Reviewed tool profile

GPT-6 Luna

OpenAI’s cheapest GPT-6 model for focused, high-volume API work, with a 1.05M-token context.

Sources checked Oct 8

Pricing: API usage is billed per million tokens. Standard rates are $0.10 input, $0.01 cached input, $0.125 cache writes and $0.50 output. Prompts over 272K input tokens cost 2x input and cache rates and 1.5x output for the whole request. Batch and Flex cost half of Standard, and Fast mode costs double. Official source 1 ↗ · Official source 2 ↗
Available as: Available through the OpenAI API with the model ID gpt-6-luna, including the Responses, Chat Completions, Realtime and Batch endpoints. · EU data residency is available with Standard, Flex and Batch processing; regional processing adds a 10% premium where available. Official source 1 ↗ Official source 1 ↗
Primary group: Writing & Language

What it does

GPT-6 Luna is the smallest and cheapest model in OpenAI’s GPT-6 family, which OpenAI describes as its most efficient model for focused, high-volume tasks. It accepts text and image input and returns text, has a 1,050,000-token context window and 128,000 max output tokens, and supports reasoning effort from none to max. It is used through the OpenAI API with the model ID gpt-6-luna.

Official source 1 ↗ · Official source 2 ↗

Features

Low-cost, high-volume work. OpenAI positions Luna for cost-sensitive, high-volume workloads, at $0.10 input and $0.50 output per million tokens. Official source 1 ↗ · Official source 2 ↗
1.05M-token context window. Takes up to 1,050,000 tokens of context and returns up to 128,000 output tokens, with a May 18, 2026 knowledge cutoff. Official source 1 ↗
Adjustable reasoning effort. reasoning.effort can be set to none, low, medium (the default), high, xhigh or max. Official source 1 ↗
Text and image input. Accepts text and images and returns text; audio and video are not supported. Official source 1 ↗
Built-in tools in the Responses API. Supports web search, file search, code interpreter, hosted shell, computer use, MCP, skills and tool search, plus function calling, streaming and structured outputs. Official source 1 ↗
Batch, Flex and Fast processing. Batch and Flex run at 50% of Standard prices for work that can wait, and Fast mode at 2x for lower latency. Official source 1 ↗ · Official source 2 ↗

Pricing & free limits

Standard

$0.10 input / $0.50 outputUSD per million tokens

Cached input $0.01 and cache writes $0.125. Prompts over 272K input tokens: $0.20 input / $0.75 output. Official source 1 ↗ · Official source 2 ↗

Batch and Flex

$0.05 input / $0.25 outputUSD per million tokens

Half of Standard rates; cached input $0.005 and cache writes $0.0625. Official source 1 ↗ · Official source 2 ↗

Fast

$0.20 input / $1.00 outputUSD per million tokens

Twice the Standard rates for faster processing. Official source 1 ↗ · Official source 2 ↗

Billing details

Cached input is billed at 10% of the uncached input rate, and cache writes at 1.25x. Official source 1 ↗

Requests with more than 272K input tokens are billed at 2x input and cache rates and 1.5x output for the full request; regional processing adds 10% where available. Official source 1 ↗

Free access & limits

The OpenAI API’s Free usage tier does not support GPT-6 Luna; access starts at the Build tier (5,000 requests and 2,000,000 tokens per minute). Official source 1 ↗

Best for & limitations

Run classification, extraction and other focused tasks at high volume and low cost. Official source 1 ↗ · Official source 2 ↗

Process very long documents or codebases in one request with the 1.05M-token context window. Official source 1 ↗

Run large offline jobs through the Batch API at half the Standard price. Official source 1 ↗ · Official source 2 ↗

Build lightweight agents that call web search, file search, code interpreter or computer use through the Responses API. Official source 1 ↗

No audio or video. Audio and video input or output are not supported; images are input only. Official source 1 ↗
No fine-tuning. Fine-tuning is not supported for GPT-6 Luna. Official source 1 ↗
Function calling limits in Chat Completions. Chat Completions supports function calling only with reasoning effort set to none; built-in tools require the Responses API. Official source 1 ↗
Long prompts cost more. Prompts over 272K input tokens are billed at higher rates for the full request. Official source 1 ↗
Not on the Free API tier. GPT-6 Luna is not available on the API’s Free usage tier. Official source 1 ↗