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.
GPT-5.6 Luna vs 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 |
Cheapest provider for each
- GPT-5.6 Luna: Databricks at $0.20 input and $1.20 output per 1M tokens (
databricks/databricks-gpt-5-6-luna) - Ripple 65B Preview: GMI Cloud at $0.20 input and $0.60 output per 1M tokens (
gmi/gmicloud/Ripple-65B-Preview)
When to pick which
Pick GPT-5.6 Luna for
- Available from 14 providers through LiteLLM, vs 2.
Pick Ripple 65B Preview for
- Costs 50% less per output token: $0.60 vs $1.20 per 1M.
From differences in the data above only; where the data is equal, no reason is given.
Call GPT-5.6 Luna or Ripple 65B Preview with LiteLLM
Both use the OpenAI format through LiteLLM, so switching is a model name change. Set each provider's API key in the environment first.
from litellm import completion
messages = [{"role": "user", "content": "Hello!"}]
# GPT-5.6 Luna
response = completion(model="gpt-5.6-luna", messages=messages)
# Ripple 65B Preview
response = completion(model="gmi/gmicloud/Ripple-65B-Preview", messages=messages)
# GPT-5.6 Luna, falling back to Ripple 65B Preview if the call fails
response = completion(model="gpt-5.6-luna", messages=messages, fallbacks=["gmi/gmicloud/Ripple-65B-Preview"])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.