OpenAIGPT-4.1 Nano pricing
$0.10 per 1M input tokens and $0.40 per 1M output tokens. In real work that is 0.05¢ per chat answer and 0.15¢ to summarize a 20-page PDF.
What GPT-4.1 Nano costs per task
Token counts estimated from a measured model of the same lab (GPT-6 Luna), rescaled by tokenizer. Reasoning tokens are billed as output.
| Task | Cost | Tokens used | Price rank | Basis |
|---|---|---|---|---|
| Answer a chat question | 0.05¢$0.48 / 1,000 | 45 in · 540 out · 639 reasoning | 56 of 336 | estimated |
| Reply to a customer email | <0.01¢$0.06 / 1,000 | 258 in · 94 out | 8 of 336 | estimated |
| Write a 1,500-word blog post | 0.09¢$0.95 / 1,000 | 59 in · 2,217 out · 143 reasoning | 21 of 336 | estimated |
| Write 10 product descriptions | 0.04¢$0.44 / 1,000 | 283 in · 987 out · 34 reasoning | 12 of 336 | estimated |
| Translate 1,000 words | 0.07¢$0.69 / 1,000 | 1,330 in · 1,328 out · 67 reasoning | 49 of 336 | estimated |
| Proofread one page (500 words) | 0.04¢$0.37 / 1,000 | 718 in · 664 out · 91 reasoning | 32 of 336 | estimated |
| Summarize a 20-page PDF | 0.15¢$1.51 / 1,000 | 12,987 in · 449 out · 84 reasoning | 41 of 336 | estimated |
| Extract data from an invoice | 0.03¢$0.26 / 1,000 | 373 in · 422 out · 140 reasoning | 18 of 336 | estimated |
| Analyze a 200-row spreadsheet | 0.16¢$1.60 / 1,000 | 4,779 in · 456 out · 2,338 reasoning | 12 of 336 | estimated |
| Answer from 5 retrieved documents (RAG) | 0.05¢$0.50 / 1,000 | 3,690 in · 234 out · 104 reasoning | 15 of 336 | estimated |
| Classify 100 support tickets | 0.05¢$0.54 / 1,000 | 1,261 in · 445 out · 590 reasoning | 10 of 336 | estimated |
| Review 500 lines of code | 0.26¢$2.56 / 1,000 | 4,557 in · 337 out · 4,921 reasoning | 27 of 336 | estimated |
| Write a SQL query | 0.03¢$0.33 / 1,000 | 126 in · 266 out · 516 reasoning | 21 of 336 | estimated |
| Run a 50-step coding agent | 7.1¢$70.85 / 1,000 | 2,237,500 in · 15,000 out · 7,000 reasoning | 32 of 336 | modeled |
Price at every provider
List prices per 1M tokens (input / output) at each host serving GPT-4.1 Nano through OpenRouter today. Hosts can differ in quantization, context and speed.
| Provider | Input / output | Cached input | Context | Uptime |
|---|---|---|---|---|
 Azureunknown | $0.10 / $0.40 | $0.03 | 1M | 100% |
OpenAIunknown | $0.10 / $0.40 | $0.025 | 1M | 100% |
Azureunknown | $0.11 / $0.44 | $0.033 | 1M |
Price history
First seen in our price history on Apr 15, 2025 at $0.10 input / $0.40 output. The list price has not changed since.
FAQ
How much does GPT-4.1 Nano cost?
GPT-4.1 Nano costs $0.10 per 1 million input tokens and $0.40 per 1 million output tokens, with cached input at $0.025 (list price on Oct 18, 2026). In practice one chat answer costs about 0.05¢ and summarizing a 20-page PDF about 0.15¢.
Where is GPT-4.1 Nano cheapest?
Among 3 providers we track, the lowest list price today is at Azure: $0.10 input and $0.40 output per 1M tokens.
Is the GPT-4.1 Nano cost per task measured or estimated?
Estimated: GPT-4.1 Nano was not run directly. Tokens come from GPT-6 Luna and are rescaled by the tokenizer of OpenAI. Real usage can differ.