- Reasoning - Responses API . - Decisions API . - Multi-agent orchestration (preview). - Chat Completions API. - Streaming. - Structured outputs. - Text and image input with text output. - Functions, tools, and parallel tool calling. - Reasoning effort and verbosity. - Computer use - Full summary of capabilities .
function_calling| 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 |
|---|---|---|
| gpt-6-astra | 1.1M | 128K |
| gpt-6-luna | 1.1M | 128K |
| gpt-6-sol | 1.1M | 128K |
| GPT-6 series | — | — |
/v1/models/azure/gpt-6-luna- Reasoning - Responses API . - Decisions API . - Multi-agent orchestration (preview). - Chat Completions API. - Streaming. - Structured outputs. - Text and image input with text output. - Functions, tools, and parallel tool calling. - Reasoning effort and verbosity. - Computer use - Full summary of capabilities .