GPT-6 Luna Pro
openai/gpt-6-luna-pro- OpenAI
- Family · GPT-6 Luna Pro
- File · Image · Text → Text
- Reasoning · adjustable
- Tools · JSON · Vision
Not on OSMEXO yet
Spec & list price
Context1M
Max output128K
Input / 1M$0.10
Output / 1M$0.505× input
Usage
Tokens / day69.4B▲ 36% 7d
Usage rank#40
Requests / day586.9K
Tool calls / req0.23
Per request · 30 days
Avg input45.7K3.1× median
Avg output1.8K2.7× median
Cache hit66%about median
Reasoning share61%about median
Tool-call failures0.6%0.3× median
Consumption
Peak 217.0B 2 OctLow 37.0B 10 OctRank today #40
News & trends
Trending · 14 days
- Same model, 2.8x the bill: GPT-6 Luna Pro tested #Shorts226 views
- Hype or Hire: GPT-6 Luna Pro: same model, 2.8x bill4 views
News · latest from OpenAI
- GPT-6.1 Terra vs. Claude Opus 5.5: Cheaper and faster in three tests at maxthenewstack.io · 2 Nov
- Chinese labs now target OpenAI's GPT-6 Astra for distillationfork.zone · 1 Nov
- GPT-6.1 Terrasimonwillison.net · 31 Oct
- GPT-5.6 Sol can beat Factorio on peaceful moderyanmadden.net · 31 Oct
Speed
Output speed#48/334121 tok/s1.8× faster than median
Fastest provider246 tok/sbest of 6 providers
First token#32911 s10.7× longer than median
Technical details
- Reasoning
- on · medium
- Tokenizer
- GPT
- Moderation
- moderated
Reasoning effort
- max
- xhigh
- high
- medium · default
- low
- none
Request parameters 11
- tools
- tool_choice
- response_format
- structured_outputs
- reasoning
- reasoning_effort
- include_reasoning
- max_tokens
- max_completion_tokens
- seed
+1 more
- verbosity
When to use
Best for
- Harder reasoning at maximum effort
- Long document analysis with images
- Coding and analysis needing more depth
- Tool-calling workflows with structured output
Think twice for
- High-volume simple chat (cheaper options exist)
- Latency-critical interactive apps
- Self-hosting (closed weights)
Research papers
Same family
GPT-6 Luna ProWant GPT-6 Luna Pro on OSMEXO?
Sign in to request it. Requests are reviewed; a request does not guarantee availability.

