> ## Documentation Index > Fetch the complete documentation index at: https://docs.honeyhive.ai/llms.txt > Use this file to discover all available pages before exploring further. # Create a batch of model events (deprecated) > Deprecated. Use `POST /v1/events/batch` with `event_type="model"` on each event instead. Migration notes: the top-level array `model_events` becomes `events`; each element must explicitly set `event_type: "model"` (the legacy route sets this server-side); the deprecated top-level aliases `is_single_session` and `session` are not accepted by the v1 route (`PostEventBatchRequest` is `.strict()`); use `single_session` and `session_properties` instead. The legacy route continues to serve traffic and remaps the model-specific fields on each event (`model`, `messages`, `response`, `provider`, `usage`, `cost`, `hyperparameters`, `template`, `template_inputs`, `tools`, `tool_choice`, `response_format`, `duration`, `error`) into `inputs.*` / `outputs.*` before storage. ## OpenAPI ````yaml post /events/model/batch openapi: 3.0.3 info: title: HoneyHive API version: 1.0.1 servers: - url: https://api.honeyhive.ai security: - BearerAuth: [] paths: /events/model/batch: post: tags: - Events summary: Create a batch of model events description: Please refer to our instrumentation guide for detailed information operationId: createModelEventBatch requestBody: required: true content: application/json: schema: type: object properties: model_events: type: array items: $ref: '#/components/schemas/CreateModelEvent' responses: '200': description: Model events created content: application/json: schema: type: object properties: event_ids: type: array items: type: string success: type: boolean example: event_ids: - 7f22137a-6911-4ed3-bc36-110f1dde6b66 - 7f22137a-6911-4ed3-bc36-110f1dde6b67 success: true '500': description: Model events partially created content: application/json: schema: type: object properties: event_ids: type: array items: type: string errors: type: array items: type: string description: >- Any failure messages for events that could not be created success: type: boolean example: event_ids: - 7f22137a-6911-4ed3-bc36-110f1dde6b66 - 7f22137a-6911-4ed3-bc36-110f1dde6b67 errors: - Could not create event due to missing model - Could not create event due to missing provider success: true x-codeSamples: - lang: python label: createModelEventBatch source: >- import honeyhive from honeyhive.models import components, operations s = honeyhive.HoneyHive( bearer_auth="", ) res = s.events.create_model_event_batch(request=operations.CreateModelEventBatchRequestBody( model_events=[ components.CreateModelEvent( project='New Project', model='gpt-4o', provider='openai', messages=[ { 'role': 'system', 'content': 'Hello, world!', }, ], response={ 'role': 'assistant', 'content': 'Hello, world!', }, duration=42, usage={ 'prompt_tokens': 10, 'completion_tokens': 10, 'total_tokens': 20, }, cost=0.00008, error=None, source='playground', event_name='Model Completion', hyperparameters={ 'temperature': 0, 'top_p': 1, 'max_tokens': 1000, 'presence_penalty': 0, 'frequency_penalty': 0, 'stop': [ '', ], 'n': 1, }, template=[ { 'role': 'system', 'content': 'Hello, {{ name }}!', }, ], template_inputs={ 'name': 'world', }, tools=[ { 'key': '', }, ], tool_choice='none', response_format={ 'type': 'text', }, ), ], )) if res.object is not None: # handle response pass - lang: typescript label: createModelEventBatch source: |- import { HoneyHive } from "honeyhive"; async function run() { const sdk = new HoneyHive({ bearerAuth: "", }); const res = await sdk.events.createModelEventBatch({ modelEvents: [ { project: "New Project", model: "gpt-4o", provider: "openai", messages: [ { "role": "system", "content": "Hello, world!", }, ], response: { "role": "assistant", "content": "Hello, world!", }, duration: 42, usage: { "prompt_tokens": 10, "completion_tokens": 10, "total_tokens": 20, }, cost: 0.00008, error: null, source: "playground", eventName: "Model Completion", hyperparameters: { "temperature": 0, "top_p": 1, "max_tokens": 1000, "presence_penalty": 0, "frequency_penalty": 0, "stop": [ "", ], "n": 1, }, template: [ { "role": "system", "content": "Hello, {{ name }}!", }, ], templateInputs: { "name": "world", }, tools: [ { "key": "", }, ], toolChoice: "none", responseFormat: { "type": "text", }, }, ], }); if (res.statusCode == 200) { // handle response } } run(); components: schemas: CreateModelEvent: type: object properties: project: type: string description: Project associated with the event model: type: string description: Model name provider: type: string description: Model provider messages: type: array items: type: object additionalProperties: true description: Messages passed to the model response: type: object additionalProperties: true description: Final output JSON of the event duration: type: number description: How long the event took in milliseconds usage: type: object additionalProperties: true description: Usage statistics of the model cost: type: number description: Cost of the model completion error: type: string description: Any error description if event failed source: type: string description: Source of the event - production, staging, etc event_name: type: string description: Name of the event hyperparameters: type: object additionalProperties: true description: Hyperparameters used for the model template: type: array items: type: object additionalProperties: true description: Template used for the model template_inputs: type: object additionalProperties: true description: Inputs for the template tools: type: array items: type: object additionalProperties: true description: Tools used for the model tool_choice: type: string description: Tool choice for the model response_format: type: object additionalProperties: true description: Response format for the model required: - project - model - provider - messages - response - duration - usage example: project: New Project model: gpt-4o provider: openai messages: - role: system content: Hello, world! response: role: assistant content: Hello, world! duration: 42 usage: prompt_tokens: 10 completion_tokens: 10 total_tokens: 20 cost: 0.00008 error: null source: playground event_name: Model Completion hyperparameters: temperature: 0 top_p: 1 max_tokens: 1000 presence_penalty: 0 frequency_penalty: 0 stop: [] 'n': 1 template: - role: system content: Hello, {{ name }}! template_inputs: name: world tools: type: function function: name: get_current_weather description: Get the current weather parameters: type: object properties: location: type: string description: The city and state, e.g. San Francisco, CA format: type: string enum: - celsius - fahrenheit description: >- The temperature unit to use. Infer this from the users location. required: - location - format tool_choice: none response_format: type: text securitySchemes: BearerAuth: type: http scheme: bearer ````