Skip to content
SF·SIX
SF·SIX / PROVIDER PRICING

Cloudflare API pricing

Live prices for every model Cloudflare serves: its own per-1M-token prices, or per image, second or character, next to the cheapest price elsewhere.

By the SF·SIX research desk, ColdAI · Updated · Prices checked · Sources: OpenRouter · Methodology

Cloudflare serves 19 models with live API prices on SF·SIX, 19 models priced per 1M tokens. The cheapest is Granite 4.0 Micro at $0.017 per 1M input and $0.112 per 1M output tokens. The most used on OpenRouter is DeepSeek V4.1 Flash (5.41T tokens on 2026-10-16).

Models with live prices
19
Cheapest language model
Granite 4.0 Micro$0.017 / $0.112 per 1M tokens
Most used on OpenRouter (2026-10-16)
DeepSeek V4.1 Flash5.41T tokens
Newest model
DeepSeek V4.1 Flash2026-09-10
Cheapest standard host for
4 models of 19

Cloudflare token prices (USD per 1M tokens)

Cloudflare token prices (USD per 1M tokens)
ModelInput / 1MOutput / 1MTermsCheapest standard price anywhereContext (tokens)OpenRouter tokens / day
GLM 5.3$1.40$4.40Standard$0.50 / $1.51Sail Research (fp8)1,048,576942.62B
DeepSeek V4.1 Flash$0.10$0.90Standard$0.09 / $0.18Decart (fp4)1,048,5765.41T
GLM 5.2$0.19$8.00Standard$0.189 / $0.594Baidu (fp8)1,048,576140.87B
DeepSeek V4 Flash 0731$0.44$1.32Standard$0.0598 / $0.1795Baidu (fp8)1,048,576620.6B
DeepSeek V4 Pro 0813$1.32$3.96Standard$0.1333 / $0.40Baidu (fp8)1,048,576161.08B
Qwen3.8 27B$0.45$3.20Standard$0.02 / $0.50Tenstorrent (fp4)1,000,00062.19B
Kimi K2.6$0.95$4.00Standard$0.4323 / $1.82Baidu (fp4)262,144Not in named rows
DeepSeek V4 Pro 0423$1.15$2.55Standard$0.1775 / $0.3549Baidu (fp8)1,048,57685.51B
DeepSeek V4 Flash 0423$0.44$1.32Standard$0.0181 / $0.0361Baidu (fp8)1,048,576423.23B
Kimi K2.7 Code$0.95$4.00Standard$0.7125 / $3.00StreamLake262,144Not in named rows
Gemma 4 26B A4B$0.10$0.30Standard$0.042 / $0.22Darkbloom262,144Not in named rows
Llama 3.3 70B Instruct$0.293$2.25Standard · fp8$0.135 / $0.40Novita AI (bf16)131,072Not in named rows
Llama 3.1 8B Instruct$0.152$0.287Standard · fp8$0.02 / $0.04DeepInfra (fp8)131,072Not in named rows
GLM 4.7 Flash$0.0605$0.40Standard$0.06 / $0.40Venice AI (fp8)200,000Not in named rows
Llama 3.2 3B Instruct$0.0509$0.335Standard$0.05 / $0.33Parasail (bf16)131,072Not in named rows
Granite 4.0 Micro$0.017$0.112StandardCloudflarecheapest standard host131,000Not in named rows
Mistral Small 3.1 24B$0.351$0.555StandardCloudflarecheapest standard host128,000Not in named rows
Qwen2.5 Coder 32B Instruct$0.66$1.00StandardCloudflarecheapest standard host32,768Not in named rows
Llama 3.2 1B Instruct$0.027$0.201StandardCloudflarecheapest standard host60,000Not in named rows

Cloudflare’s own endpoint for each model (standard tier and default region first), next to the cheapest standard price from any provider. Most widely served first.

Method

Prices are USD per 1M tokens at the standard service tier in the default region: the cheapest qualifying provider per model, with flex, batch, priority and fast endpoints and unusually low outliers never used as the headline. “Blended” weights input and output 3:1. Missing prices are unknown, not free. OpenRouter tokens per day are the latest full UTC day of OpenRouter’s public rankings (named rows only). Prices move: see AI API price changes for recent cuts and increases.

More on Cloudflare

Related pages