GPT-6 Luna
GPT-6 LunaAlternatives?
CheaperLing 3.0 FlashthinkingOpensame-55%$0.06 / $0.18Context: 1.05M → 262K+1
BetterClaude Haiku 5.5low+12.6+442%$0.024Context: 1.05M → 1M+6
OpenGLM 5.3max+41.9+44,306%$2.01Context: 1.05M → 1M+5CheaperLing 3.0 Flash VLthinkingOpensame-55%$0.06 / $0.18Context: 1.05M → 262KCheaperLing 3.0 Flash FinthinkingOpensame-55%$0.06 / $0.18Context: 1.05M → 262K+1Ling 3.0 FlashthinkingOpensame-55%$0.06 / $0.18Context: 1.05M → 262K+1Ling 3.0 Flash VLthinkingOpensame-55%$0.06 / $0.18Context: 1.05M → 262KLing 3.0 Flash FinthinkingOpensame-55%$0.06 / $0.18Context: 1.05M → 262K+1
Gemma 4 31BthinkingOpensame-20%$0.10 / $0.34Context: 1.05M → 256KClaude Haiku 5.5low+12.6+442%$0.024Context: 1.05M → 1M+6GPT-5.6 Lunahigh+2.5+874%$0.044
MiMo v2.6 FlashthinkingOpen+22.7+1,281%$0.062Context: 1.05M → 1M+4GPT-6.1 Sollow+30.8+2,795%$0.13Remove unsupported parameters+5GPT-6 Sollow+9.1+2,840%$0.13GLM 5.3maxOpen+41.9+44,306%$2.01Context: 1.05M → 1M+5MiMo v2.6 ProthinkingOpen+34.8+2,850%$0.13Context: 1.05M → 1M+4
DeepSeek V4.1 Flash 1017maxOpen+33.8+5,702%$0.26Context: 1.05M → 1M+5Ling 3.1 FlashOpen+33.3+22,033%$1.00Context: 1.05M → 1M+1
Step 5 PreviewthinkingOpen+33.3+22,625%$1.03Context: 1.05M → 1M+4GPT-6 Astralow+41.9+18,000%$0.82Monitoring can return HTTP 403+2GPT-6.1 Sollow+30.8+2,795%$0.13Remove unsupported parameters+5GPT-5.5 Instant (June 2026)+12.6+15,210%$0.69Context: 1.05M → 400KGPT-6 Sollow+9.1+2,840%$0.13GPT-5.5medium+5.1+19,863%$0.90Prompts with >272K input tokensGPT-5.4 Minixhigh+2+9,805%$0.45Context: 1.05M → 400KGPT-5.6 Terralow+1.5+3,098%$0.14Prompts with >272K input tokensGPT-5.6 Sollow+1+5,671%$0.26All OpenAI models →History
2 versionsWatch 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 $0.005 at low 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?›
#122 of 334 in Chat & Knowledge, #74 of 132 in Coding, #73 of 133 in Agents & Tool Use, #56 of 195 in Writing & Language, #41 of 124 in Vision & Documents.
Is GPT-6 Luna better than Kimi K3?›
On Terminal-Bench 4.0, GPT-6 Luna scores 12.6 vs 12.6 — about the same. It is 100% 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 GLM 5.3.
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?›
Ling 3.0 Flash (cheaper), Claude Haiku 5.5 (better), GLM 5.3 (open weights).