# GPT-5.6 Luna vs GPT-6 Luna

As of November 12, 2026, GPT-5.6 Luna costs 100% more per input token than GPT-6 Luna ($0.20 vs $0.10 per 1M), and both have a 922K-token context window.

- Page: https://models.litellm.ai/compare/gpt-5.6-luna-vs-gpt-6-luna
- GPT-5.6 Luna: https://models.litellm.ai/models/gpt-5.6-luna
- GPT-6 Luna: https://models.litellm.ai/models/gpt-6-luna

## Side by side

| | GPT-5.6 Luna | GPT-6 Luna |
|---|---|---|
| Input, per 1M tokens | $0.20 | $0.10 |
| Output, per 1M tokens | $1.20 | $0.50 |
| Cache read, per 1M tokens | $0.02 | $0.01 |
| Cache write, per 1M tokens | $0.25 | $0.125 |
| Context window | 922,000 tokens | 922,000 tokens |
| Max output | 128,000 tokens | 128,000 tokens |
| Image input | Yes | Yes |
| Tool calling | Yes | Yes |
| Structured output (JSON) | Yes | Yes |
| Prompt caching | Yes | Yes |
| Reasoning | Yes | Yes |
| Providers on LiteLLM | 14 | 13 |
| Price shown is from | OpenAI | OpenAI |
| Added to LiteLLM | July 9, 2026 | September 22, 2026 |

Headline prices in USD per 1M tokens, from LiteLLM's model price file.

## Cheapest provider for each

- GPT-5.6 Luna: Databricks at $0.20 input per 1M tokens (`databricks/databricks-gpt-5-6-luna`)
- GPT-6 Luna: OpenAI at $0.10 input per 1M tokens (`gpt-6-luna`)

## Benchmark scores

| Benchmark | GPT-5.6 Luna | GPT-6 Luna |
|---|---|---|
| Epoch Capabilities Index (Overall) | 156.7 | 156.4 |
| FrontierCode (Coding and agents) | 39.8% | 42.4% (max) |
| APEX-Agents (Coding and agents) | 43.0% | 44.3% (max) |
| GPQA Diamond (Reasoning and knowledge) | 91.6% (max) | 90.5% (max) |
| ARC-AGI-2 (Reasoning and knowledge) | 59.5% (max) | 59.3% (max) |
| SimpleQA Verified (Reasoning and knowledge) | 41.0% (max) | 41.4% (max) |
| FrontierMath (tiers 1-3) (Math) | 82.1% (max) | 78.9% (max) |
| FrontierMath (tier 4) (Math) | 61.0% (max) | 56.1% (max) |
| OTIS Mock AIME 2024-2025 (Math) | 98.3% (max) | 98.9% (max) |

From the Epoch AI Benchmarking Hub (https://epoch.ai/benchmarks), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/), data as of September 22, 2026: Epoch's own runs and results it collects from each benchmark's leaderboard. Higher is better.

## When to pick which

- GPT-6 Luna: Costs 50% less per input token: $0.10 vs $0.20 per 1M.

## FAQ

### Which is cheaper, GPT-5.6 Luna or GPT-6 Luna?

GPT-6 Luna is cheaper at 3 input tokens per output token: $0.20 per 1M tokens blended ($0.10 input, $0.50 output), versus $0.45 ($0.20 and $1.20) for GPT-5.6 Luna, as of November 12, 2026.

### Which has the larger context window, GPT-5.6 Luna or GPT-6 Luna?

Both have a 922,000-token context window.

### Can I switch from GPT-5.6 Luna to GPT-6 Luna without changing my code?

Yes. Through LiteLLM both use the OpenAI format, so switching means changing the model name from "gpt-5.6-luna" to "gpt-6-luna", or pointing a LiteLLM gateway model alias at the other model. You can also use one as a fallback for the other.