The Known Good Updated 4 Sep 2026 Subscribe
Providers· Inference host· 19 tracked models

Cloudflare — pricing & performance

Compare models All providers Data sources
Models served
19
of 1,094 tracked models
Mean output speed
40
tokens per second, averaged over
19 measured endpoints
Mean latency
2.6s
time to first token, averaged over
19 measured endpoints
Cheapest blended
$0.041
per 1M tokens at a 3:1
input:output blend
Output speed on Cloudflare

Output tokens per second for all 19 models on Cloudflare with published throughput telemetry, the most recent figure OpenRouter publishes for each host. Higher is better. We do not run these measurements ourselves.

⇩
74
70
65
64
61
58
42
39
35
34
33
33
The Known Good
19 models on Cloudflare
Full leaderboard →
Model Creator Input $/M Output $/M Blended Speed TTFT Context
DeepSeek: DeepSeek V4 Flash 0423 DeepSeek $0.44 $1.32 $0.66 65 0.9s 384k
DeepSeek: DeepSeek V4 Flash 0731 DeepSeek $0.44 $1.32 $0.66 61 1.1s 1.31M
DeepSeek: DeepSeek V4 Pro 0423 DeepSeek $1.15 $2.55 $1.50 12 33.0s 1.05M
DeepSeek: DeepSeek V4 Pro 0813 DeepSeek $1.32 $3.96 $1.98 58 1.6s 1.05M
Google: Gemma 4 26B A4B Google $0.10 $0.30 $0.15 42 0.7s 256k
IBM: Granite 4.0 Micro IBM $0.017 $0.11 $0.041 35 0.8s 131k
Meta: Llama 3.1 8B Instruct Meta $0.15 $0.29 $0.19 19 0.6s 32k
Meta: Llama 3.2 1B Instruct Meta $0.027 $0.20 $0.070 70 0.2s 60k
Meta: Llama 3.2 3B Instruct Meta $0.051 $0.34 $0.12 74 0.2s 80k
Meta: Llama 3.3 70B Instruct Meta $0.29 $2.25 $0.78 14 0.3s 24k
Mistral: Mistral Small 3.1 24B Mistral $0.35 $0.56 $0.40 33 0.4s 128k
MoonshotAI: Kimi K2.6 Moonshot AI $0.95 $4.00 $1.71 39 1.0s 262k
MoonshotAI: Kimi K2.7 Code Moonshot AI $0.95 $4.00 $1.71 33 2.1s 262k
Qwen2.5 Coder 32B Instruct Alibaba $0.66 $1.00 $0.74 24 0.3s 33k
Qwen: Qwen3.8 27B Alibaba $0.45 $3.20 $1.14 29 0.8s 262k
Z.ai: GLM 4.7 Flash Z.ai $0.060 $0.40 $0.15 34 0.3s 131k
Z.ai: GLM 5.2 Z.ai $1.40 $4.40 $2.15 64 1.9s 262k
Z.ai: GLM 5.3 Z.ai $1.40 $4.40 $2.15 30 2.0s 1.31M
Z.ai: GLM 5.3 Flash Z.ai $0.15 $0.50 $0.24 31 1.8s 1.31M
The Known Good
Source. Prices, endpoint availability and throughput for Cloudflare are ingested from OpenRouter; model metadata is enriched from models.dev. A blank cell means the figure was not published for that endpoint — it never means zero. Blended price is (3 × input + output) ÷ 4, the same 3:1 blend used everywhere on this site; see methodology. Quality scores are not provider-specific: a model scores the same wherever it is hosted, so quality lives on the model pages.