cohere website screenshot

cohere

Generates a text response to a user message and streams it down, token by token.

9 APIs 16 Features

APIs

Cohere Chat API

The Cohere Chat API enables developers to integrate large language model text generation capabilities into their applications through a conversational interface. It supports mul...

Cohere Embed API

The Cohere Embed API generates vector embeddings from text and images, enabling semantic search, clustering, and classification use cases. It supports multilingual content and c...

Cohere Rerank API

The Cohere Rerank API takes a query and a list of text documents and returns them ordered by relevance with assigned relevance scores. It is commonly used as a second-stage rank...

Cohere Classify API

The Cohere Classify API performs text classification by assigning labels to input text based on provided examples. It can be used for sentiment analysis, content moderation, top...

Cohere Embed Jobs API

The Cohere Embed Jobs API allows developers to create and manage batch embedding jobs for processing large volumes of text data asynchronously. Rather than embedding texts one a...

Cohere Datasets API

The Cohere Datasets API provides endpoints for uploading, managing, and retrieving datasets used with other Cohere services such as fine-tuning and embed jobs. Developers can cr...

Cohere Models API

The Cohere Models API allows developers to list and retrieve information about available Cohere models, including the Command, Embed, and Rerank model families. It provides deta...

Cohere Tokenize API

The Cohere Tokenize API splits input text into tokens using the tokenizer associated with a specified model. It returns both the token strings and their corresponding token IDs....

Cohere Detokenize API

The Cohere Detokenize API converts a sequence of token IDs back into their corresponding text string using the tokenizer for a specified model. It is the inverse operation of th...

Collections

Cohere Chat API

OPEN

Cohere Classify API

OPEN

Cohere Datasets API

OPEN

Cohere Detokenize API

OPEN

Cohere Embed API

OPEN

Cohere Embed Jobs API

OPEN

Cohere Models API

OPEN

Cohere Rerank API

OPEN

Cohere Tokenize API

OPEN

GraphQL

Cohere GraphQL Schema

This document describes a conceptual GraphQL schema for the Cohere AI API, covering the full surface of Cohere's language model, embedding, reranking, classification, tokenizati...

GRAPHQL

Pricing Plans

Cohere Plans Pricing

6 plans

PLANS

Rate Limits

Cohere Rate Limits

5 limits

RATE LIMITS

FinOps

Cohere Finops

FINOPS

Features

Command at $1/$2 per MTok input/output
Command-light at $0.30/$0.60
Command R at $0.50/$1.50
Command R+ 08-2024 at $2.50/$10
Command R+ 04-2024 at $3/$15
Aya Expanse multilingual at $0.50/$1.50
Embed v3 with English/multilingual
Rerank for relevance scoring
Production keys: 10K req/min Chat, 2K Embed, 10K Rerank
Trial keys: 20/min Chat, 100/min Embed
Connectors for RAG over data sources
Tool use and function calling
Compass for unstructured data search
Available on AWS Bedrock, Azure, Oracle Cloud
Fine-tuning for Command and Aya
OpenAI-compatible Chat Completions endpoint

Event Specifications

Cohere Streaming API

AsyncAPI definition for Cohere's HTTP+SSE streaming endpoints. Cohere's streaming responses are NOT delivered via WebSockets. They are delivered as Server-Sent Events (SSE) over...

ASYNCAPI

Semantic Vocabularies

Cohere Context

0 classes · 10 properties

JSON-LD

JSON Structure

Cohere Structure

0 properties

JSON STRUCTURE

Resources

👥
GitHubOrganization
GitHubOrganization
🔗
LinkedIn
LinkedIn
🔗
JSONLD
JSONLD
🔗
JSONSchema
JSONSchema
🔗
JSONSchema
JSONSchema
🔗
JSONSchema
JSONSchema
🔗
JSONSchema
JSONSchema
🔗
LlmsText
LlmsText

Sources

Raw ↑ 
opencollection: 1.0.0
info:
  name: Cohere Tokenize API
  version: '1.0'
request:
  auth:
    type: bearer
    token: '{{bearerToken}}'
items:
- info:
    name: Tokenize
    type: folder
  items:
  - info:
      name: Tokenize text
      type: http
    http:
      method: POST
      url: https://api.cohere.com/v1/tokenize
      body:
        type: json
        data: '{}'
    docs: Splits input text into smaller units called tokens using byte-pair encoding (BPE) for the specified model. Returns
      both the token strings and their corresponding integer token IDs. The text must be between 1 and 65536 characters.
bundled: true