
Cloudflare Models
US connectivity cloud running Workers AI inference across its global network, including the Clef decision models. Prompts and outputs are Customer Content: Cloudflare does not use them to train models or improve its services, and does not store them unless a storage product is used alongside Workers AI. Requesty routes to 2 Cloudflare models starting at $0.09 per 1M input tokens with context windows up to 66K tokens. One API key and an OpenAI-compatible SDK. Provider rates plus 5% on pay as you go, or 0% with your own keys.
All Cloudflare models
| Model | Context | Max Output | Input/1M | Output/1M | Capabilities | Coding |
|---|---|---|---|---|---|---|
| 66K | β | $0.09 | Free | π | N/A | |
| 66K | β | $0.24 | Free | π | N/A |
About Cloudflare on Requesty
How many Cloudflare models are available through Requesty?
Requesty routes to 2 Cloudflare models including regional variants, with pricing synced in real time to the upstream provider.
What is the cheapest Cloudflare model?
The cheapest Cloudflare model starts at $0.09 per million input tokens. See the pricing column in the table below for full per-model rates.
Does Requesty add markup on Cloudflare pricing?
No. Requesty passes through exactly what Cloudflare charges. You pay the same per-token rates as going direct, plus you get smart routing, caching, analytics, and one unified API for 600+ models.
Is my data used to train Cloudflare models?
Cloudflare's terms state that API data is not used for training. See their privacy policy for the authoritative statement.
Where are Cloudflare models hosted?
Cloudflare models are hosted in πΊπΈ US, π Global network. Some models are available in additional regions through AWS Bedrock, Azure, or Google Vertex AI: filter by region on the Cloudflare rows in the models explorer.
