Skip to main content
Cohere logo
  • Category: artificial intelligence
  • Auth: API_KEY
  • Composio-managed OAuth available? N/A
  • Tools: 22
  • Triggers: 0
  • Slug: COHERE
  • Version: 20261030_00

Tools

Slug: COHERE_CANCEL_BATCHCancel one in-progress Cohere batch. This requires a production Cohere API key, stops the batch irreversibly, and cannot be undone.

Input Parameters

string
required
Cohere ID of the in-progress batch to cancel.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: COHERE_CANCEL_EMBED_JOBIrreversibly cancel one active Cohere asynchronous embed job by ID. Cohere accrued charges for work processed before cancellation still apply, and partial results are not available. Cancel only a caller-owned job. This action sends one request and does not poll for the cancelled state.

Input Parameters

string
required
Unique identifier of the active, caller-owned embed job to cancel.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: COHERE_CHATGenerate one non-streaming Cohere chat response from an ordered conversation, optionally using documents, tools, structured output, or reasoning controls.

Input Parameters

integer
Best-effort deterministic sampling seed.
string
required
Cohere chat model name; use COHERE_LIST_MODELS with endpoint=chat to discover current choices.
array
Functions the model may call.
integer
Top-k sampling value; 0 disables top-k sampling.
number
Top-p probability mass from 0.01 to 0.99.
boolean
Include generated-token log probabilities in the response.
array
required
Conversation messages in chronological order.
integer
Scheduling priority; lower numbers are handled earlier.
object
Reasoning enablement and optional token budget.
array
Short relevant text or structured documents used to ground the answer.
integer
Maximum output tokens; low values may produce finish_reason=MAX_TOKENS.
string ("CONTEXTUAL" | "STRICT" | "OFF")
Safety instruction mode; model compatibility varies.
number
Generation randomness; lower values are more deterministic.
string ("REQUIRED" | "NONE")
REQUIRED asks the model to call at least one supplied tool. NONE asks the model not to call tools, but this is best-effort and model-dependent.
boolean
Force generated tool calls to follow the supplied function schemas strictly.
array
Up to five strings that stop generation before the matching sequence.
object
Plain-text or structured JSON output configuration.
object
Citation generation configuration.
number
Presence-based repetition penalty from 0 to 1.
number
Frequency-based repetition penalty from 0 to 1.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: COHERE_CHECK_API_KEYCheck whether the connected Cohere API key is valid and return its organization and owner identifiers when available.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: COHERE_CREATE_BATCHStart one asynchronous Cohere batch from an existing validated batch request dataset and return immediately without polling. Cohere requires a production API key for the Batch API.

Input Parameters

string
required
Human-readable name for the new batch.
string
required
Cohere model that will process the batch dataset.
string
required
Identifier of a validated Cohere batch request dataset.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: COHERE_CREATE_DATASETUpload a Cohere dataset and start asynchronous validation. Returns immediately without waiting for validation to finish.

Input Parameters

object
required
Primary CSV or JSONL dataset file to upload.
string
required
Dataset name; must contain fewer than 50 characters.
string ("embed-input" | "embed-result" | "cluster-result" | "cluster-outliers" | "reranker-finetune-input" | "single-label-classification-finetune-input" | "chat-finetune-input" | "multi-label-classification-finetune-input" | "batch-chat-input" | "batch-openai-chat-input" | "batch-embed-v2-input" | "batch-chat-v2-input")
required
Dataset type used by Cohere to validate the uploaded records.
object
Optional evaluation CSV or JSONL dataset file to upload.
array
Source fields that must exist and should be retained in the dataset.
string
Single-character delimiter used to parse CSV uploads.
string
Separator Cohere should use to split raw text uploads into records.
array
Source fields to retain when present without requiring them.
boolean
Whether Cohere should retain the original uploaded file.
boolean
Whether to drop malformed rows instead of failing validation.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: COHERE_CREATE_EMBED_JOBStart one asynchronous Cohere embedding job for a validated embed-input dataset and return immediately without polling.

Input Parameters

string
Optional human-readable name for the embed job.
string
required
Cohere embedding model to use for the job.
string ("START" | "END")
Overlength behavior: START discards the beginning; END discards the end.
string
required
Validated Cohere embed-input dataset to process.
string ("search_document" | "search_query" | "classification" | "clustering" | "image")
required
How the resulting embeddings will be used: search_document, search_query, classification, clustering, or image.
array
Optional embedding encodings to produce: float, int8, uint8, binary, ubinary, or base64.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: COHERE_DELETE_DATASETPermanently delete a Cohere dataset by ID. This deletion cannot be undone.

Input Parameters

string
required
Cohere dataset ID to permanently delete.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: COHERE_DETOKENIZE_TOKENSConvert ordered Cohere token IDs back to text using the tokenizer for an explicit matching model.

Input Parameters

string
required
Cohere model whose tokenizer produced the token IDs; it must match the tokenization model.
array
required
Cohere token IDs to detokenize in order; use the exact order returned by tokenization.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: COHERE_EMBED_INPUTSCreate v2 embeddings from exactly one input form: text strings, image data URIs, or structured multimodal content.

Input Parameters

string
required
Cohere embedding model name, such as embed-v4.0; discover choices with COHERE_LIST_MODELS endpoint=embed.
array
One to 96 text strings to embed. Provide exactly one of texts, images, or inputs.
array
Image data URIs to embed. JPEG, PNG, WebP, and GIF are supported. Embed v3 accepts one image up to 5 MB; v4 and newer accept up to 20 MB of image data combined.
array
One to 96 structured multimodal inputs. Each input contains a non-empty ordered list of text or image_url blocks.
integer
Scheduling priority; lower numbers are handled earlier.
string ("NONE" | "START" | "END")
Overlength behavior: NONE errors, START discards the beginning, and END discards the end.
string ("search_document" | "search_query" | "classification" | "clustering" | "image")
required
Purpose of the input: search_document, search_query, classification, clustering, or image.
integer
Maximum tokens embedded per input before applying truncate.
array
Vector encodings to return: float, int8, uint8, binary, ubinary, or base64.
integer ("256" | "512" | "1024" | "1536")
For embed-v4 and newer, output dimensions: 256, 512, 1024, or 1536.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: COHERE_GET_BATCHRetrieve one asynchronous Cohere batch’s status and counters by batch ID. A usable batch ID depends on a production-key CREATE_BATCH lifecycle; this action performs one read only, and callers control any bounded polling.

Input Parameters

string
required
Batch ID returned by CREATE_BATCH or LIST_BATCHES.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: COHERE_GET_DATASETRetrieve one Cohere dataset by ID, including its asynchronous validation state, schema, files, parsing details, and metrics. Callers control any polling and should bound it.

Input Parameters

string
required
Cohere dataset ID returned by a dataset create or list operation.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: COHERE_GET_DATASET_USAGERead the organization’s Cohere dataset-storage consumption in bytes.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: COHERE_GET_EMBED_JOBRetrieve one Cohere asynchronous embedding job’s current status, model, and input and output dataset identifiers by job ID.

Input Parameters

string
required
Unique identifier of the embedding job to retrieve.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: COHERE_GET_MODELRetrieve a Cohere model’s endpoint compatibility, context size, features, tokenizer, and default sampling parameters by model name.

Input Parameters

string
required
Cohere model name to retrieve.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: COHERE_LIST_BATCHESReturn one page of asynchronous Cohere batches and their statuses without creating or cancelling work.

Input Parameters

string ("created_at" | "updated_at")
Sort batches by creation time or last-updated time.
integer
Maximum batches to return on this page (1-1000).
string
Continuation token returned by a prior call. Omit for the first page; pass the returned value back unchanged to fetch the next page.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: COHERE_LIST_DATASETSReturn one offset-based page of Cohere datasets, optionally filtered by type, validation status, or creation time. Cohere provides no total or continuation metadata, so callers control offset explicitly.

Input Parameters

string
Return datasets created after this timestamp.
integer
Maximum datasets to return on this page; must be positive.
string
Return datasets created before this timestamp.
integer
Zero-based number of datasets to skip. Increase it by returned_count to request the following page.
string
Filter datasets by the type recorded on the dataset.
string ("unknown" | "queued" | "processing" | "failed" | "validated" | "skipped")
Filter datasets by their current validation status.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: COHERE_LIST_EMBED_JOBSList Cohere asynchronous embedding jobs and their current statuses.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: COHERE_LIST_MODELSDiscover Cohere model names and capabilities, optionally filtered to an endpoint or its default model. Returns one page without auto-pagination.

Input Parameters

string ("chat" | "embed" | "classify" | "summarize" | "rerank" | "rate" | "generate")
Filter to models compatible with chat, embed, classify, summarize, rerank, rate, or generate.
integer
Requested models on this page (1-1000). The default of 1000 reduces exposure to Cohere’s observed missing continuation token.
string
Continuation token from a prior response. Repeat the same endpoint and default_only filters when continuing; omit for the first page.
boolean
Return only the endpoint’s default model. Requires endpoint.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: COHERE_RERANK_DOCUMENTSRank text documents by relevance to a query and return the highest-scoring source documents.

Input Parameters

string
required
Cohere rerank model name; discover current choices with COHERE_LIST_MODELS endpoint=rerank.
string
required
Search query used to score the documents.
integer
Maximum highest-ranked results to return; must not exceed the number of documents.
integer
Scheduling priority; lower numbers are handled earlier.
array
required
Non-empty text documents to rank; result indexes refer to this zero-based array.
integer
Maximum tokens considered from each document.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: COHERE_TOKENIZE_TEXTConvert text into token IDs with an explicit Cohere model. Detokenization must use the same model because token IDs differ between model tokenizers.

Input Parameters

string
required
Text to tokenize, from 1 to 65,536 characters.
string
required
Model whose tokenizer to use. Use the same model when detokenizing these token IDs.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: COHERE_TRANSCRIBE_AUDIOTranscribe an uploaded audio file to text with a Cohere transcription model.

Input Parameters

object
required
Audio file to transcribe. Supported file extensions are .flac, .mp3, .mpeg, .mpga, .ogg, and .wav.
string
required
Cohere transcription model ID.
string
required
Language of the audio in ISO-639-1 format.
number
Sampling temperature from 0 to 1; lower values are more deterministic.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not