> ## Documentation Index
> Fetch the complete documentation index at: https://composio-preview.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# CometAPI

> CometAPI provides a unified API gateway for text, image, audio, video, and other generative AI models from multiple providers.

![CometAPI logo](https://mintcdn.com/composio-preview/NPf8agM6UrvZD-Iu/images/toolkits/cometapi.svg?fit=max\&auto=format\&n=NPf8agM6UrvZD-Iu\&q=85\&s=8507db4742c2f91c2171e0f2c955b48c)

* **Category:** ai models
* **Auth:** API\_KEY
* **Composio-managed OAuth available?** N/A
* **Tools:** 6
* **Triggers:** 0
* **Slug:** `COMETAPI`
* **Version:** 20261101\_00

## Tools

> [accordion] Create Chat Completion
>
> **Slug:** `COMETAPI_CREATE_CHAT_COMPLETION`
>
> Create a non-streaming Chat Completions result for message-based conversations and function-calling workflows. Use this for models or integrations that require the OpenAI Chat Completions protocol. Requires funded organization balance.
>
> #### Input Parameters
>
> **stop** `string`
>
> One or more stop sequences, up to the provider's limit of four.
>
> **user** `string`
>
> Stable, non-sensitive end-user identifier for abuse monitoring.
>
> **model** `string` *required*
>
> Model ID from the List Models tool with openai in supported\_endpoint\_types.
>
> **tools** `array`
>
> Function tools the model may call.
>
> **top\_p** `number`
>
> Nucleus sampling value from 0 to 1. Omit unless needed; do not tune together with temperature.
>
> **messages** `array` *required*
>
> Conversation messages in order.
>
> **temperature** `number`
>
> Sampling temperature from 0 to 2. Omit unless needed; do not tune together with top\_p.
>
> **tool\_choice** `string`
>
> Tool selection mode or a specific function the model must call. Send it only together with tools; omitted otherwise, leaving the provider default.
>
> **response\_format** `object`
>
> Output format configuration for text, JSON mode, or JSON Schema output.
>
> **reasoning\_effort** `string ("low" | "medium" | "high")`
>
> Reasoning effort for compatible models.
>
> **max\_completion\_tokens** `integer`
>
> Maximum generated tokens, including reasoning tokens, for compatible models.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Create Embeddings
>
> **Slug:** `COMETAPI_CREATE_EMBEDDINGS`
>
> Create OpenAI-compatible embedding vectors for one text or a batch of texts. This metered operation requires funded organization balance.
>
> #### Input Parameters
>
> **user** `string`
>
> Stable non-sensitive end-user identifier for abuse monitoring.
>
> **input** `string` *required*
>
> One text or a batch of texts to embed. Batch results preserve input order.
>
> **model** `string` *required*
>
> Embedding model ID, such as text-embedding-3-small. Verify current availability with the List Models tool.
>
> **dimensions** `integer`
>
> Requested vector dimensions for models that support dimensionality reduction.
>
> **encoding\_format** `string ("float" | "base64")`
>
> Embedding representation. Use float for numeric vectors or base64 to reduce large response payloads.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Create Response
>
> **Slug:** `COMETAPI_CREATE_RESPONSE`
>
> Create a non-streaming OpenAI Responses API result from plain text input, with options for stateful continuation, reasoning controls, and structured text output. Requires funded organization balance; set store=true when a later call will continue from this response.
>
> #### Input Parameters
>
> **text** `object`
>
> Text output format and verbosity configuration.
>
> **input** `string` *required*
>
> Plain text input for the model.
>
> **model** `string` *required*
>
> Model ID from the List Models tool that supports the OpenAI-compatible Responses API.
>
> **store** `boolean`
>
> Whether CometAPI should store the response. Set true if its ID will be reused with previous\_response\_id; defaults to false for data minimization.
>
> **top\_p** `number`
>
> Nucleus sampling value from 0 to 1. Do not tune together with temperature.
>
> **reasoning** `object`
>
> Reasoning configuration for compatible models.
>
> **truncation** `string ("auto" | "disabled")`
>
> Context overflow behavior: fail when disabled or drop oldest inputs when auto.
>
> **temperature** `number`
>
> Sampling temperature from 0 to 2. Do not tune together with top\_p.
>
> **instructions** `string`
>
> System or developer instructions for this response.
>
> **max\_output\_tokens** `integer`
>
> Maximum generated tokens, including visible output and reasoning tokens.
>
> **previous\_response\_id** `string`
>
> Previous response ID for a stateful follow-up. The earlier response must have been created with store=true.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get API Key Usage
>
> **Slug:** `COMETAPI_GET_API_KEY_USAGE`
>
> Return quota, usage, expiration, and model restrictions for the connected CometAPI API key. This reports key-level limits, not the organization's spendable balance or commercial tier.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Models
>
> **Slug:** `COMETAPI_LIST_MODELS`
>
> List all models available to the connected API key, including provider ownership and supported protocol types when returned. Use this before generation to choose a compatible model; catalog presence does not guarantee funded execution.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Moderate Content
>
> **Slug:** `COMETAPI_MODERATE_CONTENT`
>
> Classify one text or a batch of texts with an OpenAI-compatible moderation model. This text-only operation is metered and requires funded CometAPI organization balance.
>
> #### Input Parameters
>
> **input** `string` *required*
>
> One text or a batch of texts to classify. Batch results preserve input order.
>
> **model** `string`
>
> Moderation model ID. The documented default for text is omni-moderation-latest.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not
