Cohere

Use Cohere's Command, Embed, Rerank, Parse and Transcribe models in your workflows. Generate text, answer questions from your documents with citations, extract data, classify and translate text, and read images; create embeddings and rank documents for semantic search; and turn recordings and PDFs into text.

Actions

Action	What it does
Answer from documents	Answer a question using only the documents you give it, such as help-center articles or search results, with citations saying which document backs up each part of the answer.
Ask about an image	Ask a Cohere vision model a question about one or more pictures: describe a photo, read a chart or a table, or answer a question about a scanned document.
Classify text	Have a Command model pick the one category that fits a piece of text, such as routing a support email, and say why.
Count tokens	Count how many tokens a text is for a Cohere model, to check a prompt fits before sending it or to estimate what it will cost.
Create embeddings	Turn texts into vectors with Cohere Embed for semantic search, deduplication, clustering or classification, ready to store in a vector database such as Pinecone or Qdrant.
Extract data	Pull the fields you name out of text or pictures, such as the total on a photographed receipt or the sender's company in an email, ready for a spreadsheet row or a CRM record.
Generate a Cohere response	Send a prompt to a Cohere Command model and get back its written response, as text or as a JSON object a later step can read field by field.
Get a model	Look up one Cohere model: what it is for, how much text it takes in, the abilities it has and whether it is deprecated.
List models	List the Cohere models this API key can use, with what each is for, how much text it takes in and the abilities it has.
Parse a document	Turn a PDF, a scan or a photo of a document into Markdown with Cohere Parse, keeping its reading order, lists and tables, and describing its pictures.
Rank documents by relevance	Order a list of texts or records by how well each answers a question, best first, with a score from 0 to 1.
Transcribe audio	Write down what is said in a recording with Cohere Transcribe, in any of 14 languages.
Translate text	Translate text into another language with Command A Translate, Cohere's model built for translation in 23 languages, or North Small Translate for more than 50.

Answer from documents

Answer a question using only the documents you give it, such as help-center articles or search results, with citations saying which document backs up each part of the answer.

Inputs

QuestionquestiontextRequired: What to answer, such as 'How long do refunds take?'
DocumentsdocumentslistRequired: The texts to answer from, one per entry: articles, policy sections, search results, or rows from an earlier step. Citations name them by position, counting from 1.
Instructionsinstructionstext: How to answer, such as 'Reply in two sentences' or 'Say you do not know when the documents do not cover it'.
Modelmodeltext: Which Cohere model does the work. Command A+ suits most jobs.One of: command-a-plus-05-2026 (Command A+ (most capable, recommended)), command-a-reasoning-08-2025 (Command A Reasoning (thinks before it answers)), command-a-03-2025 (Command A), command-r-plus-08-2024 (Command R+), command-r-08-2024 (Command R), command-r7b-12-2024 (Command R7B (fastest, lowest cost)). Default: command-a-plus-05-2026.
Maximum response lengthmax_tokensnumber: The most tokens the response may use; a token is about three-quarters of a word. Leave blank to use the model's own maximum output length.At least 1.
Thinkingthinkingtext: Whether a reasoning model (Command A+ or Command A Reasoning) thinks before it answers. Thinking is slower, and it counts against the maximum response length. Other models never think. Off works as expected on Command A Reasoning; Command A+ then reasons inside its answer instead.One of: default (Model's default), on, off. Default: default.

Outputs

answertext: The answer.
citationslist: Each passage of the answer the documents back up.
cited_positionslist: The positions of the documents cited, from 1.
finish_reasontext: COMPLETE when it finished, MAX_TOKENS when it was cut off, STOP_SEQUENCE when it stopped at a stop word.
input_tokensnumber: Tokens read, as billed.
is_groundedtrue/false: Whether any document backs up the answer.
modeltext: The model that answered.
output_tokensnumber: Tokens written, as billed.
sourceslist: The documents cited, in the order given.
was_cut_offtrue/false: Whether it hit the maximum response length.

Example output

{
  "answer": "Refunds are issued within 5 business days.",
  "citations": [
    {
      "document_positions": [
        2
      ],
      "text": "within 5 business days"
    }
  ],
  "cited_positions": [
    2
  ],
  "finish_reason": "COMPLETE",
  "input_tokens": 120,
  "is_grounded": true,
  "model": "command-a-plus-05-2026",
  "output_tokens": 12,
  "sources": [
    {
      "citation_count": 1,
      "document": "Refunds are issued within 5 business days of approval.",
      "position": 2
    }
  ],
  "was_cut_off": false
}

Ask about an image

Ask a Cohere vision model a question about one or more pictures: describe a photo, read a chart or a table, or answer a question about a scanned document.

Inputs

ImagesimageslistRequired: The pictures to look at: upload them, pick files from an earlier step, or paste public web addresses. PNG, JPEG, WebP or GIF (other formats are converted), up to 20.
Questionquestiontext: What to ask about the pictures. Leave blank for a detailed description.
Modelmodeltext: Which Cohere model looks at the pictures. Command A Vision answers at once; Command A+ thinks first, which can take a while.One of: command-a-vision-07-2025 (Command A Vision (answers at once, recommended)), command-a-plus-05-2026 (Command A+ (thinks first; most capable)), c4ai-aya-vision-32b (Aya Vision 32B (23 languages)). Default: command-a-vision-07-2025.
Detaildetailtext: How closely to look. High reads small print but uses more tokens; Low is faster and cheaper.One of: auto (Automatic), low (Low (faster, fewer tokens)), high (High (reads small print)). Default: auto.
Maximum response lengthmax_tokensnumber: The most tokens the response may use; a token is about three-quarters of a word. Leave blank to use the model's own maximum output length.At least 1.
Thinkingthinkingtext: Whether a reasoning model (Command A+ or Command A Reasoning) thinks before it answers. Thinking is slower, and it counts against the maximum response length. Other models never think. Off works as expected on Command A Reasoning; Command A+ then reasons inside its answer instead.One of: default (Model's default), on, off. Default: default.

Outputs

answertext: The model's answer.
finish_reasontext: COMPLETE when it finished, MAX_TOKENS when it was cut off, STOP_SEQUENCE when it stopped at a stop word.
image_countnumber: How many pictures it looked at.
input_tokensnumber: Tokens read, as billed.
modeltext: The model that answered.
output_tokensnumber: Tokens written, as billed.
was_cut_offtrue/false: Whether it hit the maximum response length.

Example output

{
  "answer": "A monarch butterfly resting on a pink flower.",
  "finish_reason": "COMPLETE",
  "image_count": 1,
  "input_tokens": 790,
  "model": "command-a-vision-07-2025",
  "output_tokens": 12,
  "was_cut_off": false
}

Classify text

Have a Command model pick the one category that fits a piece of text, such as routing a support email, and say why. The answer is always exactly one of the categories you list.

Inputs

TexttexttextRequired: The text to classify, such as an email, a review or a support ticket.
CategoriescategorieslistRequired: The categories to choose from, one per entry. The step always returns exactly one of them, spelled as you wrote it.
How to decideinstructionstext: Rules for borderline cases, such as 'Anything that mentions money back is a Refund request'.
Modelmodeltext: Which Cohere model decides. Command A+ suits most jobs.One of: command-a-plus-05-2026 (Command A+ (most capable, recommended)), command-a-03-2025 (Command A), command-r-plus-08-2024 (Command R+), command-r-08-2024 (Command R). Default: command-a-plus-05-2026.

Outputs

categorieslist: The categories it chose from.
categorytext: The category chosen.
input_tokensnumber: Tokens read, as billed.
modeltext: The model that chose.
output_tokensnumber: Tokens written, as billed.
reasontext: Why, in one sentence.

Example output

{
  "categories": [
    "Refund request",
    "Bug report",
    "Sales question"
  ],
  "category": "Refund request",
  "input_tokens": 96,
  "model": "command-a-plus-05-2026",
  "output_tokens": 21,
  "reason": "The customer asks for their money back."
}

Count tokens

Count how many tokens a text is for a Cohere model, to check a prompt fits before sending it or to estimate what it will cost.

Inputs

TexttexttextRequired: The text to count, up to 65,536 characters.
Modelmodeltext: The model whose tokens to count: each family splits text its own way. Defaults to command-a-plus-05-2026.Default: command-a-plus-05-2026.

Outputs

character_countnumber: How many characters the text is.
modeltext: The model whose tokens were counted.
token_countnumber: How many tokens the text is.
token_stringslist: Each token's text, in order.
tokenslist: The tokens, as the numbers the model reads.

Example output

{
  "character_count": 12,
  "model": "command-a-plus-05-2026",
  "token_count": 3,
  "token_strings": [
    "Hello",
    " world",
    "!"
  ],
  "tokens": [
    28339,
    2286,
    38
  ]
}

Create embeddings

Turn texts into vectors with Cohere Embed for semantic search, deduplication, clustering or classification, ready to store in a vector database such as Pinecone or Qdrant.

Inputs

TextstextslistRequired: The texts to turn into vectors, one per entry. Each gives one vector, in the same order; up to 1,000.
What the texts areinput_typetext: Embed what you store as 'Documents to search' and what you look things up with as 'Search queries': Cohere makes the two kinds to match each other.One of: search_document (Documents to search (to store)), search_query (Search queries (to look up with)), classification (Texts to classify), clustering (Texts to group). Default: search_document.
Modelmodeltext: Which Embed model to use. Match the model already used for any vectors you will compare these with.One of: embed-v5.0-pro (Embed 5 Pro (most capable, recommended)), embed-v5.0-fast (Embed 5 Fast), embed-v4.0 (Embed 4), embed-multilingual-v3.0 (Embed Multilingual 3 (1,024 numbers)), embed-english-v3.0 (Embed English 3 (1,024 numbers)), embed-multilingual-light-v3.0 (Embed Multilingual Light 3 (384 numbers)), embed-english-light-v3.0 (Embed English Light 3 (384 numbers)). Default: embed-v5.0-pro.
Vector lengthdimensionstext: Shorter vectors take less storage. Embed 5 and Embed 4 can be shortened; the older models always give their own length.One of: full (Full length (the model's default)), 256 (256 numbers), 512 (512 numbers), 768 (768 numbers (Embed 5 only)), 1024 (1,024 numbers), 1536 (1,536 numbers), 2048 (2,048 numbers (Embed 5 only)). Default: full.

Outputs

countnumber: How many vectors.
dimensionsnumber: How many numbers each vector has.
embeddinglist: The first text's vector.
embeddingslist: One vector per text, in the same order.
input_tokensnumber: Tokens billed.
input_typetext: What the texts were embedded as.
modeltext: The model used.

Example output

{
  "count": 2,
  "dimensions": 3,
  "embedding": [
    0.012,
    -0.043,
    0.031
  ],
  "embeddings": [
    [
      0.012,
      -0.043,
      0.031
    ],
    [
      0.018,
      -0.039,
      0.027
    ]
  ],
  "input_tokens": 14,
  "input_type": "search_document",
  "model": "embed-v5.0-pro"
}

Extract data

Pull the fields you name out of text or pictures, such as the total on a photographed receipt or the sender's company in an email, ready for a spreadsheet row or a CRM record. A field the material does not mention comes back empty, never guessed.

Inputs

Texttexttext: The text to pull the fields out of, such as an email or an invoice. Leave blank when the images hold everything.
Imagesimageslist: Pictures to read: upload them, pick files from an earlier step, or paste public web addresses. PNG, JPEG, WebP or GIF (other formats are converted), up to 20.
Fieldsfieldslist: The pieces of information you want, one per entry. Add what each means after a colon to steer it: 'total: the amount due in dollars'.
Instructionsinstructionstext: Extra rules, such as 'Write dates as YYYY-MM-DD'.
Modelmodeltext: Which Cohere model reads the material. Pictures need Command A+ or Command A Vision.One of: command-a-plus-05-2026 (Command A+ (reads images, recommended)), command-a-vision-07-2025 (Command A Vision (reads images)), command-a-03-2025 (Command A), command-r-plus-08-2024 (Command R+), command-r-08-2024 (Command R). Default: command-a-plus-05-2026.
JSON Schema (advanced)json_schematext: Instead of 'Fields', paste a JSON Schema whose root is an object, for numbers, lists or nested fields. Every object in it must list its required fields. When set, 'Fields' is ignored.

Outputs

dataobject: The fields, by the names asked for.
found_fieldslist: The fields that were filled.
input_tokensnumber: Tokens read, as billed.
missing_fieldslist: The fields the material did not mention.
modeltext: The model that read it.
output_tokensnumber: Tokens written, as billed.

Example output

{
  "data": {
    "invoice number": "INV-1042",
    "total": "$1,250.00",
    "vendor": "Acme Ltd"
  },
  "found_fields": [
    "invoice number",
    "vendor",
    "total"
  ],
  "input_tokens": 212,
  "missing_fields": [],
  "model": "command-a-plus-05-2026",
  "output_tokens": 31
}

Generate a Cohere response

Send a prompt to a Cohere Command model and get back its written response, as text or as a JSON object a later step can read field by field.

Inputs

PromptprompttextRequired: The message or question to send to Cohere.
Modelmodeltext: Which Cohere model writes the response. Command A+ suits most jobs; Command A Reasoning thinks first, for harder problems; Command R7B is the fastest. Defaults to command-a-plus-05-2026.One of: command-a-plus-05-2026 (Command A+ (most capable, recommended)), command-a-reasoning-08-2025 (Command A Reasoning (thinks before it answers)), command-a-03-2025 (Command A), command-r-plus-08-2024 (Command R+), command-r-08-2024 (Command R), command-r7b-12-2024 (Command R7B (fastest, lowest cost)). Default: command-a-plus-05-2026.
Maximum response lengthmax_tokensnumber: The most tokens the response may use; a token is about three-quarters of a word. Leave blank to use the model's own maximum output length.At least 1.
Instructionsinstructionstext: How the model should behave, such as 'Answer in one short paragraph' or 'You are a friendly support agent for Acme'.
Creativity (temperature)temperaturenumber: From 0 (focused and repeatable) to 1 (most varied). Leave blank for Cohere's default of 0.3.From 0 to 1.0.
Thinkingthinkingtext: Whether a reasoning model (Command A+ or Command A Reasoning) thinks before it answers. Thinking is slower and uses more tokens, and comes back separately from the response. Other models never think. Off works as expected on Command A Reasoning; Command A+ then reasons inside its answer instead.One of: default (Model's default), on, off. Default: default.
Response formatreply_formattext: Choose 'A JSON object' to get the response as data, in 'data'. Say in the prompt which fields the object should have.One of: text, json (A JSON object). Default: text.

Outputs

dataobject: The response as a JSON object, when the response format is A JSON object.
finish_reasontext: COMPLETE when it finished, MAX_TOKENS when it was cut off, STOP_SEQUENCE when it stopped at a stop word.
input_tokensnumber: Tokens read, as billed.
modeltext: The model that answered.
output_tokensnumber: Tokens written, as billed.
response_texttext: The text that Cohere generated for your prompt.
statustext: Action execution status.
thinkingtext: The model's reasoning, when it thought first.
was_cut_offtrue/false: Whether it hit the maximum response length.

Example output

{
  "data": null,
  "finish_reason": "COMPLETE",
  "input_tokens": 18,
  "model": "command-a-plus-05-2026",
  "output_tokens": 24,
  "response_text": "Here is a thoughtful response to your question about artificial intelligence and its applications in modern software development.",
  "status": "success",
  "thinking": null,
  "was_cut_off": false
}

Get a model

Look up one Cohere model: what it is for, how much text it takes in, the abilities it has and whether it is deprecated.

Inputs

ModelmodeltextRequired: The model to look up. Pick one, or type its name, such as command-a-plus-05-2026.

Outputs

context_lengthnumber: The most tokens it can take in at once.
default_forlist: The endpoints it is Cohere's default model for.
endpointslist: What it can be used for: chat, embed, rerank and so on.
featureslist: Extra abilities, such as tool use, vision or JSON output.
is_deprecatedtrue/false: Whether Cohere has deprecated it.
is_fine_tunedtrue/false: Whether it is a fine-tuned model.
nametext: The model's name, to use in any Cohere step.
sampling_defaultsobject: The settings it uses when a request leaves them out, such as temperature.
tokenizer_urltext: Where its tokenizer's configuration lives.

Example output

{
  "context_length": 128000,
  "default_for": [
    "chat"
  ],
  "endpoints": [
    "chat"
  ],
  "features": [
    "tools",
    "json_mode",
    "vision",
    "reasoning"
  ],
  "is_deprecated": false,
  "is_fine_tuned": false,
  "name": "command-a-plus-05-2026",
  "sampling_defaults": {
    "p": 0.75,
    "temperature": 0.3
  },
  "tokenizer_url": "https://storage.googleapis.com/cohere-public/tokenizers/command-a-plus-05-2026.json"
}

List models

List the Cohere models this API key can use, with what each is for, how much text it takes in and the abilities it has.

Inputs

What it's forendpointtext: Only models that do this.One of: all (Anything), chat, embed (Embeddings), rerank (Reranking). Default: all.

Outputs

countnumber: How many there are.
model_nameslist: Every model's name, in the same order.
modelslist: The models, by name.

Example output

{
  "count": 1,
  "model_names": [
    "command-a-plus-05-2026"
  ],
  "models": [
    {
      "context_length": 128000,
      "default_for": [
        "chat"
      ],
      "endpoints": [
        "chat"
      ],
      "features": [
        "tools",
        "json_mode",
        "vision",
        "reasoning"
      ],
      "is_deprecated": false,
      "is_fine_tuned": false,
      "name": "command-a-plus-05-2026"
    }
  ]
}

Parse a document

Turn a PDF, a scan or a photo of a document into Markdown with Cohere Parse, keeping its reading order, lists and tables, and describing its pictures. Reads up to 20 pages a step.

Inputs

DocumentdocumenttextRequired: The PDF or page image to parse: upload a file, pick one an earlier step produced, or paste a link to one.
First pagefirst_pagenumber: For a PDF, the first page to parse. Leave blank to start at page 1.At least 1.
Last pagelast_pagenumber: For a PDF, the last page to parse. Leave blank to go to the end; a step parses up to 20 pages.At least 1.

Outputs

markdowntext: Every page parsed, as one Markdown text.
modeltext: The model used.
page_countnumber: How many pages were parsed.
pageslist: Each page, in order.

Example output

{
  "markdown": "# Invoice INV-1042\n\n<table><tr><td>Total</td><td>$1,250.00</td></tr></table>",
  "model": "parse-v5.0",
  "page_count": 1,
  "pages": [
    {
      "images": [],
      "markdown": "# Invoice INV-1042\n\n<table><tr><td>Total</td><td>$1,250.00</td></tr></table>",
      "page": 1
    }
  ]
}

Rank documents by relevance

Order a list of texts or records by how well each answers a question, best first, with a score from 0 to 1. Useful for picking the passages or rows to hand an AI step.

Inputs

QuestionquerytextRequired: What you are looking for, written as a question or a search.
DocumentsdocumentslistRequired: The texts or records to rank, one per entry; up to 1,000. Records are ranked on all of their fields.
How many to returntop_nnumber: Keep only the best matches. Leave blank to rank them all.At least 1.
Modelmodeltext: Which Rerank model to use.One of: rerank-v4.0-pro (Rerank 4 Pro (most accurate, recommended)), rerank-v4.0-fast (Rerank 4 Fast), rerank-v3.5 (Rerank 3.5), rerank-multilingual-v3.0 (Rerank Multilingual 3), rerank-english-v3.0 (Rerank English 3). Default: rerank-v4.0-pro.

Outputs

countnumber: How many were returned.
modeltext: The model used.
querytext: The question.
resultslist: The documents, best match first.
top_documenttext: The best match's text.
top_positionnumber: Where the best match was in the list, from 1.
top_scorenumber: The best match's score, from 0 to 1.

Example output

{
  "count": 2,
  "model": "rerank-v4.0-pro",
  "query": "What is the capital of France?",
  "results": [
    {
      "document": "Paris is the capital of France.",
      "position": 2,
      "rank": 1,
      "score": 0.98
    },
    {
      "document": "The Loire is France's longest river.",
      "position": 1,
      "rank": 2,
      "score": 0.07
    }
  ],
  "top_document": "Paris is the capital of France.",
  "top_position": 2,
  "top_score": 0.98
}

Transcribe audio

Write down what is said in a recording with Cohere Transcribe, in any of 14 languages. Takes MP3, WAV, FLAC or OGG recordings of up to 25 MB.

Inputs

RecordingrecordingtextRequired: The recording to transcribe: upload a file, pick one an earlier step produced, or paste a link to one.
Languagelanguagetext: The language being spoken. Cohere Transcribe does not detect it, so pick the one the recording is in.One of: en (English), ar (Arabic), zh (Chinese), nl (Dutch), fr (French), de (German), el (Greek), it (Italian), ja (Japanese), ko (Korean), and 4 more. Default: en.
Modelmodeltext: Which Cohere Transcribe model listens.One of: cohere-transcribe-03-2026 (Cohere Transcribe (recommended)), cohere-transcribe-arabic-07-2026 (Cohere Transcribe Arabic (for Arabic speech)). Default: cohere-transcribe-03-2026.

Outputs

languagetext: The language listened for, as a code.
modeltext: The model used.
texttext: What was said.
word_countnumber: How many words were heard.

Example output

{
  "language": "en",
  "model": "cohere-transcribe-03-2026",
  "text": "Thanks for calling Acme support, how can I help you today?",
  "word_count": 11
}

Translate text

Translate text into another language with Command A Translate, Cohere's model built for translation in 23 languages, or North Small Translate for more than 50.

Inputs

TexttexttextRequired: The text to translate.
Translate intotarget_languagetextRequired: The language to translate into, such as Spanish, Japanese or Brazilian Portuguese.
Translate fromsource_languagetext: The language the text is in. Leave blank to let the model tell.
Instructionsinstructionstext: How to translate, such as 'Keep a formal tone' or 'Leave product names in English'.
Modelmodeltext: Which Cohere model translates.One of: command-a-translate-08-2025 (Command A Translate (23 languages, recommended)), north-small-translate-09-2026 (North Small Translate (50+ languages)), command-a-plus-05-2026 (Command A+). Default: command-a-translate-08-2025.

Outputs

finish_reasontext: COMPLETE when it finished, MAX_TOKENS when it was cut off, STOP_SEQUENCE when it stopped at a stop word.
input_tokensnumber: Tokens read, as billed.
modeltext: The model that answered.
output_tokensnumber: Tokens written, as billed.
source_languagetext: The language it was translated from, if given.
target_languagetext: The language it was translated into.
translationtext: The translated text.
was_cut_offtrue/false: Whether it hit the maximum response length.

Example output

{
  "finish_reason": "COMPLETE",
  "input_tokens": 41,
  "model": "command-a-translate-08-2025",
  "output_tokens": 17,
  "source_language": null,
  "target_language": "Spanish",
  "translation": "Los reembolsos se emiten en un plazo de 5 d\u00edas h\u00e1biles.",
  "was_cut_off": false
}

ActionsCopy Anchor Link

Answer from documentsCopy Anchor Link

Inputs

Outputs

Ask about an imageCopy Anchor Link

Inputs

Outputs

Classify textCopy Anchor Link

Inputs

Outputs

Count tokensCopy Anchor Link

Inputs

Outputs

Create embeddingsCopy Anchor Link

Inputs

Outputs

Extract dataCopy Anchor Link

Inputs

Outputs

Generate a Cohere responseCopy Anchor Link

Inputs

Outputs

Get a modelCopy Anchor Link

Inputs

Outputs

List modelsCopy Anchor Link

Inputs

Outputs

Parse a documentCopy Anchor Link

Inputs

Outputs

Rank documents by relevanceCopy Anchor Link

Inputs

Outputs

Transcribe audioCopy Anchor Link

Inputs

Outputs

Translate textCopy Anchor Link

Inputs

Outputs

On this page

Actions

Answer from documents

Ask about an image

Classify text

Count tokens

Create embeddings

Extract data

Generate a Cohere response

Get a model

List models

Parse a document

Rank documents by relevance

Transcribe audio

Translate text