OpenAIGPT-4o-mini (2024-07-18) pricing
$0.15 per 1M input tokens and $0.60 per 1M output tokens. In real work that is 0.07¢ per chat answer and 0.23¢ to summarize a 20-page PDF.
What GPT-4o-mini (2024-07-18) 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 | 0.07¢$0.71 / 1,000 | 45 in · 540 out · 639 reasoning | 79 of 336 | estimated |
| Reply to a customer email | <0.01¢$0.10 / 1,000 | 258 in · 94 out | 18 of 336 | estimated |
| Write a 1,500-word blog post | 0.14¢$1.42 / 1,000 | 59 in · 2,217 out · 143 reasoning | 40 of 336 | estimated |
| Write 10 product descriptions | 0.07¢$0.66 / 1,000 | 283 in · 987 out · 34 reasoning | 20 of 336 | estimated |
| Translate 1,000 words | 0.10¢$1.04 / 1,000 | 1,330 in · 1,328 out · 67 reasoning | 65 of 336 | estimated |
| Proofread one page (500 words) | 0.06¢$0.56 / 1,000 | 718 in · 664 out · 91 reasoning | 61 of 336 | estimated |
| Summarize a 20-page PDF | 0.23¢$2.27 / 1,000 | 12,987 in · 449 out · 84 reasoning | 75 of 336 | estimated |
| Extract data from an invoice | 0.04¢$0.39 / 1,000 | 373 in · 422 out · 140 reasoning | 35 of 336 | estimated |
| Analyze a 200-row spreadsheet | 0.24¢$2.39 / 1,000 | 4,779 in · 456 out · 2,338 reasoning | 23 of 336 | estimated |
| Answer from 5 retrieved documents (RAG) | 0.08¢$0.76 / 1,000 | 3,690 in · 234 out · 104 reasoning | 33 of 336 | estimated |
| Classify 100 support tickets | 0.08¢$0.81 / 1,000 | 1,261 in · 445 out · 590 reasoning | 23 of 336 | estimated |
| Review 500 lines of code | 0.38¢$3.84 / 1,000 | 4,557 in · 337 out · 4,921 reasoning | 57 of 336 | estimated |
| Write a SQL query | 0.05¢$0.49 / 1,000 | 126 in · 266 out · 516 reasoning | 40 of 336 | estimated |
| Run a 50-step coding agent | 19¢$187 / 1,000 | 2,237,500 in · 15,000 out · 7,000 reasoning | 93 of 336 | modeled |
Price at every provider
List prices per 1M tokens (input / output) at each host serving GPT-4o-mini (2024-07-18) through OpenRouter today. Hosts can differ in quantization, context and speed.
| Provider | Input / output | Cached input | Context | Uptime |
|---|---|---|---|---|
OpenAIunknown | $0.15 / $0.60 | $0.075 | 128K | 100% |
Price history
First seen in our price history on Sep 5, 2024 at $0.15 input / $0.60 output. The list price has not changed since.
FAQ
How much does GPT-4o-mini (2024-07-18) cost?
GPT-4o-mini (2024-07-18) costs $0.15 per 1 million input tokens and $0.60 per 1 million output tokens, with cached input at $0.075 (list price on Oct 18, 2026). In practice one chat answer costs about 0.07¢ and summarizing a 20-page PDF about 0.23¢.
Where is GPT-4o-mini (2024-07-18) cheapest?
Among 1 providers we track, the lowest list price today is at OpenAI: $0.15 input and $0.60 output per 1M tokens.
Is the GPT-4o-mini (2024-07-18) cost per task measured or estimated?
Estimated: GPT-4o-mini (2024-07-18) was not run directly. Tokens come from GPT-6 Luna and are rescaled by the tokenizer of OpenAI. Real usage can differ.