OpenAI · Small and fast

GPT-6 Luna API pricing and specs

OpenAI's small model, with the same hosted tools as Astra and a 'none' reasoning setting for cheap, fast steps.

Input

⁨$0.10⁩

Cached input

⁨$0.010⁩

Output

⁨$0.50⁩

US dollars per million tokens, standard tier, short-prompt rate

In Chat Completions, function calling works only with reasoning effort set to none; use the Responses API to combine tools with reasoning. Knowledge cutoff is 18 May 2026.

Prompts over 272K tokens are billed at ⁨$0.20⁩ input, ⁨$0.020⁩ cached and ⁨$0.75⁩ output per million, and the higher rate applies to the whole request.

Spec sheet

API model string: gpt-6-luna
Provider: OpenAI
Context: 1.05M tokens
Max output: 128K tokens
Released: September 22, 2026
Batch API: 50% off, results within hours
Documented agent features: Tool callingStructured outputComputer useRemote MCPBuilt-in web searchAdjustable reasoning

What a task costs

Four reference workloads priced at this model's list rates, with caching applied after the first call. Your numbers will differ; the calculator lets you change every assumption.

Workload	Per task	Per 1,000 tasks
Support bot 4 calls, short tool lookups	⁨$0.003⁩	⁨$3⁩
Coding agent 30 calls, files and test output	⁨$0.099⁩	⁨$99⁩
Browser agent 25 calls, screenshots and page text	⁨$0.070⁩	⁨$70⁩
Research agent 15 calls, long search results	⁨$0.066⁩	⁨$66⁩