Cloudflare AI Gateway
Provider rates pass through
Cloudflare AI Gateway billing summary
Platform pricing
Routing
Core gateway features free
Access
Caching and rate limits
Model catalog checked Oct 18, 2026. Official pricing
Cloudflare AI Gateway pricing and fees
Fee rules checked .
- Free core features
- Core analytics, caching and rate limiting are free on all plans. Model inference still costs money. Logpush exports are billed by volume and transformation, and Guardrails uses billable Workers AI inference. Source
- BYOK or unified billing
- With your own provider key, the provider bills your model usage. With unified billing, you buy Cloudflare credits in advance and pay 5% on the amount purchased. Cloudflare passes through provider model rates without an inference markup. Source
Two credit-funded GPT-4.1 examples
Official OpenAI rates: $2.00 per 1 million input tokens and $8.00 per 1 million output tokens. These are aggregate comparison workloads across multiple requests, not monthly plans or single prompts.
1M input + 1M output tokens
Tokens: 1 × $2.00 + 1 × $8.00 = $10.00.
One $10.00 credit purchase + $0.50 purchase fee = $10.50 USD paid.
Unified billing credit purchase. Fee: 5% of credits purchased. Direct API token cost: $10.00.
10M input + 10M output tokens
Tokens: 10 × $2.00 + 10 × $8.00 = $100.00.
One $100.00 credit purchase + $5.00 purchase fee = $105.00 USD paid.
Unified billing credit purchase. Fee: 5% of credits purchased. Direct API token cost: $100.00.
Assumes no existing credit balance, one purchase funding the full workload, standard uncached text rates and no batch discount. Excludes taxes, currency conversion, other payment charges, subscriptions and optional add-ons. BYOK is not included. Totals use provider rates as a benchmark; check the selected model route before buying.
Model quote checked .
How Cloudflare AI Gateway compares
Compare all LLM gatewaysBYOK
Yes. Provider keys can be stored in Secrets Store
Routing
Dynamic routing, fallbacks, rate limits and caching
Observability
Analytics, configurable logging and Logpush export
Deployment and data controls
Managed service; ZDR for OpenAI and Anthropic unified billing
Country and region availability
Sources checked 2026-08-22Cloudflare documents AI Gateway as available on all Cloudflare plans, but does not publish a country-by-country user availability list for the service.
- Country support status
- All-plan availability is an account-plan statement, not confirmation that every country, provider, or model is supported.
- Access limits
- Requests still depend on the selected upstream provider. Provider location rules, account eligibility, and model restrictions can apply separately.
- Regions and data location
- Cloudflare's global network and edge locations do not prove that an upstream model runs in the user's country or that the service is legally available there.
Check the gateway terms and the selected model provider before relying on access in a specific country. Network edge locations, billing currencies, and provider catalogs are not country-availability evidence.
Model catalog
77 models in this platform's catalog
| Model | Input / 1M | Output / 1M | Cached input | Context |
|---|---|---|---|---|
 indictrans2-en-indic-1Bai4bharatSource and checked dateChecked Official quote source | $0.342 | $0.342 | Not listed | Not listed |
gemma-sea-lion-v4-27b-itaisingaporeSource and checked dateChecked Official quote source | $0.351 | $0.555 | Not listed | 128K |
phonellm-mini-alpha-2daily-coSource and checked dateChecked Official quote source | $0.06 | $0.24 | Not listed | 262K |
deepseek-r1-distill-qwen-32bdeepseek-aiSource and checked dateChecked Official quote source | $0.497 | $4.881 | Not listed | 80K |
deepseek-v4-flash-0731deepseek-aiSource and checked dateChecked Official quote source | $0.44 | $1.32 | $0.014 | 1M |
deepseek-v4-pro-0813deepseek-aiSource and checked dateChecked Official quote source | $1.32 | $3.96 | $0.044 | 1M |
gemma-4-26b-a4b-itgoogleSource and checked dateChecked Official quote source | $0.1 | $0.3 | Not listed | 256K |
granite-4.0-h-microibm-graniteSource and checked dateChecked Official quote source | $0.017 | $0.112 | Not listed | 131K |
llama-3.1-8b-instruct-fp8metaSource and checked dateChecked Official quote source | $0.152 | $0.287 | Not listed | 32K |
llama-3.2-11b-vision-instructmetaSource and checked dateChecked Official quote source | $0.0485 | $0.676 | Not listed | 128K |
Model rates come from each model provider's official pricing page. The gateway's own billing rule is shown separately above. Token rates exclude taxes, payment charges, negotiated discounts, and separately published plans.