OpenAI: GPT-5.6 Luna (batch)
GPT-5.6 Luna from OpenAI is designed to handle text, file, and image inputs with a context length of 1,050,000 tokens, supporting both reasoning and tool usage. It excels in coding tasks, achieving a perfect score in its benchmark suite. However, it lacks structured output support and does not offer open weights for customization. While GPT-5.6 Luna offers robust capabilities at a price point of $0.1 per million input tokens and $0.6 per million output tokens, making it cost-effective for projects requiring extensive text processing and reasoning, its current blended benchmark score of 88.2 across three independent benchmarks suggests that it may be more suited for applications where coding is the primary focus rather than general agentic AI tasks.
Benchmark results
Independent, published benchmarks. Blended score 88.2 across 3 benchmarks, last refreshed 2026-08-13. How scoring works →
| Benchmark | Measures | Score |
|---|---|---|
| AI Index | broad capability composite | 86.3 |
| AI Index Coding | software engineering tasks | 100.0 |
| AI Index Agentic | multi-step tool-using tasks | 77.4 |
- Model ID
- openai/gpt-5.6-luna:batch
- Vendor
- openai
- Released
- July 2026
- Tokenizer
- GPT
- Input Modalities
- file, image, text
- Output Modalities
- text
- Max Output
- 128,000 tokens
- Tool Calling
- ✓ supported
- Structured Output
- ✓ supported
- Reasoning Mode
- ✓ supported
- Vision
- ✓ accepts images
- Audio
- no
- Moderated
- yes
What it costs in practice
Computed from the current $0.10/M input and $0.60/M output rates. Run your own numbers →
| Job | Tokens | Cost |
|---|---|---|
| Summarize a 50-page report | 30k in / 1.5k out | under $0.01 |
| Classify 1,000 customer emails | 500k in / 50k out | $0.08 |
| A month of a busy support chatbot | 5M in / 2M out | $1.70 |
Strong choice for
JSON Extraction
Bulk Data Labeling
Short-Form Summarization
Email Drafting
Language Learning
Customer Support
Category rankings
Where OpenAI: GPT-5.6 Luna (batch) places across the 39 categories it ranks in. How we rank →
| # | Category | Score |
|---|---|---|
| #2 | Bulk Data LabelingData · of 25 ranked | 135 |
| #2 | Short-Form SummarizationWriting · of 25 ranked | 132 |
| #2 | Email DraftingWriting · of 25 ranked | 128 |
| #2 | Language LearningEducation · of 25 ranked | 128 |
| #2 | Customer SupportBusiness · of 25 ranked | 135 |
| #2 | Chat CompanionPersonal · of 25 ranked | 132 |
| #2 | Trivia & General KnowledgePersonal · of 25 ranked | 122 |
| #2 | Dataset AnnotationResearch · of 25 ranked | 145 |
| #3 | JSON ExtractionData · of 25 ranked | 149 |
| #3 | Image CaptioningVision · of 25 ranked | 121 |
| #4 | Sales / Cold EmailBusiness · of 25 ranked | 124 |
| #4 | Job Application DraftingBusiness · of 25 ranked | 124 |
| #4 | Journaling HelperPersonal · of 25 ranked | 124 |
| #4 | Recipe GenerationPersonal · of 25 ranked | 124 |
| #8 | Code CompletionCode · of 25 ranked | 133 |
| #11 | Resume WritingBusiness · of 25 ranked | 118 |
| #13 | Social Media PostsWriting · of 25 ranked | 119 |
| #13 | Voice Assistant BackendVoice · of 25 ranked | 123 |
| #14 | Regex WritingCode · of 25 ranked | 137 |
| #14 | Language TranslationWriting · of 25 ranked | 137 |
| #14 | Tutoring for KidsPersonal · of 25 ranked | 137 |
| #15 | SOP / Process DocsBusiness · of 25 ranked | 138 |
| #16 | Meeting NotesBusiness · of 25 ranked | 152 |
| #18 | Code DocumentationCode · of 25 ranked | 143 |
| #19 | CSV / Spreadsheet CleanupData · of 25 ranked | 154 |
| #19 | Function / Tool CallingAgents · of 25 ranked | 154 |
| #19 | Self-Hosted / LocalCost · of 25 ranked | 117 |
| #22 | Screenshot DebuggingVision · of 25 ranked | 142 |
| #22 | Real-Time ChatLatency · of 25 ranked | 117 |
| #23 | Marketing CopyWriting · of 25 ranked | 131 |
| #23 | Standardized Test PrepEducation · of 25 ranked | 131 |
| #23 | Diagram ExtractionVision · of 25 ranked | 149 |
| #24 | Frontend Component DesignCode · of 25 ranked | 146 |
| #24 | Chart & Graph ReadingVision · of 25 ranked | 152 |
| #24 | Browser AutomationAgents · of 25 ranked | 171 |
| #24 | Cheap Bulk InferenceCost · of 25 ranked | 137 |
| #25 | SQL GenerationCode · of 25 ranked | 172 |
| #25 | OCR / Document ParsingData · of 25 ranked | 146 |
| #25 | Table Extraction from PDFsData · of 25 ranked | 146 |
Similar models
OpenAI: GPT-5.6 Luna Pro
OpenAI: GPT-5.6 Luna Pro (batch)
OpenAI: GPT-5.6 Luna
OpenAI: GPT-5.6 Terra Pro
OpenAI: GPT-5.6 Terra Pro (batch)
OpenAI: GPT-5.6 Terra
Quick answers
- How much does OpenAI: GPT-5.6 Luna (batch) cost?
- $0.10 per million input tokens and $0.60 per million output tokens.
- What is OpenAI: GPT-5.6 Luna (batch)'s context window?
- 1,050,000 tokens, roughly 1,575 pages of text in a single request.
- Does OpenAI: GPT-5.6 Luna (batch) support tool calling?
- It supports tool calling, structured output, a reasoning mode.
- Can OpenAI: GPT-5.6 Luna (batch) process images?
- Yes, it accepts image input.