GPT-6 Luna
GPT-6 LunaAlternatives?
CheaperMuse Glimmer 30BhighOpensame-15%$0.058Context: 1.05M → 131K
BetterMiMo v2.6 ProthinkingOpen+4%+96%$0.13Context: 1.05M → 1M+4
OpenKimi K3max+6%+2,849%$2.00Context: 1.05M → 1M+4Lower effortSame modelxhigh-4%-38%$0.042
CheaperAgnes 2.5 Pro Betasame-25%$0.10 / $0.30Context: 1.05M → 1MMuse Glimmer 30BhighOpensame-15%$0.058Context: 1.05M → 131KAgnes 2.5 Pro Betasame-25%$0.10 / $0.30Context: 1.05M → 1MGPT-5.6 Lunahigh-4%-35%$0.044MiMo v2.5 ProthinkingOpen-4%-20%$0.054Context: 1.05M → 1M+1
Ling 3.0 Flash VLthinkingOpen-6%-55%$0.06 / $0.18Context: 1.05M → 262KMiMo v2.6 ProthinkingOpen+4%+96%$0.13Context: 1.05M → 1M+4
Step 5 PreviewthinkingOpen+6%+1,413%$1.03Context: 1.05M → 1M+4Kimi K3maxOpen+6%+2,849%$2.00Context: 1.05M → 1M+4
Claude Fable 5.1max+2%+11,149%$7.63Context: 1.05M → 1M+6Kimi K3maxOpen+6%+2,849%$2.00Context: 1.05M → 1M+4Step 5 PreviewthinkingOpen+6%+1,413%$1.03Context: 1.05M → 1M+4MiMo v2.6 ProthinkingOpen+4%+96%$0.13Context: 1.05M → 1M+4Muse Glimmer 30BhighOpensame-15%$0.058Context: 1.05M → 131KLing 3.1 FlashOpensame+1,374%$1.00Context: 1.05M → 1M+1GPT-5.6 Solmaxsame+2,832%$1.99GPT-6 Solmaxsame+1,440%$1.04GPT-5.6 Lunamaxsame+163%$0.18GPT-5.3 Codexxhighsame—$1.75 / $14Context: 1.05M → 400K+1GPT-6.1 Solmaxsame+968%$0.72Remove unsupported parameters+5GPT-5.6 Terramaxsame+1,962%$1.40Prompts with >272K input tokensGPT-5.5mediumsame+1,229%$0.90Prompts with >272K input tokensGPT-6 Astramax-3%+4,703%$3.26Monitoring can return HTTP 403+2All 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 $0.068 at max 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?›
#50 of 334 in Chat & Knowledge, #34 of 132 in Coding, #32 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 GPT-4.1?›
On AA-LCR (long context) 1.1, GPT-6 Luna scores 83.3 vs 68.3 — higher.
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?›
Muse Glimmer 30B (cheaper), MiMo v2.6 Pro (better), Kimi K3 (open weights).