Amux AI

OpenAI: GPT-6 Luna

Active

OpenAI: GPT-6 Luna is a fast and cost-effective model in the OpenAI GPT-6 series, positioned lower than GPT-6 Sol. It is suitable for high-concurrency and latency-sensitive workloads such as chat, classification, and lightweight agent tasks; at higher inference workloads, it can take on complex software engineering and computer usage tasks that previously required Sol-level models. It shares the improvements in factual reliability of the GPT-6 family, as well as a clearer, more concise communication style.

By:
OpenAI
Input:
Output:
Context length:
1.05M
Max output:
128K
Published:
2026-09-23
toolsreasoningstructuredOutputstreamingvisioncaching

Providers

Same model, different providers. Automatic routing spreads requests across healthy providers by default, or ranks them by price, latency and more.

Provider
90% offLowestamux-special$0.1-0.2$0.01-0.02/1M tokens$0.5-0.75$0.05-0.075/1M tokens
Read$0.01-0.02$0.001-0.002/1M tokensWrite$0.125-0.25$0.0125-0.025/1M tokens
1.05M71.04%5.6s963.42 tps
20% offazure$0.1-0.2$0.08-0.16/1M tokens$0.5-0.75$0.4-0.6/1M tokens
Read$0.01-0.02$0.008-0.016/1M tokensWrite$0.125-0.25$0.1-0.2/1M tokens
1.05M—2.9s168.73 tps

Availability

24 hours · 11/04–11/05

Success rate of requests sent by the Amux AI gateway to each provider. Client errors are excluded.

Tok/s

24 hours · 11/04–11/05

Average output speed of streaming requests, in tokens per second (TPS).

TTFT

24 hours · 11/04–11/05

Average time to first token (TTFT) of streaming requests, measured from request dispatch to the first token received.

Activity

24 hours · 11/04–11/05

Relative request activity over time, broken down by serving provider. Indexed to the peak within the selected range (= 100); reflects trends and provider share, not absolute volume.

Related models

More models from OpenAI

OpenAI: GPT-6.1 Terra1.05M contextfrom $0.1 / M tokens2 providersGPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol. It is suited for everyday agentic, coding, and writing work, is particularly strong at understanding screenshots and on-screen content, and is efficient enough for high-volume workloads.
OpenAI: GPT-6.1 Sol1.05M contextfrom $0.1 / M tokens2 providersGPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional work, and multi-step business workflow automation, and approaches Astra-level results on these tasks at a much lower cost. Compared with GPT-6 Sol, it makes fewer factual errors and is more reliable at respecting explicit restrictions and user intent during agentic tasks.
OpenAI: GPT-6 Sol1.05M contextfrom $0.1 / M tokens2 providersOpenAI: GPT-6 Sol is a cost-effective high-end model in the OpenAI GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna. It is suitable for demanding professional work, agency coding, business workflow automation and computer use, and is particularly good at long-span software engineering tasks in real code bases. It delivers near Astra-level reliability at a fraction of the cost and continues Astra’s clear, concise communication style in technical and programming conversations.