菜单
The OpenAI REST API. Please see https://platform.openai.com/docs/api-reference for more details. Invoke any endpoint via `dnx tryAGI.OpenAI.CLI <group> <command>`. Requires an API key in `$OPENAI_API_KEY`.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | tryagi-openai |
| description | The OpenAI REST API. Please see https://platform.openai.com/docs/api-reference for more details. Invoke any endpoint via `dnx tryAGI.OpenAI.CLI <group> <command>`. Requires an API key in `$OPENAI_API_KEY`. |
The OpenAI REST API. Please see https://platform.openai.com/docs/api-reference for more details.
# one-time: save your API key
dnx tryAGI.OpenAI.CLI auth set <your-key>
# run a command
dnx tryAGI.OpenAI.CLI <group> <command> [options]
# explore
dnx tryAGI.OpenAI.CLI --help
dnx tryAGI.OpenAI.CLI <group> --help
| Group | Operations | Summary |
|---|---|---|
assistant | 18 | Build Assistants that can call models and use tools. |
audio | 9 | Turn audio into text or text into audio. |
audit-log | 1 | List user actions and configuration changes within this organization. |
batch | 4 | Create large batches of API requests to run asynchronously. |
certificate | 10 | |
chat | 6 | Given a list of messages comprising a conversation, the model will return a response. |
completion | 1 | Given a prompt, the model will return one or more predicted completions, and can also return the probabilities of alternative tokens at each position. |
conversation | 8 | Manage conversations and conversation items. |
data-retention | 4 | |
embedding | 1 | Get a vector representation of a given input that can be easily consumed by machine learning models and algorithms. |
eval | 12 | Manage and run evals in the OpenAI platform. |
file | 5 | Files are used to upload documents that can be used with features like Assistants and Fine-tuning. |
fine-tuning | 13 | Manage fine-tuning jobs to tailor a model to your specific training data. |
group | 5 | |
group-organization-role-assignment | 4 | |
group-user | 4 | |
hosted-tool | 2 | |
image | 3 | Given a prompt and/or an input image, the model will generate a new image. |
invite | 4 | |
model | 3 | List and describe the various models available in the API. |
moderation | 1 | Given text and/or image inputs, classifies if those inputs are potentially harmful. |
project | 23 | |
project-group | 4 | |
project-group-role-assignment | 4 | |
project-user-role-assignment | 4 | |
realtime | 9 | |
response | 10 | |
role | 10 | |
skill | 11 | |
spend-alert | 10 | |
upload | 4 | Use Uploads to upload large files in multiple parts. |
usage | 11 | |
user | 4 | |
user-organization-role-assignment | 4 | |
vector-store | 16 | |
video | 10 | |
default | 24 |
The bundled CLI also prints any of these on demand:
dnx tryAGI.OpenAI.CLI skill # SKILL.md
dnx tryAGI.OpenAI.CLI skill commands # commands.md
dnx tryAGI.OpenAI.CLI skill auth # auth.md
dnx tryAGI.OpenAI.CLI skill list # list bundled skill files
When the user asks to perform an operation against this API:
dnx tryAGI.OpenAI.CLI auth show. If source: none, ask the user for their key.--json to get structured output for downstream parsing.--help on the group rather than guessing.