GPT-4.1: cost, energy and CO₂ per token
- Provider
- OpenAI
- Confidence
- low
GPT-4.1 emits about 626 g of CO₂e, uses 7.3 L of water and 1.4 kWh of electricity per million generated tokens.
Key figures, per million tokens
public price, in eurosOn the bill
GPT-4.11M generated tokens€6.95
1M input tokens€1.74
1M tokens read from cache€0.43
Not on the bill
CO₂e, 1M generated tokensabout 4 km in a combustion car626 g
Water7.3 L
Energy1.4 kWh
1M input tokens105 g, 1.2 L, 237 Wh
GPT-4.1 among the 34 models in the registry
Of the 34 models in the TokenClimate registry, GPT-4.1 ranks 15th for carbon intensity per million generated tokens, below the median (668 g). The gap with Mistral Small 4, the registry's most frugal, is still ×32.
Sources and method
Full equations and assumptions in the methodology.
The calculation, per million generated tokens
1,419 Wh × (1.12 × 0.35 g/Wh + 0.049 g/Wh) = 626 g
- Energy per token
- The per-token energy factor behind the figures above, published with its citation. EcoLogits v0.11.3
- Infrastructure parameters
- Datacenter parameters applied to this provider (the equations live in the methodology). Jegham et al., arXiv:2505.09598 (v6)
PUE 1.12 Grid carbon intensity (CIF) 0.35 kgCO₂e/kWh On-site water (WUE) 0.3 L/kWh Off-site water (EWIF) 4.35 L/kWh Amortised manufacturing (embodied) 49 gCO₂e/kWh - Price
- Public provider prices. developers.openai.com, pricing
Frequently asked questions
- How much CO₂e for 1 million tokens with GPT-4.1?
- About 626 g per million generated tokens and 105 g per million input tokens (factors ecologits-0.11.3-2026-10 of the TokenClimate registry).
- Where do these figures come from?
- Factors published in TokenClimate's versioned registry, each with its citation on this page. The full equations and parameters are in the public methodology, at tokenclimate.com/en/methodology.
- What is the confidence level?
- Low confidence: extrapolated from another model, or estimated by a parametric tool.
- How can you measure your organisation's real usage?
- The TokenClimate dashboard connects to your organisation's Anthropic, OpenAI or OpenRouter admin keys (stored encrypted) and measures cost and CO₂e per team and per model. You can see it in the demo: tokenclimate.com/demo. Locally, the open source plugin claude-carbon measures a Claude Code session.
Does your organisation use GPT-4.1?
The dashboard pulls your volumes every day from your Anthropic, OpenAI or OpenRouter admin keys, and puts cost and CO₂e on each team and each model.