Coveo vs Onyx
Coveo
coveo.comOnyx
onyx.appSide by side
| Figure | Coveo | Onyx |
|---|---|---|
| Price from | — | $20/mo |
| Free plan | — | Yes |
| Free trial | Yes | Yes |
| Open source | — | Yes |
| Web | Yes | Yes |
| Windows | — | Yes |
| macOS | — | Yes |
| Linux | — | Yes |
| API | Yes | Yes |
| Self-hosted | — | Yes |
| Plans published | 1 | 3 |
| Spec score · AI Enterprise Search Software | 7.9 (#10) | 8.9 (#3) |
| Founded | 2004 | G2 lists Onyx AI as serving customers since 2023 and gives 2023 as its founding year. |
| Integrations | Coveo lists native integrations including Adobe, Agentforce, Salesforce, ServiceNow, Sitecore, Zendesk, SAP, Shopify, and OpenAI ChatGPT Enterprise; it also offers open APIs and frameworks for custom integrations. | The product advertises more than 50 synced connectors and names Slack, Google Drive, Confluence, Salesforce, GitHub and Jira among supported sources. |
| Search | The platform includes hybrid search, advanced rules and business logic, A/B testing, and query pipeline management. | Onyx searches indexed sources in parallel and presents relevant documents with source permissions enforced. |
| Security | Coveo states that hosted customer data is encrypted at rest with AES-256 and in transit using TLS 1.3, with TLS 1.2 supported for compatibility. | The site says documents and embeddings can stay in the customer's infrastructure, data is not used for training, and source permissions are enforced at query time. |
| Support | The pricing page lists Coveo Care, business value assessment and realization, and an implementation partner network; Technical Account Manager and Developer Support are listed as add-ons. | The Business plan includes Community Support; Enterprise lists Dedicated Support and an Enterprise SLA. |
| What it does | Coveo provides an AI-Relevance Platform for search, recommendations, personalization, and product or knowledge discovery across commerce, service, website, and workplace experiences. | Onyx connects organizational knowledge sources to chat, search, agents and AI workflows, acting as a context layer for people and agents. |
Plans
In their own words
Coveo
Coveo is a cloud AI-Relevance Platform for search, recommendations, personalization, and discovery across commerce, service, website, and workplace experiences. Its hybrid search combines advanced rules, business logic, A/B testing, and query pipeline management. A unified index, native and universal connectors, document-level security, permissions, and refresh controls support indexed content. Behavioral features include query suggestions, Automatic Relevance Tuning, dynamic navigation, and content recommendations. Generative and agentic options include conversational search, generative answering, Answer API, Coveo for Agentforce, Passage Retrieval API, and Smart Snippets; the pricing page marks this suite as an add-on. Commerce capabilities cover catalog indexing, recommendations, listing optimization, merchandising, and conversational product discovery, with some add-ons. Integrations include Adobe, Salesforce, ServiceNow, Sitecore, Zendesk, SAP, Shopify, and OpenAI ChatGPT Enterprise, plus open APIs. Hosted data uses AES-256 at rest and TLS 1.3 in transit. Pricing is on request, and a trial organization lasts 14 days.
Onyx
Onyx connects enterprise knowledge so people and AI agents can use relevant context in answers. It searches indexed sources in parallel and presents documents while enforcing each source's permissions. More than 50 connectors sync connected tools in the background and support hybrid semantic and keyword search. The Business plan lists chat and search, major LLM access, custom agents, MCP/OpenAPI actions, web search, deep research, code interpreter, and image generation. Business costs $20 a month, billed annually at $20 per user per month, for teams of any size, with 40+ app connectors and Community Support. Onyx provides APIs for messages, agents, LLM management, actions, and user authentication. Slack integrations can provide responses and agents; Microsoft Teams and Zendesk are described as coming soon. Deployments can run in a customer's cloud or on bare metal, including on-premise and fully air-gapped environments. The site says documents and embeddings can remain in customer infrastructure, data is not used for training, and permissions are checked at query time. Native Windows, macOS, and Linux apps connect to an existing deployment.