Model
GPT-5.6 Luna
Cost-efficient GPT-5.6 model for fast, high-volume workloads
13 providersreleased knowledge cutoff 2026-02-16closed weights
$0.1
best input /M · NanoGPT
$0.6
best output /M
1.05M
context window
128K
max output
Compare providers (sorted by listed input price)
| Provider | Input /M | Output /M | Cache read /M | Cache write /M | Context | Capabilities | Status | Updated |
|---|---|---|---|---|---|---|---|---|
| NanoGPT openai/gpt-5.6-luna | $0.1 | $0.6 | $0.01 | $0.125 | 1.05M | reasoningtoolsstructuredvision | Jul 9, 2026 | |
| Impossibl openai/gpt-5.6-luna | $0.2 | $1.20 | $0.02 | $0.25 | 1.05M | reasoningtoolsstructuredvision | Jul 9, 2026 | |
| OpenRouter openai/gpt-5.6-luna | $0.2 | $1.20 | $0.02 | $0.25 | 1.05M | reasoningtoolsstructuredvision | Jul 9, 2026 | |
| CrossModel openai/gpt-5.6-luna | $0.2 | $1.20 | $0.02 | $0.25 | 1.05M | reasoningtoolsstructuredvision | Jul 9, 2026 | |
| OpenAI gpt-5.6-luna | $0.2 | $1.20 | $0.02 | $0.25 | 1.05M | reasoningtoolsstructuredvision | Jul 9, 2026 | |
| LLM Gateway openai/gpt-5.6-luna | $0.2 | $1.20 | $0.02 | $0.25 | 1.05M | reasoningtoolsstructuredvision | Jul 9, 2026 | |
| Merge Gateway openai/gpt-5.6-luna | $0.2 | $1.20 | $0.02 | — | 1.05M | reasoningtoolsstructuredvision | Jul 9, 2026 | |
| Cloudflare AI Gateway openai/gpt-5.6-luna | $0.2 | $1.20 | $0.02 | $0.25 | 1.05M | reasoningtoolsstructuredvision | Jul 9, 2026 | |
| Ofox openai/gpt-5.6-luna | $0.2 | $1.20 | $0.02 | $0.25 | 1.05M | reasoningtoolsstructuredvision | Jul 9, 2026 | |
| Vercel AI Gateway openai/gpt-5.6-luna | $0.2 | $1.20 | $0.02 | $0.25 | 1.05M | reasoningtoolsstructuredvision | Jul 9, 2026 | |
| Eden AI openai/gpt-5.6-luna | $0.2 | $1.20 | $0.02 | $0.25 | 1.05M | reasoningtoolsstructuredvision | Jul 9, 2026 | |
| Kilo Gateway openai/gpt-5.6-luna | $0.2 | $1.20 | $0.02 | $0.25 | 1.05M | reasoningtoolsstructuredvision | Jul 9, 2026 | |
| ZenMux openai/gpt-5.6-luna | $1 | $6 | $0.1 | $1.25 | 1.05M | reasoningtoolsstructuredvision | Jul 9, 2026 |
Price badge
https://models.sutraworks.ai/badge/openai/gpt-5.6-luna.svgLive SVG, regenerated on every hourly sync — paste it into a README to always show the current cheapest listed price. Updates when prices change; no build step needed on your side.
Benchmarks
- SWE-Bench Pro ↗(resolve rate)report ↗62.7
- Terminal-Bench ↗(success rate)report ↗84.7
- DeepSWE(resolve rate)report ↗67.2
- GPQA Diamond ↗(accuracy)report ↗92.3
- FrontierMath ↗(accuracy)report ↗78.6
- BrowseComp ↗(accuracy)report ↗83.3
- OSWorld ↗(success rate)report ↗45.6
- MMMU Pro ↗(accuracy)report ↗78.4
- Agents' Last Examreport ↗50.3
- Toolathlon(success rate)report ↗53.4
- Artificial Analysis Intelligence Index ↗(index score)report ↗51.2
- Artificial Analysis Coding Agent Index ↗(index score)report ↗74.6
Prices are per million tokens (USD). “—” means the provider does not publicly list a price for this model. Data from models.dev; verify with the provider before purchasing.