# Cloudflare AI Gateway vs Not Diamond

| Attribute | Cloudflare AI Gateway | Not Diamond |
|---|---|---|
| **vioscaleAI score** | 65.1 (35% (low)) | 62.1 (60% (medium)) |
| content.faq | `[{"answer":"A platform providing visibility into AI API usage through analytics and logging, with controls for caching, rate limiting, and request management across multiple AI providers. It is indexed under Llm Gateways.","source":"https://developers.cloudflare.com/ai-gateway/reference/pricing/","question":"What is Cloudflare AI Gateway?","confidence":0.6},{"answer":"Cloudflare AI Gateway offers a free tier, so you can start without paying. Paid plans start at $0.05. Prices are published openly on the vendor's own pricing page. Pricing changes often, so verify at source before relying on it.","source":"https://developers.cloudflare.com/ai-gateway/reference/pricing/","question":"Is Cloudflare AI Gateway free?","confidence":0.6},{"answer":"We have confirmed browser-based access to Cloudflare AI Gateway. That is the extent of what we could verify from public sources, so it may well offer desktop or mobile clients we have not indexed.","source":"https://developers.cloudflare.com/ai-gateway/reference/pricing/","question":"What platforms does Cloudflare AI Gateway support?","confidence":0.6},{"answer":"We have only confirmed a cloud / SaaS deployment for Cloudflare AI Gateway, so it appears to be vendor-hosted. If a self-hosted option exists we have not found it documented publicly.","source":"https://developers.cloudflare.com/ai-gateway/reference/pricing/","question":"Can Cloudflare AI Gateway be self-hosted?","confidence":0.6},{"answer":"We have confirmed 10 integrations for Cloudflare AI Gateway, including Workers AI, Vectorize, MCP (Model Context Protocol), Third-party LLM models, OpenAI, Anthropic, Google Gemini and Replicate, plus 2 more. This is what we could verify from public sources, so the vendor may support others we have not indexed.","source":"https://developers.cloudflare.com/ai-gateway/reference/pricing/","question":"What does Cloudflare AI Gateway integrate with?","confidence":0.6}]` | - |
| deployment.options | `{"cloud":true}` | `{"cloud":true}` |
| description.long | An intermediary service that routes AI model requests through Cloudflare's network to provide visibility, caching, rate limiting, cost tracking, and data loss prevention. It enables organizations to observe and control AI traffic without modifying their existing tools or coding agents. | A model routing service for coding agents that uses machine learning to predict and recommend the most cost-effective and accurate AI model for each request. Engineering teams typically achieve 20-40% cost savings without quality degradation through continuous learning from real usage patterns. |
| features.capabilities | `{"caching":"exact","open_source":false,"pricing_model":"usage-based-saas","rate_limiting":true,"deployment_model":"managed-SaaS","architecture_model":"global_edge_network","automatic_failover":true,"guardrails_moderation":"built-in","openai_compatible_api":true,"request_cost_observability":true,"bring_your_own_keys_byok_routing":true,"pii_redaction_and_data_masking_in_flight":true,"universal_api_key_for_100_plus_llm_providers":true,"zero_data_retention_and_prompt_logging_opt_out":false,"auto_fallback_routing_on_rate_limit_or_downtime":true,"organization_wide_cost_tracking_and_chargebacks":true,"semantic_caching_for_repeat_queries_and_cost_savings":false}` | `{"pricing_model":"usage-based-saas","deployment_model":"managed-SaaS","routing_strategy":"custom","request_cost_observability":true}` |
| integrations.count | 6 | - |
| integrations.list | `[{"name":"Workers AI"},{"name":"Vectorize"},{"name":"MCP (Model Context Protocol)"},{"name":"Third-party LLM models"},{"name":"OpenAI"},{"name":"Anthropic"},{"name":"Google Gemini"},{"name":"Replicate"},{"name":"Cloudflare Workers"},{"name":"Agent Memory"},{"name":"Cloudflare Workers AI","native":true,"category":"ai"},{"name":"Cloudflare Vectorize","native":true,"category":"database"},{"name":"Claude Code","native":true,"category":"coding_agent"},{"name":"Claude Desktop","native":true,"category":"coding_agent"},{"name":"GitHub Copilot CLI","native":true,"category":"coding_agent"},{"name":"OpenAI Codex","native":true,"category":"coding_agent"},{"name":"OpenCode","native":true,"category":"coding_agent"},{"name":"Pi","native":true,"category":"coding_agent"}]` | - |
| market.availability | `{"primaryMarkets":[],"availabilityScope":"global","availableCountries":[],"notAvailableCountries":[]}` | `{"primaryMarkets":["US"],"availabilityScope":"global","availableCountries":[],"notAvailableCountries":[]}` |
| platform.support | `{"web":true}` | - |
| pricing | `{"type":"hybrid","plans":[{"free":true,"name":"Free","features":["dashboard analytics","caching","rate limiting","DLP scanning"],"description":"Core AI Gateway features: dashboard analytics, caching, rate limiting, and DLP scanning"},{"free":false,"name":"Workers Paid","features":["10M log storage per gateway","Logpush available"],"components":[{"per":{"qty":1,"unit":"million requests"},"kind":"metered","amount":0.05,"currency":"USD","description":"Logpush requests after 10 million/month"}],"description":"Higher log storage limits and Logpush available","includedLimits":{"log_storage":"10,000,000 logs per gateway"}}],"summary":"Free for core features (caching, rate limiting, analytics). Paid log storage and Logpush available on Workers Paid plan.","currency":"USD","freeTier":true,"sourceUrl":"https://developers.cloudflare.com/ai-gateway/reference/pricing/","retrievedAt":"2026-10-02T16:15:28.076Z","startingPrice":{"unit":"million requests","amount":0.05,"currency":"USD"}}` | `{"type":"usage","plans":[{"free":false,"name":"Pay-as-you-go","summary":"$0.05 per million tokens routed","features":["Multi-harness support","Multi-provider support","Savings and usage dashboard","Continuous learning from harness usage"],"components":[{"per":{"qty":1,"unit":"million tokens"},"kind":"metered","amount":0.05,"currency":"USD"}],"description":"For developers and small teams","contactSales":false},{"free":false,"name":"Enterprise","summary":"Custom pricing","features":["Volume-based discounts","Organization-wide analytics","Advanced security and admin controls","SSO with SAML","Privacy-preserving deployment"],"description":"For enterprise teams ready to scale","contactSales":true}],"summary":"$0.05 per million tokens; enterprise plans available","currency":"USD","sourceUrl":"https://notdiamond.ai/pricing","retrievedAt":"2026-10-06T22:08:09.888Z","startingPrice":{"unit":"million tokens","amount":0.05,"currency":"USD"}}` |
| pricing.free_tier | yes | - |
| pricing.model | freemium | commercial |
| pricing.price_level | low | low |
| pricing.starting_price | `{"amount":0.05,"currency":"USD"}` | `{"amount":0.05,"currency":"USD"}` |
| pricing.transparent | yes | yes |
| security.certifications | - | `[{"name":"SOC 2","status":"active"},{"name":"ISO 27001","status":"active"}]` |
| security.iso27001 | - | yes |
| security.soc2 | - | yes |

## Capabilities (Llm Gateways)

| Capability | Cloudflare AI Gateway | Not Diamond |
|---|:--:|:--:|
| **Capabilities** |  |  |
| Openai compatible API | ✓ | - |
| Automatic failover | ✓ | - |
| Routing strategy | - | Custom |
| Caching | Exact | - |
| Virtual key management | - | - |
| Budget spend controls | - | - |
| Rate limiting | ✓ | - |
| Guardrails moderation | Built in | - |
| Request cost observability | ✓ | ✓ |
| Streaming support | - | - |
| Deployment model | Managed SaaS | Managed SaaS |
| Open source | ✗ | - |
| Pricing model | Usage based saas | Usage based saas |

*Source: vioscaleAI. Generated 2026-10-16T19:06:35.378Z. "-" = undocumented, not absent.*