GPT-6 Luna: Benchmarks, Pricing & Context Window
GPT-6 Luna is a language model from OpenAI, released in September 2026, with multimodal input, a 1.1M-token context window, and pricing from $0.100/M input, $0.010/M cached input, $0.500/M output.
GPT-6 Luna is OpenAI's GPT-6 model for focused, high-volume tasks. It supports text and image input with text output, a 1,050,000-token context window (maximum input 922,000 tokens), and 128,000 output tokens. Reasoning effort supports
GPT-6 Luna benchmarks
Capability tiers
Standing within each category, adjusted for leaderboard depth.
Real tasks performance
High-confidence performance for GPT-6 Luna across real-world prompt categories. Only 95% intervals at most 4 points wide are shown.
Performance by conversation depth
How GPT-6 Luna holds up as conversations get longer.
Quality Tracker
GPT-6 Luna Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Wed Sep 23 2026GPT-6 Luna pricing
Providers
GPT-6 Luna starts at $0.100 per million input tokens and $0.500 per million output tokens via OpenAI. Reused prompt prefixes cost $0.0100 per million cached input tokens.
| Provider | Input $/M | Cached input $/M | Output $/M | Context in / out | TTFT p95 s | Output p5 c/s | Modalities in / out |
|---|---|---|---|---|---|---|---|
 OpenAI | $0.100 | $0.0100 | $0.500 | 1.1M/128.0K | — | — | / |
Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests.
GPT-6 Luna context window
Input and output token limits for GPT-6 Luna, plus how it ranks on long-context understanding.
Try now
huggleMake it with
GPT-6 Luna.
GPT-6 Luna latency
GPT-6 Luna time to first token, sustained output throughput, and failed-request rate from live model usage over the trailing 7 days.
GPT-6 Luna examples
Recent arena outputs from GPT-6 Luna, picked from the highest-ranked matchups.
GPT-6 Luna license
GPT-6 Luna is a proprietary model available under its provider's product and API terms, has a knowledge cutoff of May 2026.
- License
- Proprietary
- Hosted access
- Knowledge cutoff
- May 2026
Proprietary license - usage restrictions apply
GPT-6 Luna resources
Official sources for GPT-6 Luna: provider documentation, official playground, paper or system card, official launch post.
GPT-6 Luna vs other models
The most-compared alternatives to GPT-6 Luna are Qwen3.8-Flash-Next, Qwen3.8 Flash, GPT-5.5. Open any pair side-by-side for benchmarks, pricing, context, and latency.
Models like GPT-6 Luna
Models ranked just above and below GPT-6 Luna by LLM Stats score.
FAQ
Common questions about GPT-6 Luna.