# GPT-5.6 Luna vs GPT-5.6 Terra

As of October 21, 2026, GPT-5.6 Terra costs 900% more per input token than GPT-5.6 Luna ($2.00 vs $0.20 per 1M), and both have a 922K-token context window.

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

## Side by side

| | GPT-5.6 Luna | GPT-5.6 Terra |
|---|---|---|
| Input, per 1M tokens | $0.20 | $2.00 |
| Output, per 1M tokens | $1.20 | $12.00 |
| Cache read, per 1M tokens | $0.02 | $0.20 |
| Cache write, per 1M tokens | $0.25 | $2.50 |
| 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 | 9 | 9 |
| Price shown is from | OpenAI | OpenAI |
| Added to LiteLLM | July 9, 2026 | July 9, 2026 |

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

## Cheapest provider for each

- GPT-5.6 Luna: OpenAI at $0.20 input per 1M tokens (`gpt-5.6-luna`)
- GPT-5.6 Terra: OpenAI at $2.00 input per 1M tokens (`gpt-5.6-terra`)

## Benchmark scores

| Benchmark | GPT-5.6 Luna | GPT-5.6 Terra |
|---|---|---|
| Epoch Capabilities Index (Overall) | 156.5 | 160.1 |
| FrontierCode (Coding and agents) | 39.8% | 41.3% |
| APEX-Agents (Coding and agents) | 43.0% | 58.2% (max) |
| GPQA Diamond (Reasoning and knowledge) | 91.6% (max) | 93.3% (max) |
| ARC-AGI-2 (Reasoning and knowledge) | 59.5% (max) | 83.9% (max) |
| SimpleQA Verified (Reasoning and knowledge) | 41.0% (max) | 43.2% (max) |
| FrontierMath (tiers 1-3) (Math) | 82.1% (max) | 86.0% (max) |
| FrontierMath (tier 4) (Math) | 61.0% (max) | 70.7% (max) |
| OTIS Mock AIME 2024-2025 (Math) | 98.3% (max) | 99.7% (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 August 10, 2026: Epoch's own runs and results it collects from each benchmark's leaderboard. Higher is better.

## When to pick which

- GPT-5.6 Luna: Costs 90% less per input token: $0.20 vs $2.00 per 1M.

## FAQ

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

GPT-5.6 Luna is cheaper at 3 input tokens per output token: $0.45 per 1M tokens blended ($0.20 input, $1.20 output), versus $4.50 ($2.00 and $12.00) for GPT-5.6 Terra, as of October 21, 2026.

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

Both have a 922,000-token context window.

### Can I switch from GPT-5.6 Luna to GPT-5.6 Terra 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-5.6-terra", or pointing a LiteLLM gateway model alias at the other model. You can also use one as a fallback for the other.