# GPT-5.6 Luna Usage, Cost & Rank | OpenCode Data

> GPT-5.6 Luna ranked #18 by tokens across OpenCode last week, with 0.7% of tokens over the past two months. GPT-5.6 Luna costs $0.20 per 1M input tokens and $1.20 per 1M output tokens.

Cost-efficient GPT-5.6 model for fast, high-volume workloads

- Page: https://opencode.ai/data/openai/gpt-5-6-luna
- JSON: https://opencode.ai/data/openai/gpt-5-6-luna.json
- Model ID: openai/gpt-5.6-luna
- Lab: OpenAI
- Updated: 2026-10-02T08:39:37.000Z

## Model facts

| Fact | Value |
| --- | --- |
| Context window | 1.1M |
| Max output | 128K |
| Knowledge cutoff | 2026-02-16 |
| Release date | 2026-07-09 |
| Input modalities | text, image, pdf |
| Output modalities | text |
| Reasoning | Yes |
| Tool calling | Yes |
| Open weights | No |

## Pricing: USD per 1M tokens

| Input | Output | Cached input | Cache write |
| --- | --- | --- | --- |
| $0.20 | $1.20 | $0.02 | $0.25 |

## OpenCode usage: past 2 months

| Metric | Value |
| --- | --- |
| Rank by tokens last week | #18 |
| Tokens | 6.4T |
| Share of all tokens | 0.7% |
| Change vs previous 2 months | +406% |
| Unique users | 602K |
| Completed sessions | 2,078,163 |
| Average tokens per session | 3.1M |
| Average cost per session | $0.1591 |
| Total spend | $330,733 |
| Input tokens served from cache | 99.4% |
| Weekly retention | 55.0% |

## Daily usage: past 2 months

| Date | Tokens | Unique users | Sessions |
| --- | --- | --- | --- |
| 2026-08-08 | 175B | 12K | 31,621 |
| 2026-08-09 | 153B | 10K | 32,735 |
| 2026-08-10 | 242B | 15K | 46,240 |
| 2026-08-11 | 242B | 21K | 22,006 |
| 2026-08-12 | 248B | 17K | 7,207 |
| 2026-08-13 | 226B | 17K | 1,542 |
| 2026-08-14 | 213B | 17K | 1,529 |
| 2026-08-15 | 190B | 14K | 1,159 |
| 2026-08-16 | 207B | 15K | 1,179 |
| 2026-08-17 | 462B | 25K | 2,910 |
| 2026-08-18 | 380B | 22K | 59,303 |
| 2026-08-19 | 231B | 21K | 57,102 |
| 2026-08-20 | 165B | 18K | 35,718 |
| 2026-08-21 | 145B | 17K | 34,860 |
| 2026-08-22 | 101B | 12K | 25,278 |
| 2026-08-23 | 94B | 10K | 23,857 |
| 2026-08-24 | 145B | 13K | 33,914 |
| 2026-08-25 | 126B | 12K | 30,799 |
| 2026-08-26 | 118B | 12K | 28,881 |
| 2026-08-27 | 109B | 11K | 30,385 |
| 2026-08-28 | 88B | 9.5K | 28,180 |
| 2026-08-29 | 68B | 6.9K | 18,336 |
| 2026-08-30 | 65B | 6.4K | 18,675 |
| 2026-08-31 | 98B | 9.6K | 27,536 |
| 2026-09-01 | 89B | 9.3K | 23,853 |
| 2026-09-02 | 83B | 9.2K | 24,052 |
| 2026-09-03 | 81B | 9.2K | 25,320 |
| 2026-09-04 | 70B | 8.6K | 26,159 |
| 2026-09-05 | 59B | 6.3K | 24,660 |
| 2026-09-06 | 63B | 6.3K | 27,697 |
| 2026-09-07 | 93B | 9.1K | 59,020 |
| 2026-09-08 | 98B | 9.1K | 63,446 |
| 2026-09-09 | 92B | 8.8K | 49,570 |
| 2026-09-10 | 88B | 9.5K | 48,845 |
| 2026-09-11 | 70B | 8.3K | 44,756 |
| 2026-09-12 | 62B | 6.5K | 37,874 |
| 2026-09-13 | 59B | 6.4K | 40,328 |
| 2026-09-14 | 94B | 9.7K | 59,741 |
| 2026-09-15 | 94B | 9.7K | 54,851 |
| 2026-09-16 | 86B | 9.9K | 53,938 |
| 2026-09-17 | 86B | 10K | 65,757 |
| 2026-09-18 | 86B | 9.8K | 69,424 |
| 2026-09-19 | 67B | 8.9K | 65,742 |
| 2026-09-20 | 69B | 10K | 76,972 |
| 2026-09-21 | 100B | 15K | 106,193 |
| 2026-09-22 | 90B | 16K | 87,495 |
| 2026-09-23 | 72B | 14K | 80,753 |
| 2026-09-24 | 52B | 6.2K | 38,172 |
| 2026-09-25 | 36B | 4.5K | 26,616 |
| 2026-09-26 | 27B | 3.5K | 35,416 |
| 2026-09-27 | 24B | 3.4K | 20,129 |
| 2026-09-28 | 40B | 5K | 40,088 |
| 2026-09-29 | 35B | 4.9K | 30,866 |
| 2026-09-30 | 31B | 4.4K | 25,590 |
| 2026-10-01 | 29B | 3.9K | 32,388 |
| 2026-10-02 | 8.1B | 1.5K | 11,500 |

## Top countries: past 2 months

| Rank | Country | Tokens | Share |
| --- | --- | --- | --- |
| 1 | United States | 1.1T | 17.3% |
| 2 | Japan | 493B | 7.7% |
| 3 | Brazil | 394B | 6.1% |
| 4 | Germany | 328B | 5.1% |
| 5 | Singapore | 327B | 5.1% |
| 6 | India | 238B | 3.7% |
| 7 | Spain | 236B | 3.7% |
| 8 | Indonesia | 199B | 3.1% |
| 9 | France | 167B | 2.6% |
| 10 | Colombia | 164B | 2.6% |
| 11 | Argentina | 147B | 2.3% |
| 12 | United Kingdom | 145B | 2.3% |
| 13 | Mexico | 128B | 2% |
| 14 | Türkiye | 125B | 1.9% |
| 15 | Netherlands | 122B | 1.9% |

## Nearby models by tokens last week

| Rank | Model | Lab | Tokens |
| --- | --- | --- | --- |
| 14 | [mimo-v2.6-pro](https://opencode.ai/data/xiaomi/mimo-v2-6-pro.md) | Xiaomi | 464B |
| 15 | [nemotron-3.5-lightning](https://opencode.ai/data/nvidia/nemotron-3-5-lightning.md) | NVIDIA | 267B |
| 16 | [ling-3.0-flash-fin](https://opencode.ai/data/inclusionai/ling-3-0-flash-fin.md) | inclusionAI | 256B |
| 17 | [qwen3.8-flash](https://opencode.ai/data/alibaba/qwen3-8-flash.md) | Qwen | 256B |
| 18 | [gpt-5.6-luna](https://opencode.ai/data/openai/gpt-5-6-luna.md) | OpenAI | 195B |
| 19 | [minimax-m3](https://opencode.ai/data/minimax/minimax-m3.md) | MiniMax | 181B |
| 20 | [mai-experimental-test](https://opencode.ai/data/unknown/mai-experimental-test.md) | - | 180B |
| 21 | [kimi-k2.7-code](https://opencode.ai/data/moonshotai/kimi-k2-7-code.md) | Moonshot | 136B |
| 22 | [glm-5.3](https://opencode.ai/data/zhipuai/glm-5-3.md) | Zhipu | 95B |
| 23 | [fledge-alpha](https://opencode.ai/data/unknown/fledge-alpha.md) | - | 90B |

## Benchmarks

| Benchmark | Score | Metric | Source |
| --- | --- | --- | --- |
| SWE-Bench Pro | 62.7 | resolve rate | https://openai.com/index/gpt-5-6/ |
| Terminal-Bench | 84.7 | success rate | https://openai.com/index/gpt-5-6/ |
| DeepSWE | 67.2 | resolve rate | https://openai.com/index/gpt-5-6/ |
| GPQA Diamond | 92.3 | accuracy | https://openai.com/index/gpt-5-6/ |
| FrontierMath | 78.6 | accuracy | https://openai.com/index/gpt-5-6/ |
| BrowseComp | 83.3 | accuracy | https://openai.com/index/gpt-5-6/ |
| OSWorld | 45.6 | success rate | https://openai.com/index/gpt-5-6/ |
| MMMU Pro | 78.4 | accuracy | https://openai.com/index/gpt-5-6/ |
| Agents' Last Exam | 50.3 |  | https://openai.com/index/gpt-5-6/ |
| Toolathlon | 53.4 | success rate | https://openai.com/index/gpt-5-6/ |
| Artificial Analysis Intelligence Index | 51.2 | index score | https://artificialanalysis.ai/articles/gpt-5-6-has-landed |
| Artificial Analysis Coding Agent Index | 74.6 | index score | https://artificialanalysis.ai/articles/gpt-5-6-has-landed |

## Methodology

- Updates: Aggregated every hour. Days and weeks use UTC.
- Tokens: Input, output, reasoning, and cached tokens for each request.
- Users and sessions: Approximate counts of distinct users and OpenCode sessions.
- Cost: Session cost is the average cost per OpenCode session. Token prices are list prices from the OpenCode model catalog.
- Retention: The share of a model's users in one week who use it again the next week.
- Citation: Cite OpenCode Data (opencode.ai/data) with the update time shown at the top of the page.