Push Prompt

(v2)

POST

Creates a new commit for the prompt with the given alias, creating the prompt first when it does not exist. Send text for a text prompt or messages for a messages prompt, not both.

POST/v2/prompts

curl -X POST "https://api.confident-ai.com/v2/prompts" \
  -H "CONFIDENT_API_KEY: <PROJECT-API-KEY>" \
  -H "Content-Type: application/json" \
  -d '{
  "text": "Hello, {{name}}! How can I help you today?",
  "alias": "greeting",
  "interpolationType": "MUSTACHE",
  "modelSettings": {
    "provider": "OPEN_AI",
    "name": "gpt-4o",
    "temperature": 0.7,
    "maxTokens": 1024,
    "topP": 1,
    "topK": 40,
    "frequencyPenalty": 0,
    "presencePenalty": 0,
    "stopSequence": [
      "\n\nHuman:",
      "###"
    ],
    "reasoningEffort": "MINIMAL",
    "verbosity": "LOW"
  },
  "outputType": "TEXT",
  "outputSchema": {
    "title": "Greeting",
    "type": "object",
    "properties": {
      "greeting": {
        "type": "string"
      }
    },
    "required": [
      "greeting"
    ],
    "additionalProperties": false
  },
  "tools": [
    {
      "id": "<TOOL-ID>",
      "version": "00.00.01"
    }
  ],
  "branch": "main",
  "imagesMapping": {}
}'

200

{
  "success": true,
  "data": {
    "promptId": "<PROMPT-ID>",
    "hash": "bab04ce"
  },
  "link": "https://app.confident-ai.com/project/<PROJECT-ID>/prompt-studio/<PROMPT-ID>?branch=<BRANCH-NAME>",
  "deprecated": false
}

Headers

CONFIDENT_API_KEYstringRequired
The API key of your Confident AI project.

Request body

Text Prompt Inputobject
Pushes a commit to a text prompt. interpolationType defaults to FSTRING when omitted.
Show 9 propertiesHide 9 properties
- textstringRequired
  The text content of the prompt.
- aliasstringRequired
  The alias of the prompt, unique within your project. A new prompt is created when no prompt with this alias exists.
- interpolationTypeenum
  The type of interpolation format used in the prompt to insert dynamic variables.
  Show 5 enum valuesHide 5 enum values
  - MUSTACHE
  - MUSTACHE_WITH_SPACE
  - FSTRING
  - DOLLAR_BRACKETS
  - JINJA
- modelSettingsobject
  This is the model settings the prompt was authored for.
  Show 11 propertiesHide 11 properties
  - providerenum
    This is the provider of the model.
    Show 21 enum valuesHide 21 enum values
    OPEN_AI
    CUSTOM
    CONFIDENT_AI
    BEDROCK
    ANTHROPIC
    GEMINI
    X_AI
    DEEPSEEK
    MOONSHOT_AI
    VERTEX_AI
    AZURE
    MISTRAL
    PERPLEXITY
    OPEN_ROUTER
    PORTKEY
    LITE_LLM
    TRUE_FOUNDRY
    HUGGING_FACE
    TYPE_SAFE
    FAL
    Z_AI
  - namestring
    This is the name of the model.
  - temperaturenumber
    This controls randomness in the model's output. Higher values make output more random.
  - maxTokensnumber
    This is the maximum number of tokens to generate.
  - topPnumber
    This controls diversity via nucleus sampling. Lower values focus on more likely tokens.
  - topKnumber
    This limits sampling to the K most likely tokens at each step.
  - frequencyPenaltynumber
    This is the penalty for tokens based on their frequency in the text so far.
  - presencePenaltynumber
    This is the penalty for tokens based on whether they appear in the text so far.
  - stopSequencelist of strings
    This is the sequences where the model will stop generating further tokens.
  - reasoningEffortenum
    This is the level of reasoning effort for the model.
    Show 4 enum valuesHide 4 enum values
    MINIMAL
    LOW
    MEDIUM
    HIGH
  - verbosityenum
    This is the verbosity level for model output.
    Show 3 enum valuesHide 3 enum values
    LOW
    MEDIUM
    HIGH
- outputTypeenum
  The type of output expected from the prompt.
  Show 3 enum valuesHide 3 enum values
  - TEXT
  - JSON
  - SCHEMA
- outputSchemaobject
  The JSON Schema the prompt's output must match, used when outputType is SCHEMA. It can describe objects (properties and required), arrays (items), and string, integer, number, boolean and null values. title names it, additionalProperties can only be false, and any other keyword is rejected.
- toolslist of objects
  The tools available to the prompt. The commit pins each one at a version.
  Show 6 propertiesHide 6 properties
  - idstring
    The id of an existing tool. Omit it to use name instead.
  - versionstring
    The version to pin. Omit it to use the latest version.
  - namestring
    The name of the tool. Without id, the tool with this name is used or created; with id, a new name renames it.
  - descriptionstring | null
    What the tool does.
  - modeenum
    This is the mode for your tool input fields, which controls whether fields outside the schema are allowed.
    Show 3 enum valuesHide 3 enum values
    ALLOW_ADDITIONAL
    NO_ADDITIONAL
    STRICT
  - schemaobject
    The JSON Schema for the tool's input. List each parameter under properties with a type, and name the mandatory ones in required. A parameter can also have a description, an enum of allowed values, or items for an array. Whether extra properties are allowed is set by mode.
- branchstring
  The name of the branch to push the new commit to. The branch is created from main when it does not exist yet.
- imagesMappingobject
  Images placed in the prompt's text or message contents with [CONFIDENT:IMAGE:<key>] markers, keyed by each marker's <key>. When you send it, Confident AI stores its own copy of every image the prompt contains; without it, the prompt is stored as sent.
OR
Messages Prompt Inputobject
Pushes a commit to a messages prompt. interpolationType defaults to FSTRING when omitted.
Show 9 propertiesHide 9 properties
- messageslist of objectsRequired
  The list of messages that make up the prompt.
  Show 4 propertiesHide 4 properties
  - rolestringRequired
    This is the role of the message, which can be user, assistant, system, or developer.
  - contentstringRequired
    This is the text content of the message.
  - tool_callslist of objects
    Tool calls made by an assistant message, in the OpenAI chat format.
    Show 3 propertiesHide 3 properties
    idstringRequired
    typeenumRequired
    Show 1 enum valueHide 1 enum value
    function
    functionobjectRequired
    Show 2 propertiesHide 2 properties
    namestringRequired
    argumentsstringRequired
    JSON-encoded arguments passed to the tool.
  - tool_call_idstring
    For tool messages, the id of the assistant tool call this result answers.
- aliasstringRequired
  The alias of the prompt, unique within your project. A new prompt is created when no prompt with this alias exists.
- interpolationTypeenum
  The type of interpolation format used in the prompt to insert dynamic variables.
  Show 5 enum valuesHide 5 enum values
  - MUSTACHE
  - MUSTACHE_WITH_SPACE
  - FSTRING
  - DOLLAR_BRACKETS
  - JINJA
- modelSettingsobject
  This is the model settings the prompt was authored for.
  Show 11 propertiesHide 11 properties
  - providerenum
    This is the provider of the model.
    Show 21 enum valuesHide 21 enum values
    OPEN_AI
    CUSTOM
    CONFIDENT_AI
    BEDROCK
    ANTHROPIC
    GEMINI
    X_AI
    DEEPSEEK
    MOONSHOT_AI
    VERTEX_AI
    AZURE
    MISTRAL
    PERPLEXITY
    OPEN_ROUTER
    PORTKEY
    LITE_LLM
    TRUE_FOUNDRY
    HUGGING_FACE
    TYPE_SAFE
    FAL
    Z_AI
  - namestring
    This is the name of the model.
  - temperaturenumber
    This controls randomness in the model's output. Higher values make output more random.
  - maxTokensnumber
    This is the maximum number of tokens to generate.
  - topPnumber
    This controls diversity via nucleus sampling. Lower values focus on more likely tokens.
  - topKnumber
    This limits sampling to the K most likely tokens at each step.
  - frequencyPenaltynumber
    This is the penalty for tokens based on their frequency in the text so far.
  - presencePenaltynumber
    This is the penalty for tokens based on whether they appear in the text so far.
  - stopSequencelist of strings
    This is the sequences where the model will stop generating further tokens.
  - reasoningEffortenum
    This is the level of reasoning effort for the model.
    Show 4 enum valuesHide 4 enum values
    MINIMAL
    LOW
    MEDIUM
    HIGH
  - verbosityenum
    This is the verbosity level for model output.
    Show 3 enum valuesHide 3 enum values
    LOW
    MEDIUM
    HIGH
- outputTypeenum
  The type of output expected from the prompt.
  Show 3 enum valuesHide 3 enum values
  - TEXT
  - JSON
  - SCHEMA
- outputSchemaobject
  The JSON Schema the prompt's output must match, used when outputType is SCHEMA. It can describe objects (properties and required), arrays (items), and string, integer, number, boolean and null values. title names it, additionalProperties can only be false, and any other keyword is rejected.
- toolslist of objects
  The tools available to the prompt. The commit pins each one at a version.
  Show 6 propertiesHide 6 properties
  - idstring
    The id of an existing tool. Omit it to use name instead.
  - versionstring
    The version to pin. Omit it to use the latest version.
  - namestring
    The name of the tool. Without id, the tool with this name is used or created; with id, a new name renames it.
  - descriptionstring | null
    What the tool does.
  - modeenum
    This is the mode for your tool input fields, which controls whether fields outside the schema are allowed.
    Show 3 enum valuesHide 3 enum values
    ALLOW_ADDITIONAL
    NO_ADDITIONAL
    STRICT
  - schemaobject
    The JSON Schema for the tool's input. List each parameter under properties with a type, and name the mandatory ones in required. A parameter can also have a description, an enum of allowed values, or items for an array. Whether extra properties are allowed is set by mode.
- branchstring
  The name of the branch to push the new commit to. The branch is created from main when it does not exist yet.
- imagesMappingobject
  Images placed in the prompt's text or message contents with [CONFIDENT:IMAGE:<key>] markers, keyed by each marker's <key>. When you send it, Confident AI stores its own copy of every image the prompt contains; without it, the prompt is stored as sent.

Response

Push Prompt succeeded.

successboolean
Indicates if the request was successful.
dataobject
Show 2 propertiesHide 2 properties
- promptIdstring
  This is the id of the prompt generated by Confident AI, not to be confused with the alias you supplied.
- hashstring
  This is the hash of the commit created by this push, not to be confused with a version number.
linkstring
This is the URL of the resource on the Confident AI platform.
deprecatedboolean
Indicates if this endpoint is deprecated.

Built byConfident AI