Day 0 support for GPT-6 Sol and GPT-6 Luna on LiteLLM

[misbahsy]

GPT-6 Sol and GPT-6 Luna are now live on LiteLLM

Call gpt-6-sol and gpt-6-luna through the LiteLLM AI Gateway with spend tracking, rate limits, fallbacks and logging in one place.

Half the price of GPT-5.6 - Sol is $2 / MTok input and $10 output, Luna is $0.10 and $0.50, against GPT-5.6's current $4 / $20 and $0.20 / $1.20. Both keep a 1,050,000-token context window with 922K input and 128K output.

Built on Astra - trained with the same methods as GPT-6 Astra. Per OpenAI, Sol at xhigh scores 33.2% on AutomationBench at $0.27 a task, and 68.8% on DeepSWE v1.1 at max.

Worth checking before you route traffic to it:

Rates double on input and cache above 272K input tokens, and output goes to 1.5x, so long-context requests cost more than the headline.

temperature only applies with reasoning_effort="none". The default effort is medium, so send none explicitly alongside it or LiteLLM drops or refuses the parameter.

Get started, no redeploy needed:

Pricing landed in PR #42515, and GPT-6 parameter handling has shipped since v1.101.0. Reload your pricing in the UI under Models + Endpoints -> Price Data -> Reload Price Data (or POST /reload/model_cost_map as an admin), on any version v1.76.0 or newer.

model_list:
  - model_name: gpt-6-sol
    litellm_params:
      model: openai/gpt-6-sol
      api_key: os.environ/OPENAI_API_KEY
  - model_name: gpt-6-luna
    litellm_params:
      model: openai/gpt-6-luna
      api_key: os.environ/OPENAI_API_KEY

Read the full guide → Day 0 Support: GPT-6 Sol and GPT-6 Luna

Misbah Syed
DevRel @ LiteLLM