GPT-4o mini API Pricing
OpenAI · released 2024-07-18
Pricing
0.015¢ / 1K
0.060¢ / 1K
0.026¢ / 1K
What it actually costs
| Workload | Tokens | Cost |
|---|---|---|
| Short chat reply | 500 in / 300 out | 0.0255¢ |
| RAG query | 4,000 in / 500 out | 0.09¢ |
| Long document summary | 50,000 in / 1,000 out | 0.81¢ |
| Code review of a 2k-line file | 30,000 in / 2,000 out | 0.57¢ |
| 1,000 chat replies/day for 30 days | 30,000 × (500 in / 300 out) | $7.65 |
Cost = (input tokens ÷ 1,000,000 × $0.15) + (output tokens ÷ 1,000,000 × $0.60).
Benchmarks
#396 of 533
#170 of 197
#199 of 249
Similar intelligence, lower price
| Model | Intelligence | Blended $/1M |
|---|---|---|
| Llama 3.1 Instruct 8B | 6.9 | $0.028 |
| Gemma 4 E4B (Reasoning) | 8.9 | $0.04 |
| Sarvam 30B (high) | 6.6 | $0.047 |
| Granite 4.2 3B | 9.1 | $0.052 |
| Nova Micro | 5.9 | $0.061 |
Leaderboard neighbours
| Model | Intelligence | Blended $/1M |
|---|---|---|
| NVIDIA Nemotron Nano 9B V2 (Non-reasoning) | 6.8 | $0.086 |
| GLM-4.5V (Non-reasoning) | 6.7 | $0.90 |
| GPT-4 | 6.7 | $37.50 |
| GPT-4o mini | 6.7 | $0.262 |
| Gemini 2.5 Flash-Lite (Non-reasoning) | 6.7 | $0.175 |
| Hermes 4 - Llama-3.1 70B (Non-reasoning) | 6.7 | — |
| Mistral Small 3 | 6.7 | $0.15 |
More from OpenAI
| Model | Intelligence | Blended $/1M |
|---|---|---|
| GPT-6 Astra (max) | 52.7 | $20.00 |
| GPT-5.6 Sol (max) | 47.0 | $8.00 |
| GPT-5.6 Terra (max) | 42.1 | $4.50 |
| GPT-5.4 (xhigh) | 39.0 | $5.625 |
| GPT-5.5 (xhigh) | 38.4 | $11.25 |
| GPT-5.6 Luna (max) | 37.3 | $0.45 |
| GPT-5.3 Codex (xhigh) | 32.5 | $4.813 |
| GPT-5.2 (xhigh) | 30.4 | $4.813 |
Count tokens & estimate cost for GPT-4o mini See GPT-4o mini on the leaderboard
Source: Artificial Analysis · last synced 2026-09-22
FAQ
Who develops GPT-4o mini?
GPT-4o mini is developed by OpenAI, released 2024-07-18.
How much does GPT-4o mini cost per million tokens?
GPT-4o mini costs $0.15 per 1M input tokens and $0.60 per 1M output tokens ($0.262 blended), per Artificial Analysis's official pricing data.
How does GPT-4o mini rank on benchmarks?
GPT-4o mini scores 6.7 on the Artificial Analysis Intelligence Index, ranking #396 of 533 models we track.
Is there a cheaper model with similar intelligence to GPT-4o mini?
Yes — Llama 3.1 Instruct 8B scores similar intelligence (6.9) at $0.028/1M blended, versus $0.262/1M for GPT-4o mini.
Where does this data come from?
Pricing and benchmark data for GPT-4o mini comes from Artificial Analysis (artificialanalysis.ai), synced daily. Last synced 2026-09-22.