High-volume, cost-sensitive work
Choose GPT-4.1 nano
GPT-4.1 nano costs 13% less on a typical mix of three input tokens for every output token ($0.18 against $0.20 per million tokens).
GPT-4.1 nano vs GPT-6 Luna: price, context and capabilities
Choose GPT-4.1 nano for high-volume, cost-sensitive work and writing and code generation. Choose GPT-6 Luna for reused prompts and documents (RAG, agents), reasoning over long documents, the latest release and the most recent knowledge.
In short
- GPT-4.1 nano is 13% cheaper than GPT-6 Luna at the headline price ($0.175 / 1M tokens vs $0.20 / 1M tokens).
- GPT-6 Luna reads more per request: 1.05M tokens against 1.05M.
- GPT-6 Luna is the newer model (Sep 22, 2026, against Apr 14, 2025).
- 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-4.1 nano
GPT-4.1 nano charges $0.40 per million output tokens, against $0.50 for GPT-6 Luna. 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 $0.03 for GPT-4.1 nano.
Reasoning over long documents
Choose GPT-6 Luna
GPT-6 Luna scores 83.3% on Long-context reasoning (AA-LCR), against 20.3% for GPT-4.1 nano.
Latest release
Choose GPT-6 Luna
GPT-6 Luna is the newer release (Sep 22, 2026, against Apr 14, 2025 for GPT-4.1 nano).
Most recent knowledge
Choose GPT-6 Luna
GPT-6 Luna was trained on data up to May 2026, against June 2024 for GPT-4.1 nano.
Monthly cost at three volumes
| Volume | GPT-4.1 nano | GPT-6 Luna | Difference |
|---|---|---|---|
| Prototype: 1M input, 250K output tokens | $0.20 | $0.23 | GPT-4.1 nano, $0.03 less |
| Production: 20M input, 5M output tokens | $4.00 | $4.50 | GPT-4.1 nano, $0.50 less |
| Scale: 500M input, 100M output tokens | $90.00 | $100.00 | GPT-4.1 nano, $10.00 less |
Standard rates, without caching or batch discounts. Volumes are per month.
Specifications side by side
| GPT-4.1 nano | GPT-6 Luna | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Category | Language models | Language models |
| Status | Deprecated | Generally available |
| Headline price | $0.175 / 1M tokens | $0.20 / 1M tokens |
| Input | $0.10 / 1M tokens | $0.10 / 1M tokens |
| Output | $0.40 / 1M tokens | $0.50 / 1M tokens |
| Cached input | $0.025 / 1M tokens | $0.01 / 1M tokens |
| Context window | 1.05M | 1.05M |
| Max output | 33k | 128k |
| Released | Apr 14, 2025 | Sep 22, 2026 |
| Knowledge cutoff | June 2024 | 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-4.1-nano | gpt-6-luna |
Benchmarks side by side
Leader in bold.
| Benchmark | GPT-4.1 nano | GPT-6 Luna |
|---|---|---|
| Humanity's Last Exam | 3.8% | 38.5% |
| MMMU-Pro (visual reasoning) | 40.1% | 79.7% |
| Long-context reasoning (AA-LCR) | 20.3% | 83.3% |
| Terminal-Bench Hard | 3.8% | No data |
| GPQA Diamond | 51.2% | No data |
| IFBench (instruction following) | 32% | No data |
| τ²-Bench (agentic tool use) | 17.3% | No data |
| Intelligence Index | No data | 38.1 |
| SciCode | No data | 54.6% |
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-4.1 nano or GPT-6 Luna?
Choose GPT-4.1 nano for high-volume, cost-sensitive work and writing and code generation. Choose GPT-6 Luna for reused prompts and documents (RAG, agents), reasoning over long documents, the latest release and the most recent knowledge.
Which is cheaper, GPT-4.1 nano or GPT-6 Luna?
GPT-4.1 nano is 13% cheaper than GPT-6 Luna at the headline price ($0.175 / 1M tokens vs $0.20 / 1M tokens).
Which has the larger context window, GPT-4.1 nano or GPT-6 Luna?
GPT-6 Luna reads more per request: 1.05M tokens against 1.05M.
What is the difference between GPT-4.1 nano and GPT-6 Luna?
GPT-4.1 nano is made by OpenAI and GPT-6 Luna by OpenAI. GPT-4.1 nano is 13% cheaper than GPT-6 Luna at the headline price ($0.175 / 1M tokens vs $0.20 / 1M tokens). GPT-6 Luna reads more per request: 1.05M tokens against 1.05M. GPT-6 Luna is the newer model (Sep 22, 2026, against Apr 14, 2025). Only GPT-6 Luna offers reasoning.
How much do GPT-4.1 nano and GPT-6 Luna cost per month?
At 20 million input and 5 million output tokens a month, GPT-4.1 nano costs $4.00 and GPT-6 Luna costs $4.50, at standard rates.
Which is newer, GPT-4.1 nano or GPT-6 Luna?
GPT-6 Luna was released on Sep 22, 2026 and GPT-4.1 nano on Apr 14, 2025.