Skip to main content
POST
/
v1
/
prompts
/
run
Run Prompt Version
curl --request POST \
  --url https://api.getmaxim.ai/v1/prompts/run \
  --header 'Content-Type: application/json' \
  --header 'x-maxim-api-key: <api-key>' \
  --data '
{
  "promptId": "<string>",
  "versionId": "<string>",
  "workspaceId": "<string>",
  "messages": [
    {
      "role": "assistant",
      "content": "<string>",
      "tool_call_id": "<string>",
      "tool_calls": [
        {
          "id": "<string>",
          "type": "function",
          "function": {
            "name": "<string>",
            "arguments": "<string>"
          }
        }
      ]
    }
  ],
  "modelName": "<string>",
  "modelProvider": "openai",
  "modelParameters": {}
}
'
{
  "data": {
    "usage": {
      "totalTokens": 123,
      "promptTokens": 123,
      "completionTokens": 123
    },
    "output": null
  }
}

Authorizations

​
x-maxim-api-key
string
header
required

API key for authentication

Body

application/json
​
promptId
string
required

Unique identifier for the prompt

​
versionId
string
required

Unique identifier for the version

​
workspaceId
string
required

Unique identifier for the workspace

​
messages
object[]

Array of messages

​
modelName
string

Name of the model to use

​
modelProvider
enum<string>

Provider of the model

Available options:
openai,
azure,
huggingface,
anthropic,
together,
google,
groq,
bedrock,
maxim,
cohere,
ollama,
lmstudio,
xai,
vertex,
mistral,
fireworks
​
modelParameters
object

Model parameters configuration

Response

Prompt version executed successfully

​
data
object
required