OpenAIreasoningo3 Mini High pricing
$1.10 per 1M input tokens and $4.40 per 1M output tokens. In real work that is 0.30¢ per chat answer and 1.7¢ to summarize a 20-page PDF.
What o3 Mini High costs per task
Token counts estimated from a measured model of the same lab (GPT-6.1 Sol), rescaled by tokenizer. Reasoning tokens are billed as output.
| Task | Cost | Tokens used | Price rank | Basis |
|---|---|---|---|---|
| Answer a chat question | 0.30¢$2.97 / 1,000 | 45 in · 560 out · 103 reasoning | 190 of 336 | estimated |
| Reply to a customer email | 0.08¢$0.84 / 1,000 | 258 in · 126 out | 151 of 336 | estimated |
| Write a 1,500-word blog post | 1.0¢$10.13 / 1,000 | 59 in · 2,116 out · 172 reasoning | 184 of 336 | estimated |
| Write 10 product descriptions | 0.55¢$5.48 / 1,000 | 283 in · 1,103 out · 72 reasoning | 160 of 336 | estimated |
| Translate 1,000 words | 0.73¢$7.33 / 1,000 | 1,330 in · 1,289 out · 44 reasoning | 162 of 336 | estimated |
| Proofread one page (500 words) | 0.37¢$3.70 / 1,000 | 718 in · 662 out | 197 of 336 | estimated |
| Summarize a 20-page PDF | 1.7¢$16.52 / 1,000 | 12,987 in · 482 out · 26 reasoning | 231 of 336 | estimated |
| Extract data from an invoice | 0.24¢$2.39 / 1,000 | 373 in · 450 out | 170 of 336 | estimated |
| Analyze a 200-row spreadsheet | 3.8¢$38.13 / 1,000 | 4,779 in · 919 out · 6,553 reasoning | 213 of 336 | estimated |
| Answer from 5 retrieved documents (RAG) | 0.60¢$6.00 / 1,000 | 3,690 in · 442 out | 189 of 336 | estimated |
| Classify 100 support tickets | 0.37¢$3.67 / 1,000 | 1,261 in · 442 out · 77 reasoning | 120 of 336 | estimated |
| Review 500 lines of code | 2.3¢$22.52 / 1,000 | 4,557 in · 1,135 out · 2,843 reasoning | 213 of 336 | estimated |
| Write a SQL query | 0.22¢$2.16 / 1,000 | 126 in · 312 out · 147 reasoning | 165 of 336 | estimated |
| Run a 50-step coding agent | $1.34$1,341 / 1,000 | 2,237,500 in · 15,000 out | 250 of 336 | modeled |
Price at every provider
List prices per 1M tokens (input / output) at each host serving o3 Mini High through OpenRouter today. Hosts can differ in quantization, context and speed.
| Provider | Input / output | Cached input | Context | Uptime |
|---|---|---|---|---|
OpenAIunknown | $1.10 / $4.40 | $0.55 | 200K |
Price history
First seen in our price history on Feb 13, 2025 at $1.10 input / $4.40 output. The list price has not changed since.
FAQ
How much does o3 Mini High cost?
o3 Mini High costs $1.10 per 1 million input tokens and $4.40 per 1 million output tokens, with cached input at $0.55 (list price on Oct 18, 2026). In practice one chat answer costs about 0.30¢ and summarizing a 20-page PDF about 1.7¢.
Where is o3 Mini High cheapest?
Among 1 providers we track, the lowest list price today is at OpenAI: $1.10 input and $4.40 output per 1M tokens.
Does o3 Mini High charge for reasoning tokens?
Yes. Reasoning (thinking) tokens are billed as output tokens. That is why the cost per task can be much higher than the visible answer suggests - our task costs include them.
Is the o3 Mini High cost per task measured or estimated?
Estimated: o3 Mini High was not run directly. Tokens come from GPT-6.1 Sol and are rescaled by the tokenizer of OpenAI. Real usage can differ.