Skip to Content

Update, commit, or deploy prompts in bulk

POSThttps://api.respan.ai/api/prompts/bulk/

Process 1 to 100 prompt operations sequentially in request order using exact prompt_id matching. Each item runs in its own transaction, so a failed item is rolled back without undoing successful items. update changes model configuration on the latest draft and does not accept content fields such as messages, variables, or description; commit snapshots the latest draft; deploy promotes the latest committed version. A later duplicate successful commit or deploy for the same prompt in one request is returned as an indexed error. This endpoint inherits the caller’s configured API-key or JWT rate limits; it has no fixed endpoint-specific RPM.

Servers

https://api.respan.ai: Respan API Server

Authentication

RespanApiKey

Use your Respan API key for Respan API authentication. Enter only the Respan API key value; clients send Authorization: Bearer <RESPAN_API_KEY>. For /api/responses, provider credentials such as Perplexity, OpenAI, or Azure OpenAI go in Settings -> Providers or respan_params.credential_override in the request body, not in this authentication field.

HTTP scheme: bearer; format: Respan API key.

HTTP
Authorization: Bearer $RESPAN_API_KEY

Or:

DashboardJwt

Use a dashboard JWT only for dashboard-authenticated endpoints. Respan API-key endpoints use the respanApiKey auth field instead.

HTTP scheme: bearer; format: Dashboard JWT.

HTTP
Authorization: Bearer $RESPAN_DASHBOARD_JWT

Request body

A request body is required.

application/json

Field Type Requirement Description and constraints
$ object Required body
Ordered prompt operations to process.
Reference: #/components/schemas/PromptBulkRequest
Additional properties are not allowed
requests array<object or object or object> Required in parent
Prompt operations. Error indices refer to this zero-based array.
Minimum items: 1
Maximum items: 100
requests[] object or object or object Array item
One action in a prompt bulk request.
Reference: #/components/schemas/PromptBulkRequestItem
Discriminator: {"propertyName":"action","mapping":{"update":"#/components/schemas/PromptBulkUpdateItem","commit":"#/components/schemas/PromptBulkCommitItem","deploy":"#/components/schemas/PromptBulkDeployItem"}}
requests[] (oneOf 1) object Schema variant
Update model configuration on the prompt’s latest draft.
Reference: #/components/schemas/PromptBulkUpdateItem
Additional properties are not allowed
requests[] (oneOf 1).prompt_id string Required in parent
Exact prompt ID to mutate.
Minimum length: 1
Maximum length: 70
requests[] (oneOf 1).action string Required in parent
Allowed: "update"
requests[] (oneOf 1).body object Required in parent
Non-empty model configuration changes for the latest draft. Prompt content fields are not accepted.
Reference: #/components/schemas/PromptBulkUpdateBody
Minimum properties: 1
Additional properties are not allowed
Example: {"model":"gpt-6-luna","temperature":0.25,"max_tokens":512}
requests[] (oneOf 1).body.model string Optional
Primary model for the draft.
Maximum length: 70
requests[] (oneOf 1).body.stream boolean Optional
Whether gateway responses using this prompt should stream.
requests[] (oneOf 1).body.temperature number or null Optional
Sampling temperature.
requests[] (oneOf 1).body.max_tokens integer or null Optional
Maximum output tokens.
requests[] (oneOf 1).body.top_p number or null Optional
Nucleus-sampling probability mass.
requests[] (oneOf 1).body.frequency_penalty number or null Optional
Frequency penalty.
requests[] (oneOf 1).body.presence_penalty number or null Optional
Presence penalty.
requests[] (oneOf 1).body.reasoning_effort string or null Optional
Provider-specific reasoning effort.
Maximum length: 70
requests[] (oneOf 1).body.verbosity string or null Optional
Provider-specific output verbosity.
Maximum length: 50
requests[] (oneOf 1).body.thinking any Optional
Provider-specific thinking configuration. Any JSON value is accepted.
requests[] (oneOf 1).body.seed integer or null Optional
Optional deterministic sampling seed.
requests[] (oneOf 1).body.tools array<any> or null Optional
Tool definitions made available to the model.
requests[] (oneOf 1).body.tools[] any Array item
-
requests[] (oneOf 1).body.tool_choice any Optional
Tool-selection configuration. Any JSON value is accepted.
requests[] (oneOf 1).body.response_format any Optional
Structured response-format configuration. Any JSON value is accepted.
requests[] (oneOf 1).body.json_schema any Optional
JSON schema for structured output. Any JSON value is accepted.
requests[] (oneOf 1).body.is_enforcing_response_format boolean Optional
Whether to enforce the configured response format.
requests[] (oneOf 2) object Schema variant
Commit the prompt’s latest draft.
Reference: #/components/schemas/PromptBulkCommitItem
Additional properties are not allowed
requests[] (oneOf 2).prompt_id string Required in parent
Exact prompt ID to mutate.
Minimum length: 1
Maximum length: 70
requests[] (oneOf 2).action string Required in parent
Allowed: "commit"
requests[] (oneOf 2).body object Optional
Optional commit metadata.
Reference: #/components/schemas/PromptBulkCommitBody
Additional properties are not allowed
Example: {"description":"Tune production configuration"}
requests[] (oneOf 2).body.description string Optional
Optional commit message. Blank strings are accepted.
requests[] (oneOf 3) object Schema variant
Deploy the prompt’s latest committed version.
Reference: #/components/schemas/PromptBulkDeployItem
Additional properties are not allowed
requests[] (oneOf 3).prompt_id string Required in parent
Exact prompt ID to mutate.
Minimum length: 1
Maximum length: 70
requests[] (oneOf 3).action string Required in parent
Allowed: "deploy"
requests[] (oneOf 3).body object Optional
If provided, this object must be empty.
Maximum properties: 0
Additional properties are not allowed

OpenAPI request schema

{
  "$ref": "#/components/schemas/PromptBulkRequest"
}
Update, commit, and deploy one prompt
JSON
{ "requests": [ { "prompt_id": "prm_customer_support", "action": "update", "body": { "model": "gpt-6-luna", "temperature": 0.25, "max_tokens": 512 } }, { "prompt_id": "prm_customer_support", "action": "commit", "body": { "description": "Tune production configuration" } }, { "prompt_id": "prm_customer_support", "action": "deploy" } ] }

Examples

Update, commit, and deploy one prompt

Headers

JSON
{ "Authorization": "Bearer YOUR_RESPAN_API_KEY" }

Request

JSON
{ "requests": [ { "prompt_id": "prm_customer_support", "action": "update", "body": { "model": "gpt-6-luna", "temperature": 0.25, "max_tokens": 512 } }, { "prompt_id": "prm_customer_support", "action": "commit", "body": { "description": "Tune production configuration" } }, { "prompt_id": "prm_customer_support", "action": "deploy" } ] }

Response

JSON
{ "body": { "success_count": 3, "error_count": 0, "errors": [] } }

Responses

200

All prompt operations succeeded.

application/json

Field Type Requirement Description and constraints
$ object Body
Canonical result envelope for a bulk operation.
Reference: #/components/schemas/BulkOperationResponse
Example: {"success_count":1,"error_count":0,"errors":[]}
success_count integer Required in parent
Number of items successfully processed.
Minimum: 0
error_count integer Required in parent
Number of items that failed.
Minimum: 0
errors array<object> Required in parent
Item-level failures, keyed by zero-based input index.
errors[] object Array item
An item that failed during a bulk operation. index is zero-based and identifies the corresponding item in the request array.
Reference: #/components/schemas/BulkItemError
errors[].index integer Required in parent
Zero-based index of the failed item in the submitted array.
Minimum: 0
errors[].error string Required in parent
Error message for the failed item.

OpenAPI response schema

{
  "$ref": "#/components/schemas/BulkOperationResponse"
}
All three operations succeeded
JSON
{ "success_count": 3, "error_count": 0, "errors": [] }

207

Some prompt operations succeeded and some failed. Successful items remain committed.

application/json

Field Type Requirement Description and constraints
$ object Body
Canonical result envelope for a bulk operation.
Reference: #/components/schemas/BulkOperationResponse
Example: {"success_count":1,"error_count":0,"errors":[]}
success_count integer Required in parent
Number of items successfully processed.
Minimum: 0
error_count integer Required in parent
Number of items that failed.
Minimum: 0
errors array<object> Required in parent
Item-level failures, keyed by zero-based input index.
errors[] object Array item
An item that failed during a bulk operation. index is zero-based and identifies the corresponding item in the request array.
Reference: #/components/schemas/BulkItemError
errors[].index integer Required in parent
Zero-based index of the failed item in the submitted array.
Minimum: 0
errors[].error string Required in parent
Error message for the failed item.

OpenAPI response schema

{
  "$ref": "#/components/schemas/BulkOperationResponse"
}
One prompt was not found
JSON
{ "success_count": 1, "error_count": 1, "errors": [ { "index": 1, "error": "Prompt 'prm_missing' not found." } ] }

400

The request failed validation, or every prompt operation failed.

application/json

Field Type Requirement Description and constraints
$ object or object Body
-
$ (oneOf 1) object Schema variant
Canonical result envelope for a bulk operation.
Reference: #/components/schemas/BulkOperationResponse
Example: {"success_count":1,"error_count":0,"errors":[]}
$ (oneOf 1).success_count integer Required in parent
Number of items successfully processed.
Minimum: 0
$ (oneOf 1).error_count integer Required in parent
Number of items that failed.
Minimum: 0
$ (oneOf 1).errors array<object> Required in parent
Item-level failures, keyed by zero-based input index.
$ (oneOf 1).errors[] object Array item
An item that failed during a bulk operation. index is zero-based and identifies the corresponding item in the request array.
Reference: #/components/schemas/BulkItemError
$ (oneOf 1).errors[].index integer Required in parent
Zero-based index of the failed item in the submitted array.
Minimum: 0
$ (oneOf 1).errors[].error string Required in parent
Error message for the failed item.
$ (oneOf 2) object Schema variant
Additional properties are allowed
$ (oneOf 2).requests array<any> Required in parent
DRF validation errors for the request array.
$ (oneOf 2).requests[] any Array item
-

OpenAPI response schema

{
  "oneOf": [
    {
      "$ref": "#/components/schemas/BulkOperationResponse"
    },
    {
      "type": "object",
      "required": [
        "requests"
      ],
      "properties": {
        "requests": {
          "type": "array",
          "description": "DRF validation errors for the request array.",
          "items": {}
        }
      },
      "additionalProperties": true
    }
  ]
}
Every operation failed
JSON
{ "success_count": 0, "error_count": 1, "errors": [ { "index": 0, "error": "Prompt 'prm_missing' not found." } ] }
Update contains a content field
JSON
{ "requests": [ { "body": { "messages": [ "Unknown field." ] } } ] }
No operations supplied
JSON
{ "requests": [ "At least 1 request is required." ] }

403

The API key is missing, invalid or expired, or it can’t update prompts.

application/json

Field Type Requirement Description and constraints
$ object Body
-
detail string Required in parent
-

OpenAPI response schema

{
  "type": "object",
  "required": [
    "detail"
  ],
  "properties": {
    "detail": {
      "type": "string"
    }
  }
}
Example
JSON
{ "detail": "Your API key is invalid or expired, please check your API key in the platform settings." }

422

The request contains more than 100 prompt operations.

application/json

Field Type Requirement Description and constraints
$ object Body
-
detail string Required in parent
-

OpenAPI response schema

{
  "type": "object",
  "required": [
    "detail"
  ],
  "properties": {
    "detail": {
      "type": "string"
    }
  }
}
Example
JSON
{ "detail": "Cannot process more than 100 items at once." }

429

Rate limit exceeded.

application/json

Field Type Requirement Description and constraints
$ object Body
-
detail string Required in parent
-
retry_after integer Optional
Seconds to wait before retrying, when provided.
Minimum: 0

OpenAPI response schema

{
  "type": "object",
  "required": [
    "detail"
  ],
  "properties": {
    "detail": {
      "type": "string"
    },
    "retry_after": {
      "type": "integer",
      "minimum": 0,
      "description": "Seconds to wait before retrying, when provided."
    }
  }
}
Example
JSON
{ "detail": "Rate limit exceeded", "retry_after": 30 }

OpenAPI source

The operation and referenced components below retain the complete OpenAPI definitions, including constraints and examples.

OpenAPI operation

{
  "summary": "Update, commit, or deploy prompts in bulk",
  "operationId": "processPromptBulkOperations",
  "tags": [
    "Prompts"
  ],
  "description": "Process 1 to 100 prompt operations sequentially in request order using exact `prompt_id` matching. Each item runs in its own transaction, so a failed item is rolled back without undoing successful items. `update` changes model configuration on the latest draft and does not accept content fields such as `messages`, `variables`, or `description`; `commit` snapshots the latest draft; `deploy` promotes the latest committed version. A later duplicate successful `commit` or `deploy` for the same prompt in one request is returned as an indexed error. This endpoint inherits the caller's configured API-key or JWT rate limits; it has no fixed endpoint-specific RPM.",
  "requestBody": {
    "required": true,
    "content": {
      "application/json": {
        "schema": {
          "$ref": "#/components/schemas/PromptBulkRequest"
        },
        "examples": {
          "updateCommitDeploy": {
            "summary": "Update, commit, and deploy one prompt",
            "value": {
              "requests": [
                {
                  "prompt_id": "prm_customer_support",
                  "action": "update",
                  "body": {
                    "model": "gpt-6-luna",
                    "temperature": 0.25,
                    "max_tokens": 512
                  }
                },
                {
                  "prompt_id": "prm_customer_support",
                  "action": "commit",
                  "body": {
                    "description": "Tune production configuration"
                  }
                },
                {
                  "prompt_id": "prm_customer_support",
                  "action": "deploy"
                }
              ]
            }
          }
        }
      }
    }
  },
  "responses": {
    "200": {
      "description": "All prompt operations succeeded.",
      "content": {
        "application/json": {
          "schema": {
            "$ref": "#/components/schemas/BulkOperationResponse"
          },
          "examples": {
            "allSucceeded": {
              "summary": "All three operations succeeded",
              "value": {
                "success_count": 3,
                "error_count": 0,
                "errors": []
              }
            }
          }
        }
      }
    },
    "207": {
      "description": "Some prompt operations succeeded and some failed. Successful items remain committed.",
      "content": {
        "application/json": {
          "schema": {
            "$ref": "#/components/schemas/BulkOperationResponse"
          },
          "examples": {
            "partialSuccess": {
              "summary": "One prompt was not found",
              "value": {
                "success_count": 1,
                "error_count": 1,
                "errors": [
                  {
                    "index": 1,
                    "error": "Prompt 'prm_missing' not found."
                  }
                ]
              }
            }
          }
        }
      }
    },
    "400": {
      "description": "The request failed validation, or every prompt operation failed.",
      "content": {
        "application/json": {
          "schema": {
            "oneOf": [
              {
                "$ref": "#/components/schemas/BulkOperationResponse"
              },
              {
                "type": "object",
                "required": [
                  "requests"
                ],
                "properties": {
                  "requests": {
                    "type": "array",
                    "description": "DRF validation errors for the request array.",
                    "items": {}
                  }
                },
                "additionalProperties": true
              }
            ]
          },
          "examples": {
            "allFailed": {
              "summary": "Every operation failed",
              "value": {
                "success_count": 0,
                "error_count": 1,
                "errors": [
                  {
                    "index": 0,
                    "error": "Prompt 'prm_missing' not found."
                  }
                ]
              }
            },
            "invalidUpdateBody": {
              "summary": "Update contains a content field",
              "value": {
                "requests": [
                  {
                    "body": {
                      "messages": [
                        "Unknown field."
                      ]
                    }
                  }
                ]
              }
            },
            "emptyBatch": {
              "summary": "No operations supplied",
              "value": {
                "requests": [
                  "At least 1 request is required."
                ]
              }
            }
          }
        }
      }
    },
    "403": {
      "description": "The API key is missing, invalid or expired, or it can't update prompts.",
      "content": {
        "application/json": {
          "schema": {
            "type": "object",
            "required": [
              "detail"
            ],
            "properties": {
              "detail": {
                "type": "string"
              }
            }
          },
          "example": {
            "detail": "Your API key is invalid or expired, please check your API key in the platform settings."
          }
        }
      }
    },
    "422": {
      "description": "The request contains more than 100 prompt operations.",
      "content": {
        "application/json": {
          "schema": {
            "type": "object",
            "required": [
              "detail"
            ],
            "properties": {
              "detail": {
                "type": "string"
              }
            }
          },
          "example": {
            "detail": "Cannot process more than 100 items at once."
          }
        }
      }
    },
    "429": {
      "description": "Rate limit exceeded.",
      "content": {
        "application/json": {
          "schema": {
            "type": "object",
            "required": [
              "detail"
            ],
            "properties": {
              "detail": {
                "type": "string"
              },
              "retry_after": {
                "type": "integer",
                "minimum": 0,
                "description": "Seconds to wait before retrying, when provided."
              }
            }
          },
          "example": {
            "detail": "Rate limit exceeded",
            "retry_after": 30
          }
        }
      }
    }
  },
  "security": [
    {
      "RespanApiKey": []
    },
    {
      "DashboardJwt": []
    }
  ],
  "x-fern-examples": [
    {
      "name": "Update, commit, and deploy one prompt",
      "request": {
        "requests": [
          {
            "prompt_id": "prm_customer_support",
            "action": "update",
            "body": {
              "model": "gpt-6-luna",
              "temperature": 0.25,
              "max_tokens": 512
            }
          },
          {
            "prompt_id": "prm_customer_support",
            "action": "commit",
            "body": {
              "description": "Tune production configuration"
            }
          },
          {
            "prompt_id": "prm_customer_support",
            "action": "deploy"
          }
        ]
      },
      "response": {
        "body": {
          "success_count": 3,
          "error_count": 0,
          "errors": []
        }
      },
      "headers": {
        "Authorization": "Bearer YOUR_RESPAN_API_KEY"
      }
    }
  ]
}

OpenAPI path metadata

{}

Referenced OpenAPI components

{
  "schemas": {
    "BulkItemError": {
      "type": "object",
      "description": "An item that failed during a bulk operation. `index` is zero-based and identifies the corresponding item in the request array.",
      "required": [
        "index",
        "error"
      ],
      "properties": {
        "index": {
          "type": "integer",
          "minimum": 0,
          "description": "Zero-based index of the failed item in the submitted array."
        },
        "error": {
          "type": "string",
          "description": "Error message for the failed item."
        }
      }
    },
    "BulkOperationResponse": {
      "type": "object",
      "description": "Canonical result envelope for a bulk operation.",
      "required": [
        "success_count",
        "error_count",
        "errors"
      ],
      "properties": {
        "success_count": {
          "type": "integer",
          "minimum": 0,
          "description": "Number of items successfully processed."
        },
        "error_count": {
          "type": "integer",
          "minimum": 0,
          "description": "Number of items that failed."
        },
        "errors": {
          "type": "array",
          "description": "Item-level failures, keyed by zero-based input index.",
          "items": {
            "$ref": "#/components/schemas/BulkItemError"
          }
        }
      },
      "example": {
        "success_count": 1,
        "error_count": 0,
        "errors": []
      }
    },
    "PromptBulkCommitBody": {
      "type": "object",
      "description": "Optional commit metadata.",
      "additionalProperties": false,
      "properties": {
        "description": {
          "type": "string",
          "description": "Optional commit message. Blank strings are accepted."
        }
      },
      "example": {
        "description": "Tune production configuration"
      }
    },
    "PromptBulkCommitItem": {
      "type": "object",
      "description": "Commit the prompt's latest draft.",
      "required": [
        "prompt_id",
        "action"
      ],
      "additionalProperties": false,
      "properties": {
        "prompt_id": {
          "type": "string",
          "minLength": 1,
          "maxLength": 70,
          "description": "Exact prompt ID to mutate."
        },
        "action": {
          "type": "string",
          "enum": [
            "commit"
          ]
        },
        "body": {
          "$ref": "#/components/schemas/PromptBulkCommitBody"
        }
      }
    },
    "PromptBulkDeployItem": {
      "type": "object",
      "description": "Deploy the prompt's latest committed version.",
      "required": [
        "prompt_id",
        "action"
      ],
      "additionalProperties": false,
      "properties": {
        "prompt_id": {
          "type": "string",
          "minLength": 1,
          "maxLength": 70,
          "description": "Exact prompt ID to mutate."
        },
        "action": {
          "type": "string",
          "enum": [
            "deploy"
          ]
        },
        "body": {
          "type": "object",
          "description": "If provided, this object must be empty.",
          "maxProperties": 0,
          "additionalProperties": false
        }
      }
    },
    "PromptBulkRequest": {
      "type": "object",
      "description": "Ordered prompt operations to process.",
      "required": [
        "requests"
      ],
      "additionalProperties": false,
      "properties": {
        "requests": {
          "type": "array",
          "description": "Prompt operations. Error indices refer to this zero-based array.",
          "minItems": 1,
          "maxItems": 100,
          "items": {
            "$ref": "#/components/schemas/PromptBulkRequestItem"
          }
        }
      }
    },
    "PromptBulkRequestItem": {
      "description": "One action in a prompt bulk request.",
      "oneOf": [
        {
          "$ref": "#/components/schemas/PromptBulkUpdateItem"
        },
        {
          "$ref": "#/components/schemas/PromptBulkCommitItem"
        },
        {
          "$ref": "#/components/schemas/PromptBulkDeployItem"
        }
      ],
      "discriminator": {
        "propertyName": "action",
        "mapping": {
          "update": "#/components/schemas/PromptBulkUpdateItem",
          "commit": "#/components/schemas/PromptBulkCommitItem",
          "deploy": "#/components/schemas/PromptBulkDeployItem"
        }
      }
    },
    "PromptBulkUpdateBody": {
      "type": "object",
      "description": "Non-empty model configuration changes for the latest draft. Prompt content fields are not accepted.",
      "minProperties": 1,
      "additionalProperties": false,
      "properties": {
        "model": {
          "type": "string",
          "maxLength": 70,
          "description": "Primary model for the draft."
        },
        "stream": {
          "type": "boolean",
          "description": "Whether gateway responses using this prompt should stream."
        },
        "temperature": {
          "type": "number",
          "nullable": true,
          "description": "Sampling temperature."
        },
        "max_tokens": {
          "type": "integer",
          "nullable": true,
          "description": "Maximum output tokens."
        },
        "top_p": {
          "type": "number",
          "nullable": true,
          "description": "Nucleus-sampling probability mass."
        },
        "frequency_penalty": {
          "type": "number",
          "nullable": true,
          "description": "Frequency penalty."
        },
        "presence_penalty": {
          "type": "number",
          "nullable": true,
          "description": "Presence penalty."
        },
        "reasoning_effort": {
          "type": "string",
          "maxLength": 70,
          "nullable": true,
          "description": "Provider-specific reasoning effort."
        },
        "verbosity": {
          "type": "string",
          "maxLength": 50,
          "nullable": true,
          "description": "Provider-specific output verbosity."
        },
        "thinking": {
          "description": "Provider-specific thinking configuration. Any JSON value is accepted."
        },
        "seed": {
          "type": "integer",
          "nullable": true,
          "description": "Optional deterministic sampling seed."
        },
        "tools": {
          "type": "array",
          "nullable": true,
          "description": "Tool definitions made available to the model.",
          "items": {}
        },
        "tool_choice": {
          "description": "Tool-selection configuration. Any JSON value is accepted."
        },
        "response_format": {
          "description": "Structured response-format configuration. Any JSON value is accepted."
        },
        "json_schema": {
          "description": "JSON schema for structured output. Any JSON value is accepted."
        },
        "is_enforcing_response_format": {
          "type": "boolean",
          "description": "Whether to enforce the configured response format."
        }
      },
      "example": {
        "model": "gpt-6-luna",
        "temperature": 0.25,
        "max_tokens": 512
      }
    },
    "PromptBulkUpdateItem": {
      "type": "object",
      "description": "Update model configuration on the prompt's latest draft.",
      "required": [
        "prompt_id",
        "action",
        "body"
      ],
      "additionalProperties": false,
      "properties": {
        "prompt_id": {
          "type": "string",
          "minLength": 1,
          "maxLength": 70,
          "description": "Exact prompt ID to mutate."
        },
        "action": {
          "type": "string",
          "enum": [
            "update"
          ]
        },
        "body": {
          "$ref": "#/components/schemas/PromptBulkUpdateBody"
        }
      }
    }
  },
  "securitySchemes": {
    "DashboardJwt": {
      "type": "http",
      "scheme": "bearer",
      "bearerFormat": "Dashboard JWT",
      "description": "Use a dashboard JWT only for dashboard-authenticated endpoints. Respan API-key endpoints use the respanApiKey auth field instead.",
      "x-fern-bearer": {
        "name": "dashboardJwt",
        "env": "RESPAN_DASHBOARD_JWT"
      }
    },
    "RespanApiKey": {
      "type": "http",
      "scheme": "bearer",
      "bearerFormat": "Respan API key",
      "description": "Use your Respan API key for Respan API authentication. Enter only the Respan API key value; clients send Authorization: Bearer <RESPAN_API_KEY>. For /api/responses, provider credentials such as Perplexity, OpenAI, or Azure OpenAI go in Settings -> Providers or respan_params.credential_override in the request body, not in this authentication field.",
      "x-fern-bearer": {
        "name": "respanApiKey",
        "env": "RESPAN_API_KEY"
      }
    }
  }
}