GPT-6 Luna
GPT-6 LunaAlternatives?
BetterGPT-5.6 Lunahighwins 60%+152%$0.044
OpenQwen3.8 Flashthinkingwins 94%+2,030%$0.37Context: 1.05M → 262K+6Lower effortSame modelnon-thinkingwins 24%-35%$0.011
BetterClaude Haiku 5.5mediumwins 83%+169%$0.047Context: 1.05M → 1M+6
BetterMiMo v2.6 FlashthinkingOpenwins 91%+257%$0.062Context: 1.05M → 1M+4GPT-5.6 Lunahighwins 60%+152%$0.044Claude Haiku 5.5mediumwins 83%+169%$0.047Context: 1.05M → 1M+6MiMo v2.6 FlashthinkingOpenwins 91%+257%$0.062Context: 1.05M → 1M+4GPT-6.1 Sollowwins 53%+648%$0.13Remove unsupported parameters+5MiMo v2.6 ProthinkingOpenwins 92%+662%$0.13Context: 1.05M → 1M+4Qwen3.8 FlashthinkingOpenwins 94%+2,030%$0.37Context: 1.05M → 262K+6
DeepSeek V4.1 Flash 1017maxOpenwins 94%+1,399%$0.26Context: 1.05M → 1M+5MiMo v2.6 ProthinkingOpenwins 92%+662%$0.13Context: 1.05M → 1M+4
GLM 5.3maxOpenwins 91%+11,376%$2.01Context: 1.05M → 1M+5
Kimi K3maxOpenwins 91%+11,344%$2.00Context: 1.05M → 1M+4GPT-6 Astramediumwins 89%+8,715%$1.54Monitoring can return HTTP 403+2GPT-6.1 Solmediumwins 82%+1,123%$0.21Remove unsupported parameters+5GPT-5.6 Solmediumwins 70%+2,789%$0.50GPT-6 Solmediumwins 57%+1,315%$0.25GPT-5.5 Instant (June 2026)same+3,857%$0.69Context: 1.05M → 400KGPT-5.6 Terramediumwins 42%+949%$0.18Prompts with >272K input tokensGPT-5.5mediumwins 36%+5,059%$0.90Prompts with >272K input tokensGPT-5.6 Lunamediumwins 28%-11%$0.016All OpenAI models →History
2 versionsBenchmarks
in Agents & Tool UseWatch 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 $0.017 at medium 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?›
#90 of 334 in Chat & Knowledge, #48 of 132 in Coding, #42 of 133 in Agents & Tool Use, #56 of 195 in Writing & Language, #35 of 124 in Vision & Documents. Strongest at: Long context.
Is GPT-6 Luna better than GPT-5.6 Luna?›
On AA-Briefcase 1.1 · Elo, GPT-6 Luna scores 1,334.8 vs 1,342.2 — about the same. It is 90% 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 Qwen3.8 Flash.
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 (better), Qwen3.8 Flash (open weights).