiers narrows when there is little room to go wrong. Schema caching cuts the input side to near zero.

For o3 Mini specifically, that means output tokens cost 4.0x more than input, at $4.40 vs $1.10 per MTok. At this use case’s 1,500/1,000 token split, output accounts for 73% of the $0.006050 per-call cost.

o3 Mini quality benchmarks for sql generation

Benchmark data for sql generation is pending for o3 Mini. Test against your own evaluation suite before moving to production.

Performance across all task types

o3 Mini scores by task type. SQL Generation 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 Mini

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 Mini 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