o4-mini · OpenAI
Compact reasoning model at $1.10/$4.40 — cheap thinking for structured tasks and tool loops.
Last checked Aug 16, 2026. Calculations use the listed base rates; provider-specific tiers, cache writes, batch pricing, and long-context rules may differ. Confirm the current rate at the official provider source.
Input
$1.10
per 1M tokens
Output
$4.40
per 1M tokens
Cached input
$0.275
per 1M tokens
Context window
200K
max output 100K
o4-mini cost calculator
What o4-mini costs per task
| Use case | Input tokens | Output tokens | Cost / request | Monthly @ 1K req/day |
|---|---|---|---|---|
| Customer support chatbot | 3,500 | 350 | $0.003369 | $101.063 |
| RAG / search-augmented answers | 8,000 | 500 | $0.0077 | $231.00 |
| AI coding assistant | 12,000 | 2,000 | $0.0161 | $481.80 |
| Document summarization | 25,000 | 600 | $0.0281 | $842.325 |
| Agentic workflow | 40,000 | 1,500 | $0.0292 | $874.50 |
| Content generation | 800 | 1,200 | $0.005962 | $178.86 |
| Data extraction & tagging | 2,000 | 250 | $0.00297 | $89.10 |
| Translation | 5,000 | 5,500 | $0.0291 | $872.438 |
Assumes each use case's typical cacheable share of input. See full cost scenarios.
Compare with alternatives
| Model | Input /M | Output /M | Context | Chat request* |
|---|---|---|---|---|
| o4-mini | $1.10 | $4.40 | 200K | $0.00627 |
| GPT-5.6 Lunacompare | $0.20 | $1.20 | 1.1M | $0.0014 |
| o3 | $2.00 | $8.00 | 200K | $0.0114 |
| Gemini 3.5 Flash-Lite | $0.30 | $2.50 | 1M | $0.00266 |
*4,000 in + 800 out tokens, 50% cached input where available.
Related calculations
FAQ
o4-mini costs $1.10 per 1M input tokens and $4.40 per 1M output tokens, with cached input at $0.275 per 1M tokens. Verified Aug 16, 2026 against https://developers.openai.com/api/docs/pricing.
o4-mini supports a 200,000-token context window with up to 100,000 output tokens per request, tokenized with o200k_base.
At $1.10/M input and $4.40/M output, o4-mini sits above GPT-5.6 Luna ($0.20/M in, $1.20/M out) — see the comparison table for full-workload differences.