GPT-6 Luna is OpenAI's most efficient model for focused, high-volume tasks and the cheapest tier of the GPT-6 family. It keeps the same 1,050,000-token context window as the larger models, with configurable reasoning effort, tool calling, vision and web search, and is available on AI/ML API today.
Lowest cost in the family
Twenty times cheaper per token than GPT-6 Sol, which is what makes high-volume work affordable.
Same context window
1,050,000 tokens, the same as GPT-6 Sol and GPT-6 Astra, so long inputs do not force a move up a tier.
Configurable reasoning
Effort runs from none through max, so the same model covers quick classification and harder one-off questions.
Vision and tools
Image and file input, parallel tool calls, structured outputs and web search are all available.
High-volume workloads
Classification, extraction and routing across large numbers of requests.
Routine coding
Small, repetitive engineering tasks and automated code review.
Latency-sensitive paths
Features that sit inside the request path and cannot wait for a heavier model.
GPT-6 Astra is the flagship at $13 / $65 per 1M tokens, GPT-6 Sol is the mid tier at $2.6 / $13, and GPT-6 Luna is the cheapest at $0.13 / $0.65. All three share the same 1,050,000-token context window.
Measured on the AI/ML API gateway across live traffic. Figures are medians unless stated. Last updated 2026-10-12.
import requests r = requests.post( "https://api.aimlapi.com/v1/chat/completions", headers={"Authorization": "Bearer " + AIMLAPI_KEY}, json={ "model": "openai/gpt-6-luna", "messages": [ { "role": "user", "content": "Hello!" } ] }, ) print(r.json())
const r = await fetch("https://api.aimlapi.com/v1/chat/completions", { method: "POST", headers: { Authorization: `Bearer ${process.env.AIMLAPI_KEY}`, "Content-Type": "application/json", }, body: JSON.stringify({ "model": "openai/gpt-6-luna", "messages": [ { "role": "user", "content": "Hello!" } ] }), }); console.log(await r.json());
curl -X POST https://api.aimlapi.com/v1/chat/completions \ -H "Authorization: Bearer $AIMLAPI_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"openai/gpt-6-luna","messages":[{"role":"user","content":"Hello!"}]}'
OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Input | |
| Output | |
| Cached input |
Cache writes are billed at $0.1625 / 1M tokens.
| Benchmark | Score | What it measures | Source | Retrieved |
|---|---|---|---|---|
| Intelligence | 37.3 | Composite score across standardised reasoning, knowledge and problem-solving evaluations, measured independently by Artificial Analysis | Source | September 24, 2026 |
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
GPT-6 Luna This page | Fast, high-volume tasks | |||
| Agentic workflows and computer use | ||||
| Fast, high-volume tasks | ||||
| Everyday coding + agents |
Yes. GPT-6 Luna is available on AI/ML API through the OpenAI-compatible chat completions endpoint under the model ID openai/gpt-6-luna.
On AI/ML API, GPT-6 Luna costs $0.13 per million input tokens, $0.65 per million output tokens and $0.013 per million cached input tokens. Cache writes are billed at $0.1625 per million.
GPT-6 Luna is the fast, low-cost tier at $0.13 / $0.65 per million tokens, for routine and high-volume work. GPT-6 Sol is the everyday model above it at $2.6 / $13, for tasks that need more capability. Both share the same 1,050,000-token context window.
Work that runs at volume and cannot wait: classification, extraction, routing, routine coding tasks, monitoring and background jobs, where latency and cost matter more than reaching for the strongest model.
