GPT-4o mini API Pricing
Deprecated: OpenAI announced on October 14, 2026 that gpt-4o-mini leaves the API on January 14, 2027, and names GPT-6 Luna as the replacement. GPT-4o mini is a cheap-tier OpenAI model at $0.15/$0.60 per million tokens. $0.15/M input, $0.6/M output, and $0.075/M cached input. It remains important for old cost baselines and migration math toward GPT-5.4 mini.
GPT-4o mini API cost calculator.
Archive calculator pre-loaded with GPT-4o mini rates. Tweak spend, output mix, or cache hit rate to compare legacy bills with current replacements.
GPT-4o mini cost on real workloads.
Repo-wide bug fix
Reading 100-page contracts
Support agent ticket triage
Research planning turn
This is a chars-per-token approximation, not a real tokenizer. Actual tokens vary by language, code density, and tool-call overhead — counts are typically ±10–20% off for English prose, more for code or non-Latin scripts. For exact billing, use the vendor's official tokenizer.
| Model | Input /M | Output /M | Effective blended | Context | Best for |
|---|---|---|---|---|---|
| GPT-4o mini Current | $0.15 cache $0.075 | $0.60 | $0.129 agentic 92/8 | 128K | Legacy cheap OpenAI workloads |
| GPT-5.5 | $5.00 cache $0.50 | $30.00 | $3.61 +28× | 1M | Current replacement workloads |
| GPT-5.4 | $2.50 cache $0.25 | $15.00 | $1.80 +14× | 1.05M | Current replacement workloads |
| GPT-5.4 mini | $0.75 cache $0.075 | $4.50 | $0.541 +4.2× | 400K | Current replacement workloads |
| Claude Sonnet 4.6 | $3.00 cache $0.30 | $15.00 | $2.05 +16× | 1M | Legacy Claude production baselines |
| Gemini 3.8 Flash | $0.75 cache $0.075 | $3.75 | $0.481 +3.7× · promo | 1M | Gemini long-context work |
| DeepSeek V4 Pro | $1.32 cache $0.044 | $3.96 | $0.569 +4.4× | 1M | Low-cost reasoning and coding |
GPT-4o mini has published scores on 1 benchmark we track; its best placing is #97 of 105 on ARC-AGI-2. All of these scores come from independent leaderboards, not from the lab.
| Benchmark | Score | Rank | Leader | Source |
|---|---|---|---|---|
| ARC-AGI-2 Reasoning | 0% ARC Prize verified, best result | #97 of 105 | GPT-6 Astra · 95% | Official leaderboard ARC Prize Foundation |
GPT-4o mini API pricing FAQ.
Short answers for teams checking GPT-4o mini pricing, status, and migration choices.
Q · 01 Is GPT-4o mini still available? +
gpt-4o-mini-2024-07-18) is removed from the API on that date, and named GPT-6 Luna as the replacement. Until then it bills at the rates on this page.Q · 02 How much did GPT-4o mini cost? +
Q · 03 Is cached-input pricing included? +
Q · 04 What should teams use instead? +
gpt-6-luna: GPT-6 Luna lists at $0.10/M input and $0.50/M output and blends to $0.0682/M on our agentic mix, against $0.129/M here. Use the shelf to compare the other current options.