GPT-6 Luna
GPT-6 LunaAlternatives?
CheaperGPT-5.6 Lunamedium-18%-63%$0.016
OpenKimi K3max+18%+4,641%$2.00Context: 1.05M → 1M+4Lower effortSame modelhighsame-31%$0.029
CheaperClaude Haiku 5.5low-40%-42%$0.024Context: 1.05M → 1M+6BetterGPT-6.1 Sollow+45%+210%$0.13Remove unsupported parameters+5GPT-5.6 Lunamedium-18%-63%$0.016Claude Haiku 5.5low-40%-42%$0.024Context: 1.05M → 1M+6GPT-5.6 Lunahigh+19%+4%$0.044GPT-6.1 Sollow+45%+210%$0.13Remove unsupported parameters+5GPT-6 Sollow+30%+215%$0.13Claude Haiku 5.5max+12%+404%$0.21Context: 1.05M → 1M+6
MiniMax M3.1 Flashthinking+12%+422%$0.22Context: 1.05M → 1M+1Kimi K3maxOpen+18%+4,641%$2.00Context: 1.05M → 1M+4
MiMo v2.6 ProthinkingOpensame+216%$0.13Context: 1.05M → 1M+4
Muse Spark OpenxhighOpensame+1,900%$0.84Context: 1.05M → 1M+2
DeepSeek V4.1 Flash 1017maxOpen-8%+521%$0.26Context: 1.05M → 1M+5
Qwen3.8 27BxhighOpen-12%+2,288%$1.01Context: 1.05M → 262K+5GPT-6 Astraxhigh+73%+5,373%$2.31Monitoring can return HTTP 403+2GPT-6.1 Solxhigh+71%+831%$0.39Remove unsupported parameters+5GPT-5.6 Solxhigh+48%+2,708%$1.18GPT-6 Solxhigh+32%+1,135%$0.52GPT-5.6 Terraxhigh+32%+1,398%$0.63Prompts with >272K input tokensGPT-5.6 Lunaxhigh+28%+102%$0.085GPT-5.5xhigh+14%+6,144%$2.63Prompts with >272K input tokensGPT-5.5 Instant (June 2026)+9%+1,539%$0.69Context: 1.05M → 400KAll OpenAI models →History
2 versionsBenchmarks
in Chat & KnowledgeWatch out 4
Function calling only with none · Chat Completions›
Chat Completions function calling requires reasoning_effort none; use Responses for reasoning with tools. Source ↗
More than 272K input tokens›
Prompts above 272K input tokens charge 2× input and cache rates and 1.5× output rates for the entire request. Source ↗
Remove unsupported sampling parameters›
When reasoning effort is not none, remove temperature, top_p and top_logprobs, plus Chat Completions logprobs or Responses output logprobs inclusion. Source ↗
Cache writes billed at 1.25x›
Cache writes cost 1.25× the uncached input token rate. Source ↗
FAQ
How much does GPT-6 Luna cost?›
$0.10 per 1M input tokens and $0.50 per 1M output tokens; cached input $0.01 per 1M. A typical benchmark task costs about $0.042 at xhigh effort.
Is GPT-6 Luna free to use?›
There is no free API; the cheapest paid price is $0.10 per 1M input tokens.
How good is GPT-6 Luna, and what is it best at?›
#64 of 334 in Chat & Knowledge, #39 of 132 in Coding, #38 of 133 in Agents & Tool Use, #56 of 195 in Writing & Language, #22 of 124 in Vision & Documents. Strongest at: Agents & work tasks, Reasoning, Long context, Knowledge, Vision.
Is GPT-6 Luna better than Gemini 3.8 Flash?›
On GDP.pdf · AA all-pass, GPT-6 Luna scores 22.8 vs 22.8 — about the same. It is 95% cheaper per task.
How can I use GPT-6 Luna?›
Through the API of Amazon Bedrock, Azure, OpenAI.
What is the context window of GPT-6 Luna?›
1.05M tokens, with up to 128K output tokens.
When was GPT-6 Luna released? Is there a newer version?›
Released 2026-09-22. It is the current version in its line.
Is GPT-6 Luna open source?›
No, GPT-6 Luna is a closed model available through an API. The closest open-weights option here is Kimi K3.
Can GPT-6 Luna read images?›
It accepts text and images, PDF files as input.
What is GPT-6 Luna?›
GPT-6 Luna is a closed language model from OpenAI, released Sep 2026, the successor to GPT-4.1.
What are the best alternatives to GPT-6 Luna?›
GPT-5.6 Luna (cheaper), Kimi K3 (open weights).