GPT-5.6 Terra is designed for workloads that balance intelligence and cost. It roughly corresponds to the mini model tier used in earlier GPT-5 families. Reasoning.effort supports: none, low, medium (default), high, xhigh, and max.
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 | |
|---|---|---|---|---|---|
| Standard | $2 | $12 | $0.2 | $2.5 | $5 |
| Batch | $1 | $6 | $0.1 | $1.25 | $2.5 |
| Fast | $4 | $24 | $0.4 | $5 | $10 |
| Model | Context | Max out | Pricing |
|---|---|---|---|
| GPT-5.6 Luna | 1.1M | 128K | $0.2$1.2 |
| GPT-5.6 Terra | 1.1M | 128K | $2$12 |
| GPT-5.6 Sol | 1.1M | 128K | $4$20 |
| GPT-5.6 Cyber | 400K | 128K | $12.5$75 |
/v1/models/openai/gpt-5.6-terraGPT-5.6 Terra is designed for workloads that balance intelligence and cost. It roughly corresponds to the mini model tier used in earlier GPT-5 families. Reasoning.effort supports: none, low, medium (default), high, xhigh, and max.