High-volume, cost-sensitive work
Choose GPT-6 Luna
GPT-6 Luna costs 24% less on a typical mix of three input tokens for every output token ($0.20 against $0.26 per million tokens).
GPT-4o Mini vs GPT-6 Luna: price, context and capabilities
Choose GPT-6 Luna for high-volume, cost-sensitive work, writing and code generation, reused prompts and documents (RAG, agents), very long inputs, the latest release and the most recent knowledge; on the other points the two are level or the data is missing.
In short
- GPT-6 Luna is 24% cheaper than GPT-4o Mini at the headline price ($0.20 / 1M tokens vs $0.2625 / 1M tokens).
- GPT-6 Luna reads more per request: 1.05M tokens against 128k.
- GPT-6 Luna is the newer model (Sep 22, 2026, against Jul 18, 2024).
- Only GPT-6 Luna offers reasoning.
Which should you choose?
Each answer below comes straight from the published prices, specifications and independent benchmark results.
Writing and code generation
Choose GPT-6 Luna
GPT-6 Luna charges $0.50 per million output tokens, against $0.60 for GPT-4o Mini. Output dominates the bill when answers are long.
Reused prompts and documents (RAG, agents)
Choose GPT-6 Luna
GPT-6 Luna charges $0.01 per million cached input tokens, against $0.08 for GPT-4o Mini.
Very long inputs
Choose GPT-6 Luna
GPT-6 Luna reads up to 1.05M tokens per request, against 128k for GPT-4o Mini.
Latest release
Choose GPT-6 Luna
GPT-6 Luna is the newer release (Sep 22, 2026, against Jul 18, 2024 for GPT-4o Mini).
Most recent knowledge
Choose GPT-6 Luna
GPT-6 Luna was trained on data up to May 2026, against October 2023 for GPT-4o Mini.
Monthly cost at three volumes
| Volume | GPT-4o Mini | GPT-6 Luna | Difference |
|---|---|---|---|
| Prototype: 1M input, 250K output tokens | $0.30 | $0.23 | GPT-6 Luna, $0.08 less |
| Production: 20M input, 5M output tokens | $6.00 | $4.50 | GPT-6 Luna, $1.50 less |
| Scale: 500M input, 100M output tokens | $135.00 | $100.00 | GPT-6 Luna, $35.00 less |
Standard rates, without caching or batch discounts. Volumes are per month.
Specifications side by side
| GPT-4o Mini | GPT-6 Luna | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Category | Language models | Language models |
| Status | Deprecated | Generally available |
| Headline price | $0.2625 / 1M tokens | $0.20 / 1M tokens |
| Input | $0.15 / 1M tokens | $0.10 / 1M tokens |
| Output | $0.60 / 1M tokens | $0.50 / 1M tokens |
| Cached input | $0.075 / 1M tokens | $0.01 / 1M tokens |
| Context window | 128k | 1.05M |
| Max output | 16k | 128k |
| Released | Jul 18, 2024 | Sep 22, 2026 |
| Knowledge cutoff | October 2023 | May 2026 |
| Licence | Proprietary | Proprietary |
| Capabilities | Vision, Tool calling, Structured output, Prompt caching, Batch API | Vision, Reasoning, Tool calling, Structured output, Prompt caching, Batch API |
| API model id | gpt-4o-mini | gpt-6-luna |
Benchmarks side by side
Leader in bold.
| Benchmark | GPT-4o Mini | GPT-6 Luna |
|---|---|---|
| Humanity's Last Exam | 4.2% | 38.5% |
| MMMU-Pro (visual reasoning) | 41.5% | 79.7% |
| GPQA Diamond | 42.6% | No data |
| IFBench (instruction following) | 31% | No data |
| Intelligence Index | No data | 38.1 |
| SciCode | No data | 54.6% |
| Long-context reasoning (AA-LCR) | No data | 83.3% |
Independent evaluations by Artificial Analysis, run the same way for every model, at the reasoning setting shown. Percentages unless marked as an index.
Frequently asked questions
Should I choose GPT-4o Mini or GPT-6 Luna?
Choose GPT-6 Luna for high-volume, cost-sensitive work, writing and code generation, reused prompts and documents (RAG, agents), very long inputs, the latest release and the most recent knowledge; on the other points the two are level or the data is missing.
Which is cheaper, GPT-4o Mini or GPT-6 Luna?
GPT-6 Luna is 24% cheaper than GPT-4o Mini at the headline price ($0.20 / 1M tokens vs $0.2625 / 1M tokens).
Which has the larger context window, GPT-4o Mini or GPT-6 Luna?
GPT-6 Luna reads more per request: 1.05M tokens against 128k.
What is the difference between GPT-4o Mini and GPT-6 Luna?
GPT-4o Mini is made by OpenAI and GPT-6 Luna by OpenAI. GPT-6 Luna is 24% cheaper than GPT-4o Mini at the headline price ($0.20 / 1M tokens vs $0.2625 / 1M tokens). GPT-6 Luna reads more per request: 1.05M tokens against 128k. GPT-6 Luna is the newer model (Sep 22, 2026, against Jul 18, 2024). Only GPT-6 Luna offers reasoning.
How much do GPT-4o Mini and GPT-6 Luna cost per month?
At 20 million input and 5 million output tokens a month, GPT-4o Mini costs $6.00 and GPT-6 Luna costs $4.50, at standard rates.
Which is newer, GPT-4o Mini or GPT-6 Luna?
GPT-6 Luna was released on Sep 22, 2026 and GPT-4o Mini on Jul 18, 2024.