o3-mini API Pricing
Retired October 23, 2026: OpenAI shut o3-mini down on that date, and calls to it now fail; OpenAI names GPT-5.6 Sol as the substitute. This archive preserves OpenAI's first budget reasoning price. $1.1/M input, $4.4/M output, and $0.55/M cached input. It made production reasoning workloads far cheaper than o1 and set the $1.10/$4.40 mini-reasoning baseline.
o3-mini API cost calculator.
Archive calculator pre-loaded with the last o3-mini rates OpenAI published. Tweak spend, output mix, or cache hit rate to compare legacy bills with current replacements.
o3-mini cost on real workloads.
Repo-wide bug fix
Reading 100-page contracts
Support agent ticket triage
Research planning turn
This is a chars-per-token approximation, not a real tokenizer. Actual tokens vary by language, code density, and tool-call overhead — counts are typically ±10–20% off for English prose, more for code or non-Latin scripts. For exact billing, use the vendor's official tokenizer.
| Model | Input /M | Output /M | Effective blended | Context | Best for |
|---|---|---|---|---|---|
| o3-mini Current | $1.10 cache $0.55 | $4.40 | $0.949 agentic 92/8 | 200K | Reasoning archive comparisons |
| GPT-5.5 | $5.00 cache $0.50 | $30.00 | $3.61 +3.8× | 1M | Current OpenAI flagship |
| GPT-5.4 | $2.50 cache $0.25 | $15.00 | $1.80 +90% | 1.05M | Current OpenAI daily driver |
| GPT-5.4 mini | $0.75 cache $0.075 | $4.50 | $0.541 −43% | 400K | Current cheap OpenAI workloads |
| Claude Sonnet 5.5 | $2.00 cache $0.10 | $10.00 | $1.29 +36% | 1M | Anthropic's current Sonnet |
| Gemini 3.8 Flash | $0.75 cache $0.075 | $3.75 | $0.481 −49% · promo | 1M | Gemini long-context work |
| DeepSeek V4 Pro | $1.32 cache $0.044 | $3.96 | $0.569 −40% | 1M | Low-cost reasoning and coding |
By replacement
o3-mini has published scores on 2 benchmarks we track; its best placing is #79 of 105 on ARC-AGI-2. All of these scores come from independent leaderboards, not from the lab.
| Benchmark | Score | Rank | Leader | Source |
|---|---|---|---|---|
| ARC-AGI-2 Reasoning | 3% ARC Prize verified, best result | #79 of 105 | GPT-6 Astra · 95% | Official leaderboard ARC Prize Foundation |
| ARC-AGI-1 Reasoning | 34.5% ARC Prize verified, best result | #77 of 99 | 6 tied · 98.5% | Official leaderboard ARC Prize Foundation |
o3-mini API pricing FAQ.
Short answers for teams checking o3-mini pricing, status, and migration choices.
Q · 01 Can I still use o3-mini? +
o3-mini would be shut down on October 23, 2026, and its deprecations page now says access was shut down on that date. The substitute OpenAI names is GPT-5.6 Sol. OpenAI's pricing page still prints this model's rates in its legacy table, but they no longer buy anything; the figures here are the last OpenAI published, kept for old invoices and migration math.