Skip to content
ModelCap

Inference provider

Cloudflare: AI models and API pricing

Every tracked model Cloudflare serves through OpenRouter, with Cloudflare's own input and output price per 1M tokens, the context window it serves, disclosed quantization and measured endpoint uptime. Rows link to the model page, where every provider's deployment is listed side by side.

Snapshot as of 11 August 2026

Cloudflare serves 12 tracked models through 13 endpoints as of 11 August 2026; the highest-ranked is GLM 5.2 (ModelCap Index #13); mean measured uptime is 99.13%.

Models served
12
On the ModelCap Index
10
Cheapest output price
$0.112/1M

Language models on Cloudflare (12)

Ranked models first, in ModelCap Index order. Prices are the lowest Cloudflare lists for the model; the endpoint count shows how many deployments carry it.

Language models served by Cloudflare, with price, context, quantization and uptime
#ModelModelCap IndexInput $/1MOutput $/1MContextQuantizationUptime (30 min)Endpoints
1GLM 5.2Z.ai#1370.5$1.40$4.40262K——2Open weights
2Gemma 4 26B A4BGoogle#2559.2$0.10$0.30256K—97.61%1Open weights
3GLM 4.7 FlashZ.ai#6236.2$0.061$0.40131K—99.81%1Open weights
4Granite 4.0 MicroIBM Granite#12525.5$0.017$0.112131K—100.0%1Open weights
5Kimi K2.7 CodeMoonshot AI#18921.5$0.95$4.00262K—100.0%1
6Llama 3.3 70B InstructMeta#19320.3$0.293$2.2524Kfp895.29%1
7Qwen2.5 Coder 32B InstructQwen#20511.5$0.66$1.0033K——1Open weights
8Llama 3.1 8B InstructMeta#2193.7$0.152$0.28732Kfp899.70%1
9Llama 3.2 3B InstructMeta#2260.0$0.051$0.33580K—98.90%1
10Llama 3.2 1B InstructMeta#2270.0$0.027$0.20160K—100.0%1
11Kimi K2.6Moonshot AI—$0.95$4.00262K—100.0%1
12Mistral Small 3.1 24BMistral AI—$0.351$0.555128K—100.0%1Open weights

Cloudflare on ModelCap: common questions

How many AI models does Cloudflare serve?

12 tracked models as of 11 August 2026: 12 language models (10 with a public ModelCap Index position), across 13 live endpoints observed through OpenRouter.

What is the best model available on Cloudflare?

GLM 5.2 from Z.ai is the highest-ranked language model Cloudflare serves, at ModelCap Index position #13 and $4.40 per 1M output tokens on Cloudflare. The table lists every model in Index order.

What is the cheapest model on Cloudflare?

Granite 4.0 Micro at $0.112 per 1M output tokens ($0.017 per 1M input), the lowest positive language-token price Cloudflare lists. Free-tier endpoints, where present, show as $0 and are excluded from that comparison.

Which Cloudflare model has the largest context window?

GLM 5.2, served with a 262K-token context window on Cloudflare. Providers sometimes serve less than the model's published maximum, so the figure here is the provider's own.

How reliable is Cloudflare?

Mean measured uptime across Cloudflare endpoints is 99.13% over the last 30 minutes, as reported by OpenRouter at the time of the snapshot. Per-model uptime is in the table; it is a live operational signal, not a service-level guarantee.

Where do the Cloudflare prices come from?

From the OpenRouter catalogue entry for each Cloudflare endpoint, in USD per 1M tokens, re-observed on every ModelCap refresh. Where Cloudflare exposes several deployments of one model at different prices, the table shows the lowest and notes the count; the model page lists each deployment.

How current is this page?

It re-renders within a minute of every dataset refresh; this snapshot was published 11 August 2026. Offers retained from a failed refresh are marked stale in the data and are not counted here.

Explore further