Cohere API

Hosted text models for chat, embedding, rerank and classification.

Provider: default
Kind: AI service
Category: Compute
Official docs: https://docs.cohere.com/docs/rate-limits

Properties · 6 set by this component

property	type	values	required	kind default	this component
auth	enum	api-key \| oauth \| iam \| none	no	—	▸ api-key
contentFiltering	boolean	—	no	—	▸ true
customerManagedKeys	boolean	—	no	—	inherited
dataResidency · advanced	enum	us \| eu \| asia \| global	no	—	inherited
dataRetentionDays	integer	—	no	—	inherited
endpoint · component property	enum	chat \| embed \| rerank \| classify	no	chat	inherited
keyStore	boolean	—	no	false	inherited
keyType · component property	enum	trial \| production	no	trial	inherited
managed	boolean	—	no	false	▸ true
modality	enum	text \| vision \| speech \| multimodal \| structured \| image \| video \| audio \| embedding \| rerank	no	—	▸ text
publicEndpoint	boolean	—	no	—	▸ true
quotaUnitsPerMinute	integer	—	no	—	▸ 20
rateLimitRpm · advanced	integer	—	no	—	inherited
rateLimitTpm · advanced	integer	—	no	—	inherited
safetyMode · component property	enum	contextual \| strict \| off	no	contextual	inherited
trainingOptOut · component property	boolean	—	no	false	inherited
viaGateway	boolean	—	no	false	inherited

Rules that apply · 2

Every rule whose selector covers this component's kind or its category. Whether a rule fires depends on the design: its properties, its edges and its groups.

AI API key not managedwarning

ai-api-key-unmanaged

This AI vendor is reached with an API key, and nothing in the design holds or rotates that key. It ends up in environment files or code, every caller shares it, and a single leak runs up the vendor bill until someone notices. Put the key in a key-management component, or say it is held there with keyStore.

— all of these hold:
— the node's `auth` is "api-key"
— the node's `keyStore` is false
— the node has at least one incoming edge from an app-server, worker or client
— this does not hold:
— the design contains a node of kind key-management

Stateful node without zone redundancyerror

stateful-node-without-zone-redundancy

A stateful compute node pinned to exactly one availability zone disappears with that zone, and its state goes with it. Nodes inside a cell are exempt, because there the cell is deliberately single-zone and redundancy comes from the other cells.

— all of these hold:
— the node's `stateless` is false
— the node sits inside exactly 1 availability-zone group
— this does not hold:
— the node sits inside at least one cell group

Use it in a design

nodes:
  - { id: "cohere-api", component: "cohere-api" }

Other AI service products · 125

and 85 more → AI service page

Source

1# yaml-language-server: $schema=../../schema/component.schema.json
2# Cohere API: hosted text models for chat, embedding, rerank and classification over a public endpoint.
3# Per "Different Types of API Keys and Rate Limits", a new account gets a trial key limited to 20 requests
4# per minute on the Chat API and production keys allow 500; per "Safety Modes", the Chat API applies
5# safety mode CONTEXTUAL unless the request asks for STRICT or OFF.
6schemaVersion: "1"
7type: "component"
8id: "cohere-api"
9kind: "ai-service"
10provider: "default"
11docs: "https://docs.cohere.com/docs/rate-limits"
12defaults:
13  auth: "api-key"
14  managed: true
15  modality: "text"
16  publicEndpoint: true
17  contentFiltering: true
18  quotaUnitsPerMinute: 20
19properties:
20  keyType:
21    type: "enum"
22    values: ["trial", "production"]
23    default: "trial"
24  safetyMode:
25    type: "enum"
26    values: ["contextual", "strict", "off"]
27    default: "contextual"
28  endpoint:
29    type: "enum"
30    values: ["chat", "embed", "rerank", "classify"]
31    default: "chat"
32  trainingOptOut:
33    type: "boolean"
34    default: false

The same page as markdown, for an agent: /catalogue/components/cohere-api.md