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 2 October 2026

Cloudflare serves 18 tracked models through 18 endpoints as of 2 October 2026; the highest-ranked is GLM 5.3 (ModelCap Index #11); mean measured uptime is 98.95%.

Models served
18
On the ModelCap Index
11
Cheapest output price
$0.112/1M

Language models on Cloudflare (18)

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 5.3Z.ai#1180.9$1.40$4.401M——1
2GLM 5.3 FlashZ.ai#1778.9$0.30$1.001M—98.18%1Open weights
3DeepSeek V4 Pro 0813DeepSeek#2476.4$1.32$3.961M—98.92%1Open weights
4Qwen3.8 27BQwen#3968.9$0.45$3.20262K——1Open weights
5Gemma 4 26B A4BGoogle#4168.4$0.10$0.30256K—100.0%1Open weights
6Kimi K2.7 CodeMoonshot AI#4965.9$0.95$4.00262K——1
7Llama 3.3 70B InstructMeta#17832.4$0.293$2.2524Kfp898.78%1
8Qwen2.5 Coder 32B InstructQwen#21023.6$0.66$1.0033K—100.0%1Open weights
9Llama 3.1 8B InstructMeta#23313.5$0.152$0.28732Kfp8100.0%1
10Llama 3.2 3B InstructMeta#2628.4$0.051$0.33580K—99.22%1
11Llama 3.2 1B InstructMeta#2754.9$0.027$0.20160K—100.0%1
12Granite 4.0 MicroIBM Granite—$0.017$0.112131K—100.0%1Open weights
13DeepSeek V4 Flash 0731DeepSeek—$0.44$1.321M—100.0%1Open weights
14DeepSeek V4 Pro 0423DeepSeek—$1.15$2.551M—94.48%1Open weights
15GLM 4.7 FlashZ.ai—$0.061$0.40131K—99.37%1Open weights
16GLM 5.2Z.ai—$1.18$4.40262K——1Open weights
17Kimi K2.6Moonshot AI—$0.95$4.00262K—99.14%1
18Mistral Small 3.1 24BMistral AI—$0.351$0.555128K—97.25%1Open weights

Cloudflare on ModelCap: common questions

How many AI models does Cloudflare serve?

18 tracked models as of 2 October 2026: 18 language models (11 with a public ModelCap Index position), across 18 live endpoints observed through OpenRouter.

What is the best model available on Cloudflare?

GLM 5.3 from Z.ai is the highest-ranked language model Cloudflare serves, at ModelCap Index position #11 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 5.3, served with a 1M-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 98.95% 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?

This page uses the published ModelCap snapshot dated 2 October 2026. Publication and page updates happen separately. Offers retained from a failed refresh are marked stale in the data and are not counted here.

Explore further