GPT-5.6 Luna benchmarks, pricing and specs
GPT-5.6 Luna is an OpenAI model released on July 9, 2026 that takes text and image input and produces text. It costs $0.20 per 1M input tokens and $1.20 per 1M output tokens and accepts up to 1,050,000 tokens of context. It scores 1452 Elo on Arena Text, #29 of 39 current models (Arena, measured October 8, 2026).
- Per 1M input tokens
- $0.20
- Per 1M output tokens
- $1.20
- Context window
- 1.05M
- Arena Text
- 1452 Elo · #29/39
Data verified October 12, 2026 · Dataset 2026-10-12
Key facts
- Provider
- OpenAI
- Model family
- GPT-5.6
- Release date
- July 9, 2026
- Status
- Current
- Access
- API only
- API model id
- Not reported
- Context window
- 1,050,000 tokens
- Max output
- 128,000 tokens
- Input
- text, image
- Output
- text
- Task families
- text, multimodal
- Declared capabilities
- reasoning
GPT-5.6 Luna pricing
It is the #4 cheapest of 37 current text models priced per 1M input tokens.
Independent benchmark results
Scores come from independent evaluators that ran the model themselves, pinned to a dated snapshot. Rank is among current models in the same snapshot. OpenAI's own launch figures are listed under strengths with the publisher named, because they are not measured the same way.
| Benchmark | Score | Rank | Measured | Source |
|---|---|---|---|---|
| Arena Text | 1452 Elo | #29 of 39 | October 8, 2026 | Arena · 2026-10-12 |
| GPQA Diamond | 91.6% | #19 of 37 | October 12, 2026 | Epoch AI · 2026-10-12 |
| FrontierMath Tiers 1-3 (v2) | 82.1% | #12 of 37 | October 12, 2026 | Epoch AI · 2026-10-12 |
| SimpleQA Verified | 41% | #26 of 34 | October 12, 2026 | Epoch AI · 2026-10-12 |
Strengths, cautions and best uses
Strengths
- GPT-5.6 Luna is optimized for cost-sensitive workloads at $0.20 input and $1.20 output per 1M tokens
- Keeps the 1.05M-token context, 128K output, six effort levels and full tool set of the larger GPT-5.6 tiers
- Epoch AI measured 91.6% on GPQA Diamond and 82.1% on FrontierMath Tiers 1-3, strong for its price
Cautions
- Not in the pinned LiveBench snapshot; its independent scores here come from Epoch AI's own GPQA Diamond, FrontierMath and SimpleQA Verified runs
Best for
- High-volume API evaluation with published low token prices
- Subagents and batch reasoning where cost per call dominates
Alternatives to GPT-5.6 Luna
The closest current textmodels by price. The cheapest model that scores as well or better is listed first; failing that, the cheapest one within 3% of the benchmark's scale.
Cheaper, similar score
GPT-6 Luna
- 50% cheaper per 1M input tokens, $0.10 vs $0.20
- 9 points lower on Arena Text, 1443 vs 1452
Gemini 3.1 Flash-Lite
- 25% more per 1M input tokens, $0.25 vs $0.20
- 9.8 points lower on GPQA Diamond, 81.8 vs 91.6
- From Google
DeepSeek-V4.1-Flash
- 50% more per 1M input tokens, $0.30 vs $0.20
- 23 points higher on Arena Text, 1475 vs 1452
- From DeepSeek
Gemini 3.5 Flash-Lite
- 50% more per 1M input tokens, $0.30 vs $0.20
- 3 points higher on Arena Text, 1455 vs 1452
- From Google
Compare GPT-5.6 Luna with
Articles about GPT-5.6 Luna
Other GPT-5.6 models
GPT-5.6 Luna FAQ
How much does GPT-5.6 Luna cost?
GPT-5.6 Luna costs $0.20 per 1M input tokens and $1.20 per 1M output tokens at the standard tier. It is the #4 cheapest of 37 current text models priced per 1M input tokens. Source: OpenAI, verified August 7, 2026.
What is the context window of GPT-5.6 Luna?
GPT-5.6 Luna accepts up to 1,050,000 tokens of context. It can return up to 128,000 tokens in one response. That ranks #1 of 44 current text models by context length.
How does GPT-5.6 Luna score on independent benchmarks?
GPT-5.6 Luna scores 1452 Elo on Arena Text, #29 of 39 current models (Arena, measured October 8, 2026), 91.6% on GPQA Diamond, #19 of 37 current models (Epoch AI, measured October 12, 2026) and 82.1% on FrontierMath Tiers 1-3 (v2), #12 of 37 current models (Epoch AI, measured October 12, 2026). These are independent evaluations, not OpenAI's own launch figures.
Is GPT-5.6 Luna open source or API only?
GPT-5.6 Luna is available through OpenAI's API only; its weights are not published.
What are the best alternatives to GPT-5.6 Luna?
The closest current alternatives by price and measured performance are GPT-6 Luna (50% cheaper per 1M input tokens, $0.10 vs $0.20), Gemini 3.1 Flash-Lite (25% more per 1M input tokens, $0.25 vs $0.20), DeepSeek-V4.1-Flash (50% more per 1M input tokens, $0.30 vs $0.20) and Gemini 3.5 Flash-Lite (50% more per 1M input tokens, $0.30 vs $0.20).
Sources
- GPT-5.6: Frontier intelligence that scales with your ambition · OpenAI · official · verified August 7, 2026
- OpenAI GPT-5.6 model catalog · OpenAI · official · verified August 7, 2026
- GPT-5.6 Luna model · OpenAI · official · verified October 12, 2026
- Epoch AI Benchmarking Hub data (benchmark_data.zip) · Epoch AI · independent · verified October 12, 2026 · CC-BY-4.0
- Arena leaderboard dataset (lmarena-ai/leaderboard-dataset) · Arena · independent · verified October 12, 2026 · CC-BY-4.0
Cite this page
Van Data Team. "GPT-5.6 Luna Benchmarks, Pricing and Specs." AI Model Benchmark Dataset 2026-10-12. https://vandatateam.com/ai-model-benchmarks/gpt-5-6-luna
Reuse the data: JSON · CSV · or explore every model in the AI model benchmark comparison.
Production evaluation
Deciding whether GPT-5.6 Luna fits your workload?
Public benchmarks narrow the shortlist. We test the finalists on your own tasks, data and cost limits, then build the routing and review controls to run the winner in production.
- Evaluation cases and acceptance thresholds tied to real work
- Model routing, fallbacks and cost controls