Models, measured side by side
GPT-5.6 Luna vs GPT-6 Luna
Compare GPT-5.6 Luna, GPT-6 Luna by token pricing, context length, benchmark results, speed and tool support.
Monthly workload
Monthly cost breakdown
InputOutput
GPT-5.6 Luna
$10 / mo
GPT-6 Luna
$4.50 / mo
Performance comparison
GPT-5.6 Luna
37.3
GPT-6 Luna
38.1
Overview
Pricing & capacity
| Pricing & capacity | GPT-5.6 Luna | GPT-6 Luna |
|---|---|---|
| Input / 1M tokens | $0.20 | $0.10 |
| Output / 1M tokens | $1.20 | $0.50 |
| Cached input / 1M | $0.02 | $0.01 |
| Monthly cost | $10 | $4.50 |
| Context window | 1.1M | 1.1M |
| Maximum output | 128K | 128K |
Input / 1M tokens
- GPT-5.6 Luna
- $0.20
- GPT-6 Luna
- $0.10
Output / 1M tokens
- GPT-5.6 Luna
- $1.20
- GPT-6 Luna
- $0.50
Cached input / 1M
- GPT-5.6 Luna
- $0.02
- GPT-6 Luna
- $0.01
Monthly cost
- GPT-5.6 Luna
- $10
- GPT-6 Luna
- $4.50
Context window
- GPT-5.6 Luna
- 1.1M
- GPT-6 Luna
- 1.1M
Maximum output
- GPT-5.6 Luna
- 128K
- GPT-6 Luna
- 128K
Benchmarks & performance
| Benchmarks & performance | GPT-5.6 Luna | GPT-6 Luna |
|---|---|---|
| Arena Elo | 1,189 | 1,211 |
| MMLU-Pro | 71.8% | 75.4% |
| Intelligence Index | 37.3 | 38.1 |
| GPQA | 91.1% | Not listed |
| Humanity’s Last Exam | 39.5% | 38.5% |
| SciCode | 53.6% | 54.6% |
| Output speed | 126 tokens/s | 141 tokens/s |
| Time to first token | 106.4 s | 95.97 s |
| DesignArena rating | 1,235 | 1,277 |
| DesignArena win rate | 46.5% | 48.5% |
Arena Elo
- GPT-5.6 Luna
- 1,189
- GPT-6 Luna
- 1,211
MMLU-Pro
- GPT-5.6 Luna
- 71.8%
- GPT-6 Luna
- 75.4%
Intelligence Index
- GPT-5.6 Luna
- 37.3
- GPT-6 Luna
- 38.1
GPQA
- GPT-5.6 Luna
- 91.1%
- GPT-6 Luna
- Not listed
Humanity’s Last Exam
- GPT-5.6 Luna
- 39.5%
- GPT-6 Luna
- 38.5%
SciCode
- GPT-5.6 Luna
- 53.6%
- GPT-6 Luna
- 54.6%
Output speed
- GPT-5.6 Luna
- 126 tokens/s
- GPT-6 Luna
- 141 tokens/s
Time to first token
- GPT-5.6 Luna
- 106.4 s
- GPT-6 Luna
- 95.97 s
DesignArena rating
- GPT-5.6 Luna
- 1,235
- GPT-6 Luna
- 1,277
DesignArena win rate
- GPT-5.6 Luna
- 46.5%
- GPT-6 Luna
- 48.5%
Tools & features
| Tools & features | GPT-5.6 Luna | GPT-6 Luna |
|---|---|---|
| Function calling | Supported | Supported |
| Structured outputs | Supported | Supported |
| JSON mode | Supported | Supported |
| Reasoning | Supported | Supported |
| Deterministic seed | Supported | Supported |
| Prompt caching | Supported | Supported |
Function calling
- GPT-5.6 Luna
- Supported
- GPT-6 Luna
- Supported
Structured outputs
- GPT-5.6 Luna
- Supported
- GPT-6 Luna
- Supported
JSON mode
- GPT-5.6 Luna
- Supported
- GPT-6 Luna
- Supported
Reasoning
- GPT-5.6 Luna
- Supported
- GPT-6 Luna
- Supported
Deterministic seed
- GPT-5.6 Luna
- Supported
- GPT-6 Luna
- Supported
Prompt caching
- GPT-5.6 Luna
- Supported
- GPT-6 Luna
- Supported
API & availability
| API & availability | GPT-5.6 Luna | GPT-6 Luna |
|---|---|---|
| API identifier | gpt-5.6-luna | gpt-6-luna |
| API providers | OpenAI, Azure, OpenAI, Azure, Amazon Bedrock, Azure, OpenAI | OpenAI, OpenAI, Azure, Azure, Azure, Amazon Bedrock, OpenAI |
| Knowledge cutoff | 2026-02-16 | Not listed |
| Prices checked | Oct 8, 2026 | Oct 8, 2026 |
API identifier
- GPT-5.6 Luna
gpt-5.6-luna- GPT-6 Luna
gpt-6-luna
API providers
- GPT-5.6 Luna
- OpenAI, Azure, OpenAI, Azure, Amazon Bedrock, Azure, OpenAI
- GPT-6 Luna
- OpenAI, OpenAI, Azure, Azure, Azure, Amazon Bedrock, OpenAI
Knowledge cutoff
- GPT-5.6 Luna
- 2026-02-16
- GPT-6 Luna
- Not listed
Prices checked
- GPT-5.6 Luna
- Oct 8, 2026
- GPT-6 Luna
- Oct 8, 2026
About the models
GPT-5.6 Luna
Low-cost GPT-5.6 model; OpenAI's recommended replacement for GPT-5 nano and GPT-4.1 nano.
Full pricing & detailsGPT-6 Luna
Smallest, fastest GPT-6 model for high-volume classification, extraction and chat. Long-context requests bill at $0.20 input / $0.75 output per 1M.
Full pricing & detailsComparison FAQ
GPT-5.6 Luna: $0.20 input and $1.20 output per million tokens. GPT-6 Luna: $0.10 input and $0.50 output per million tokens. The cheaper choice depends on your input-to-output ratio; a model can have a lower input rate but a higher output rate.