OpenAI
o3
Deliberate reasoning model; high token + compute cost per answer.
Specs
- Provider
- OpenAI
- Family
- o-series
- Context window
- 200,000 tokens
- Max output
- 100,000 tokens
- Input price
- $2 / 1M
- Output price
- $8 / 1M
- Modalities
- text, image
- License
- proprietary
- Released
- Apr 16, 2025
- Training cutoff
- Jun 1, 2024
Estimated footprint
Per single text prompt (token-scaled rows assume ~1,000 tokens).
Footprint numbers are rough public estimates that vary by 10–100× across sources and depend on data-centre efficiency and local grid mix. They are shown as a low–high band with a source and date. Don't treat them as measured fact.
Energy
≈ 3.5 Wh
range 1–9 Wh
~23 s of a 9 W LED bulb
Third-party estimate (reasoning models use many more tokens) · low confidence
Water
≈ 4 mL
range 1.1–10 mL
~0.0 s of a shower
Third-party estimate (reasoning models use many more tokens) · low confidence
CO₂e
≈ 1.6 g
range 0.45–4.5 g
~13 m driven in a petrol car
Third-party estimate (reasoning models use many more tokens) · low confidence
Metric sources
| Metric | Low–Mid–High | Basis | Confidence | As of | Source |
|---|---|---|---|---|---|
| co2 | 0.45 · 1.6 · 4.5 g | per prompt | low | May 1, 2025 | Third-party estimate (reasoning models use many more tokens) |
| energy | 1 · 3.5 · 9 Wh | per prompt | low | May 1, 2025 | Third-party estimate (reasoning models use many more tokens) |
| water | 1.1 · 4 · 10 mL | per prompt | low | May 1, 2025 | Third-party estimate (reasoning models use many more tokens) |
Changelog
- Oct 6, 2026Seeded into PromptLedger reference library.