OpenAI: GPT-6 Luna (batch)
The OpenAI GPT-6 Luna model is a batch processing system that supports three input modalities: file, image, and text. It has a large context length of 1 million characters and can handle up to 128,000 completion tokens. The model also supports various tools and has reasoning capabilities. This model may be suitable for users who need to process multiple input types and have a budget that accommodates its moderate pricing: $0.05 per input token and $0.25 per output token. Its blended benchmark score of 62.2 across one independent benchmark indicates average performance, making it a potential option for those seeking a balance between price and capability.
Benchmark results
Independent, published benchmarks. Blended score 62.2 across 1 benchmark, last refreshed 2026-09-23. How scoring works →
| Benchmark | Measures | Score |
|---|---|---|
| AI Index | broad capability composite | 61.5 |
- Model ID
- openai/gpt-6-luna:batch
- Vendor
- openai
- Released
- September 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 $0.05/M input and $0.25/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 | $0.04 |
| A month of a busy support chatbot | 5M in / 2M out | $0.75 |
Strong choice for
Category rankings
Where OpenAI: GPT-6 Luna (batch) places across the 20 categories it ranks in. How we rank →
| # | Category | Score |
|---|---|---|
| #2 | Real-Time ChatLatency · of 25 ranked | 118 |
| #8 | Self-Hosted / LocalCost · of 25 ranked | 117 |
| #11 | Short-Form SummarizationWriting · of 25 ranked | 127 |
| #11 | Email DraftingWriting · of 25 ranked | 123 |
| #11 | Language LearningEducation · of 25 ranked | 123 |
| #11 | Image CaptioningVision · of 25 ranked | 120 |
| #11 | Chat CompanionPersonal · of 25 ranked | 127 |
| #12 | Code CompletionCode · of 25 ranked | 133 |
| #14 | Cheap Bulk InferenceCost · of 25 ranked | 137 |
| #15 | Social Media PostsWriting · of 25 ranked | 119 |
| #15 | Voice Assistant BackendVoice · of 25 ranked | 123 |
| #15 | Trivia & General KnowledgePersonal · of 25 ranked | 117 |
| #17 | Bulk Data LabelingData · of 25 ranked | 129 |
| #18 | Sales / Cold EmailBusiness · of 25 ranked | 119 |
| #18 | Job Application DraftingBusiness · of 25 ranked | 119 |
| #18 | Journaling HelperPersonal · of 25 ranked | 119 |
| #18 | Recipe GenerationPersonal · of 25 ranked | 119 |
| #18 | Dataset AnnotationResearch · of 25 ranked | 133 |
| #22 | JSON ExtractionData · of 25 ranked | 131 |
| #24 | Customer SupportBusiness · of 25 ranked | 127 |
Similar models
OpenAI: GPT-6 Luna Pro
OpenAI: GPT-6 Luna Pro (batch)
OpenAI: GPT-6 Luna
OpenAI: GPT-6 Sol Pro
OpenAI: GPT-6 Sol Pro (batch)
OpenAI: GPT-6 Sol
Quick answers
- How much does OpenAI: GPT-6 Luna (batch) cost?
- $0.05 per million input tokens and $0.25 per million output tokens.
- What is OpenAI: GPT-6 Luna (batch)'s context window?
- 1,050,000 tokens, roughly 1,575 pages of text in a single request.
- Does OpenAI: GPT-6 Luna (batch) support tool calling?
- It supports tool calling, structured output, a reasoning mode.
- Can OpenAI: GPT-6 Luna (batch) process images?
- Yes, it accepts image input.