GPT-4.1 pricing
GPT-4.1 costs $2 per million input tokens and $8 per million output tokens , with cached input at $0.5. Batch requests are discounted 50%.
Price per million tokens
| Input | $2 |
| Cached input | $0.5 |
| Output | $8 |
| Context window | not published |
| Batch discount | −50% |
What it costs in practice
Monthly cost for three common workload shapes, with prompt caching applied.
| Workload | Shape | Per request | Per month |
|---|---|---|---|
| Support chatbot | 1.5k in / 400 out, 100k requests/month, 30% cached | $0.00553 | $552.50 |
| RAG / document Q&A | 12k in / 700 out, 50k requests/month, 60% cached | $0.0188 | $940.00 |
| Coding agent | 25k in / 2.5k out, 20k requests/month, 80% cached | $0.04 | $800.00 |
Model your own workload with caching, batching and tokenizer correction →
Comparable models from other providers
| Model | Provider | Input | Output |
|---|---|---|---|
| Claude Sonnet 5 | Anthropic | $2 | $10 |
| Gemini 3.1 Pro (preview) | $2 | $12 | |
| Grok 4.6 | xAI | $2 | $6 |
| Grok 4.5 | xAI | $2 | $6 |
All figures verified 2026-08-18 against OpenAI's official pricing documentation . Fields the provider does not publish are shown as “—” rather than estimated.