# GPT-5.6 Luna vs Ripple 65B Preview

As of November 12, 2026, GPT-5.6 Luna and Ripple 65B Preview cost the same per input token ($0.20 per 1M), but GPT-5.6 Luna costs 100% more per output token ($1.20 vs $0.60) and has a 922K-token context window versus 1M.

- Page: https://models.litellm.ai/compare/gpt-5.6-luna-vs-ripple-65b-preview
- GPT-5.6 Luna: https://models.litellm.ai/models/gpt-5.6-luna
- Ripple 65B Preview: https://models.litellm.ai/models/ripple-65b-preview

## Side by side

| | GPT-5.6 Luna | Ripple 65B Preview |
|---|---|---|
| Input, per 1M tokens | $0.20 | $0.20 |
| Output, per 1M tokens | $1.20 | $0.60 |
| Cache read, per 1M tokens | $0.02 | $0.05 |
| Cache write, per 1M tokens | $0.25 | – |
| Context window | 922,000 tokens | 1,000,000 tokens |
| Max output | 128,000 tokens | 131,072 tokens |
| Image input | Yes | – |
| Tool calling | Yes | – |
| Structured output (JSON) | Yes | – |
| Prompt caching | Yes | Yes |
| Reasoning | Yes | – |
| Providers on LiteLLM | 14 | 2 |
| Price shown is from | OpenAI | GMI Cloud |
| Added to LiteLLM | July 9, 2026 | November 5, 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`)
- Ripple 65B Preview: GMI Cloud at $0.20 input per 1M tokens (`gmi/gmicloud/Ripple-65B-Preview`)

## When to pick which

- GPT-5.6 Luna: Available from 14 providers through LiteLLM, vs 2.
- Ripple 65B Preview: Costs 50% less per output token: $0.60 vs $1.20 per 1M.

## FAQ

### Which is cheaper, GPT-5.6 Luna or Ripple 65B Preview?

Ripple 65B Preview is cheaper at 3 input tokens per output token: $0.30 per 1M tokens blended ($0.20 input, $0.60 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 Ripple 65B Preview?

Ripple 65B Preview has the larger context window: 1,000,000 tokens, versus 922,000 for GPT-5.6 Luna.

### Can I switch from GPT-5.6 Luna to Ripple 65B Preview 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 "gmi/gmicloud/Ripple-65B-Preview", or pointing a LiteLLM gateway model alias at the other model. You can also use one as a fallback for the other.