web_searchfile_searchimage_generationcode_interpreterhosted_shellapply_patchskillscomputer_usemcptool_searchhttps://api.openai.com/v1/chat/completionshttps://api.openai.com/v1/responseshttps://api.openai.com/v1/batches| Input | Output | Cached input | 30m write | 12h write | Cache writes | |
|---|---|---|---|---|---|---|
| Standard | $0.1 | $0.5 | $0.01 | $0.125 | $0.25 | $0.125 |
| Batch | $0.05 | $0.25 | $0.005 | $0.0625 | $0.125 | — |
| Fast | $0.2 | $1 | $0.02 | $0.25 | $0.5 | — |
| Model | Context | Max out | Pricing |
|---|---|---|---|
| GPT-6 Luna | 1.1M | 128K | $0.1$0.5 |
| GPT-6 Sol | 1.1M | 128K | $2$10 |
| GPT-6 Astra | 1.1M | 128K | $10$50 |
/v1/models/openai/gpt-6-lunaGPT-6 Luna is our most efficient model for focused, high-volume tasks.