HEAD-TO-HEAD · FACTS ONLY
Cloudflare AI Gateway vs Onyx: AI endpoint control facts side by side
Short answer
By The Device Desk · Endpoint AI Finder · Published 2026-10-11
Desk research from public vendor pages read on 27 September and 11 October 2026. Profiles follow our published method; we did not run the products.
Vendor pages read September and October 2026 · updated 2026-10-13
Where do their controls sit?
- Filled or hatched marker: Cloudflare AI Gateway
- Dashed teal ring: Onyx, described
- DEV Filled marker: described on the product pages we read
- DEV Hatched marker: partly described (another component, a narrower scope, or method not detailed)
- DEV Dashed marker: not in our sources (it may exist; we did not find it)
What are the facts, side by side?
| Fact | Cloudflare AI Gateway | Onyx |
|---|---|---|
| Owner | None | None |
| Positioning | A gateway for AI applications: Cloudflare's documentation describes it as a way to observe and control AI apps, with analytics on requests, tokens and cost, logging, caching, rate limiting, request retry and model fallback across providers including Workers AI, Anthropic, Google Gemini, OpenAI and Replicate. It governs apps you build, not employees' devices. | "The Secure AI Control Plane for the Agentic Era": inline inspection of prompts, tool calls and model responses across browser AI, coding assistants, desktop AI agents, cloud workloads and MCP servers. Based in Tel Aviv and New York. |
| How it reaches devices | Routed in front of model providers from your own applications; Cloudflare says it takes one line of code to start. Source: Cloudflare AI Gateway documentation · Read 11 Oct 2026 | Endpoint agents, browser extensions, APIs and gateways. Source: Onyx Security: AI security platform · Read 27 Sep 2026 |
| On-device controlDiffers | Not in our sourcesNot described on the pages we read. | DescribedEndpoint agents cover coding assistants and desktop AI agents. Source: Onyx Security: AI security platform · Read 27 Sep 2026 |
| Browser extensionDiffers | Not in our sourcesNot described on the pages we read. | DescribedBrowser extensions cover browser AI. Source: Onyx Security: AI security platform · Read 27 Sep 2026 |
| Network or SSE proxy | Not in our sourcesNot described on the pages we read. | Not in our sourcesNot described on the pages we read. |
| AI or MCP gateway | DescribedAn AI gateway with analytics, logging, caching, rate limiting, retry and model fallback for AI applications. Source: Cloudflare AI Gateway documentation · Read 11 Oct 2026 | DescribedGateways and APIs inspect traffic inline. Source: Onyx Security: AI security platform · Read 27 Sep 2026 |
| Names the coding agents it coversDiffers | Not in our sources | PartlyCovers coding assistants; specific tools are not named on the pages we read. Source: Onyx Security: AI security platform · Read 27 Sep 2026 |
| Decides on a tool call before it runsDiffers | Not in our sources | MatchesInspects every prompt, tool call and model response inline. Source: Onyx Security: AI security platform · Read 27 Sep 2026 |
| Controls what goes into browser AIDiffers | Not in our sources | MatchesCan mask data in browser AI as well as block it. Source: Onyx Security: AI security platform · Read 27 Sep 2026 |
| Rolls out through EDR or device management you run | Not in our sources | Not in our sources |
| Can warn or ask instead of only blockingDiffers | Not in our sources | MatchesFive actions: alert, block, mask, steer or ask. Source: Onyx Security: AI security platform · Read 27 Sep 2026 |
| Can block an agent, tool or actionDiffers | Not in our sources | MatchesBlock is one of five actions. Source: Onyx Security: AI security platform · Read 27 Sep 2026 |
| Has a watch-only or simulation mode | PartlyAnalytics and logs on requests, tokens and cost without changing the traffic. Source: Cloudflare AI Gateway documentation · Read 11 Oct 2026 | PartlyAlert is one of five actions; a simulation mode is not described. Source: Onyx Security: AI security platform · Read 27 Sep 2026 |
| Records who or what took each action | PartlyLogs requests; tying a call to a person or an agent is not described. Source: Cloudflare AI Gateway documentation · Read 11 Oct 2026 | PartlyIntegrates with Okta, Entra and Splunk; separating a person from an agent is not described. Source: Onyx Security: AI security platform · Read 27 Sep 2026 |
| Also covers SaaS, cloud or homegrown AI | MatchesBuilt for AI applications you build and run. Source: Cloudflare AI Gateway documentation · Read 11 Oct 2026 | MatchesCloud workloads and MCP servers as well as devices. Source: Onyx Security: AI security platform · Read 27 Sep 2026 |
| Has a public price or tiers (vendor site or marketplace) | Not in our sources | Not in our sources |
| Built into | None | None |
| Works with | None in our sources | Lists CrowdStrike among its integrations. Source: Onyx Security: AI security platform · Read 27 Sep 2026 |
| Price | Available on all Cloudflare plans, per the documentation; plan prices are not on the page we read. Source: Cloudflare AI Gateway documentation · Read 11 Oct 2026 | Not published. Source: Onyx Security homepage · Read 27 Sep 2026 |
Where do they differ?
- On-device control: Cloudflare AI Gateway is not in our sources; Onyx describes it.
- Browser extension: Cloudflare AI Gateway is not in our sources; Onyx describes it.
- Names the coding agents it covers: Cloudflare AI Gateway is not in our sources; Onyx partly matches.
- Decides on a tool call before it runs: Cloudflare AI Gateway is not in our sources; Onyx matches.
- Controls what goes into browser AI: Cloudflare AI Gateway is not in our sources; Onyx matches.
- Can warn or ask instead of only blocking: Cloudflare AI Gateway is not in our sources; Onyx matches.
- Can block an agent, tool or action: Cloudflare AI Gateway is not in our sources; Onyx matches.
Choose Cloudflare AI Gateway if
- You build your own AI apps and want one place to log and control their model calls
- You already use Cloudflare and want AI traffic to pass through it
Choose Onyx if
- You want masking or steering rather than only allow or block
- AI use spans the browser, desktop apps, coding tools and cloud workloads
Which limits should you check?
Cloudflare AI Gateway
- It is an application gateway: it does not see employees' AI tools, coding agents or devices.
- Content controls such as blocking prompts are not described on the page we read, and plan prices are not on it.
Onyx
- Uses its own endpoint agents and browser extensions, so there is something new to roll out to devices.
- No pricing published, and specific coding agents are not named on the pages we read.