← All models

GPT-6 Luna

Language Available Full comparison ↗

openai/gpt-6-luna · by OpenAI · decoder-only-transformer

Pricing — 1 offering(s)

OpenAI

View on OpenAI ↗

About this offering: OpenAI's GPT-6 Luna, the cost-optimised tier of the GPT-6 family, launched 2026-09-22 for high-volume, cost-sensitive work. It costs $0.10 input and $0.50 output per 1M tokens, with cached input at $0.01 (OpenAI pricing page, checked 2026-10-11).

Input tokens

  • $0.10 / 1M tokens (input) Current 2026-09-22 → present

Output tokens

  • $0.50 / 1M tokens (output) Current 2026-09-22 → present

Cached input tokens

  • $0.01 / 1M tokens (cached input) Current 2026-09-22 → present

Cache writes

  • $0.125 / 1M tokens (cache write) Current 2026-09-22 → present

Batch

Batch input tokens

  • $0.05 / 1M tokens (input) Current 2026-11-03 → present

Batch output tokens

  • $0.25 / 1M tokens (output) Current 2026-11-03 → present

Showing the active price and any recorded history. Full pricing history is available via the paid API — see API docs.

See how GPT-6 Luna fits into a cost-aware routing setup

See how →

Capability profile

How GPT-6 Luna rates across core capability dimensions, with the task-level evidence behind each rating.

context window Strong

1,050,000-token context window, 128,000 max output tokens (developers.openai.com/api/docs/models/gpt-6-luna).

tool use Strong

OpenAI API docs: supports Functions, Web search, File search, Computer use.

cost efficiency Strong

Lowest-priced tier in the GPT-6 family ($0.10/$0.50 per 1M tokens, Standard, short context).

Ratings are estimated — limited independent data is available for this model.

Coding benchmarks

View the full coding benchmark leaderboard →
Benchmark Score Harness Source
terminal-bench-2-1 73.0% 2026-09 terminus-2 📊 leaderboard ↗
terminal-bench-4-0 13.6% 2026-09 mini-swe-agent 📊 leaderboard ↗

Operator guidance

Cost-optimized tier of GPT-6, launched 2026-09-22. Route high-volume, focused tasks here; step up to GPT-6 Sol when the task needs more capability.

Use cases

Limitations

Citations