AI Models

Latency, tail latency and errors for Workers AI models, measured from probe locations worldwide. Inputs are randomised to avoid caching but kept roughly the same size, and text LLMs are limited to 100 output tokens.

Overview

Models status now

62Healthy

0Elevated

0Erroring

Median latency (24h)

…

across all models · 100 output tokens for text models

——

p90 (24h)

…

1 in 10 slower than this

Least consistent (p99 ÷ median)

…

no model's p99 is 2× its median

Models with errors (24h)

…

at least one failed request

Biggest slowdown

…

nothing up 10%+ vs last 6 days

Most improved

…

nothing down 10%+ vs last 6 days

View:

Models (62)

Last 24h · 100 output tokens for text models · click a column to sort

					7 days
@cf/ai4bharat/indictrans2-en-indic-1B AI4Bharat	…	…	…	—	—	—	…
@cf/aisingapore/gemma-sea-lion-v4-27b-it AI Singapore	…	…	…	—	—	—	…
@cf/baai/bge-base-en-v1.5 BAAI	…	…	…	—	—	—	…
@cf/baai/bge-large-en-v1.5 BAAI	…	…	…	—	—	—	…
@cf/baai/bge-m3 BAAI	…	…	…	—	—	—	…
@cf/baai/bge-reranker-base BAAI	…	…	…	—	—	—	…
@cf/baai/bge-small-en-v1.5 BAAI	…	…	…	—	—	—	…
@cf/black-forest-labs/flux-1-schnell Black Forest Labs	…	…	…	—	—	—	…
@cf/bytedance/stable-diffusion-xl-lightning Bytedance	…	…	…	—	—	—	…
@cf/cloudflare/clairic Cloudflare	…	…	…	—	—	—	…
@cf/cloudflare/clef Cloudflare	…	…	…	—	—	—	…
@cf/cloudflare/clef-flash Cloudflare	…	…	…	—	—	—	…
@cf/cloudflare/clef-omni Cloudflare	…	…	…	—	—	—	…
@cf/daily-co/phonellm-mini-alpha-2 Daily	…	…	…	—	—	—	…
@cf/deepseek-ai/deepseek-r1-distill-qwen-32b DeepSeek	…	…	…	—	—	—	…
@cf/deepseek-ai/deepseek-v4-flash-0731 DeepSeek	…	…	…	—	—	—	…
@cf/deepseek-ai/deepseek-v4-pro-0813 DeepSeek	…	…	…	—	—	—	…
@cf/google/embeddinggemma-300m Google	…	…	…	—	—	—	…
@cf/google/gemma-2b-it-lora Google	…	…	…	—	—	—	…
@cf/google/gemma-4-26b-a4b-it Google	…	…	…	—	—	—	…
@cf/google/gemma-7b-it-lora Google	…	…	…	—	—	—	…
@cf/huggingface/distilbert-sst-2-int8 Hugging Face	…	…	…	—	—	—	…
@cf/ibm-granite/granite-4.0-h-micro IBM	…	…	…	—	—	—	…
@cf/llava-hf/llava-1.5-7b-hf LLaVA	…	…	…	—	—	—	…
@cf/lykon/dreamshaper-8-lcm Lykon	…	…	…	—	—	—	…
@cf/meta-llama/llama-2-7b-chat-hf-lora Meta	…	…	…	—	—	—	…
@cf/meta/llama-3.1-70b-instruct Meta	…	…	…	—	—	—	…
@cf/meta/llama-3.1-8b-instruct-fast Meta	…	…	…	—	—	—	…
@cf/meta/llama-3.1-8b-instruct-fp8 Meta	…	…	…	—	—	—	…
@cf/meta/llama-3.2-11b-vision-instruct Meta	…	…	…	—	—	—	…
@cf/meta/llama-3.2-1b-instruct Meta	…	…	…	—	—	—	…
@cf/meta/llama-3.2-3b-instruct Meta	…	…	…	—	—	—	…
@cf/meta/llama-3.3-70b-instruct-fp8-fast Meta	…	…	…	—	—	—	…
@cf/meta/llama-4-scout-17b-16e-instruct Meta	…	…	…	—	—	—	…
@cf/meta/llama-guard-3-8b Meta	…	…	…	—	—	—	…
@cf/meta/m2m100-1.2b Meta	…	…	…	—	—	—	…
@cf/microsoft/resnet-50 Microsoft	…	…	…	—	—	—	…
@cf/mistral/mistral-7b-instruct-v0.2-lora Mistral	…	…	…	—	—	—	…
@cf/mistralai/mistral-small-3.1-24b-instruct Mistral	…	…	…	—	—	—	…
@cf/moondream/moondream3.1-9B-A2B Moondream	…	…	…	—	—	—	…
@cf/moonshotai/kimi-k2.6 Popular Models	…	…	…	—	—	—	…
@cf/moonshotai/kimi-k2.7-code Popular Models	…	…	…	—	—	—	…
@cf/myshell-ai/melotts MyShell	…	…	…	—	—	—	…
@cf/nvidia/nemotron-3-120b-a12b NVIDIA	…	…	…	—	—	—	…
@cf/openai/gpt-oss-120b OpenAI	…	…	…	—	—	—	…
@cf/openai/gpt-oss-20b OpenAI	…	…	…	—	—	—	…
@cf/openai/whisper OpenAI	…	…	…	—	—	—	…
@cf/openai/whisper-large-v3-turbo OpenAI	…	…	…	—	—	—	…
@cf/openai/whisper-tiny-en OpenAI	…	…	…	—	—	—	…
@cf/pfnet/plamo-embedding-1b PFN	…	…	…	—	—	—	…
@cf/pipecat-ai/smart-turn-v2 Pipecat	…	…	…	—	—	—	…
@cf/qwen/qwen2.5-coder-32b-instruct Qwen	…	…	…	—	—	—	…
@cf/qwen/qwen3-30b-a3b-fp8 Qwen	…	…	…	—	—	—	…
@cf/qwen/qwen3-embedding-0.6b Qwen	…	…	…	—	—	—	…
@cf/qwen/qwen3.8-27b Qwen	…	…	…	—	—	—	…
@cf/qwen/qwq-32b Qwen	…	…	…	—	—	—	…
@cf/runwayml/stable-diffusion-v1-5-inpainting Runwayml	…	…	…	—	—	—	…
@cf/stabilityai/stable-diffusion-xl-base-1.0 Stabilityai	…	…	…	—	—	—	…
@cf/zai-org/glm-4.7-flash Popular Models	…	…	…	—	—	—	…
@cf/zai-org/glm-5.2 Popular Models	…	…	…	—	—	—	…
@cf/zai-org/glm-5.3 Popular Models	…	…	…	—	—	—	…
@cf/zai-org/glm-5.3-flash Popular Models	…	…	…	—	—	—	…

Popular Models6

@cf/moonshotai/kimi-k2.6?
9.94 s?
Last Update: 50.77 s ago
1 Day
4.12 s
30 Days
3.33 s
90 Days
2.91 s
24H Peak: 39.57 s
From 1:25:26 AM - 1:26:05 AM
@cf/moonshotai/kimi-k2.7-code?
3.50 s?
Last Update: 52.14 s ago
1 Day
3.02 s
30 Days
2.88 s
90 Days
2.51 s
24H Peak: 37.91 s
From 12:01:25 AM - 12:02:02 AM
@cf/zai-org/glm-4.7-flash?
2.37 s?
Last Update: 56.62 s ago
1 Day
2.51 s
30 Days
2.26 s
90 Days
2.19 s
24H Peak: 34.62 s
From 2:47:24 PM - 2:47:58 PM
@cf/zai-org/glm-5.2?
1.04 s?
Last Update: 55.63 s ago
1 Day
1.15 s
30 Days
2.17 s
90 Days
2.60 s
24H Peak: 12.01 s
From 9:30:02 AM - 9:30:14 AM
@cf/zai-org/glm-5.3?
3.41 s?
Last Update: 51.91 s ago
1 Day
3.46 s
30 Days
3.96 s
90 Days
3.40 s
24H Peak: 39.77 s
From 10:02:28 AM - 10:03:07 AM
@cf/zai-org/glm-5.3-flash?
2.35 s?
Last Update: 53.95 s ago
1 Day
3.24 s
30 Days
3.42 s
90 Days
3.06 s
24H Peak: 38.92 s
From 7:07:28 PM - 7:08:06 PM

AI Singapore1

@cf/aisingapore/gemma-sea-lion-v4-27b-it?
1.89 s?
Last Update: 1.06 min ago
1 Day
2.00 s
30 Days
2.07 s
90 Days
2.02 s
24H Peak: 6.09 s
From 10:08:48 AM - 10:08:54 AM

AI4Bharat1

@cf/ai4bharat/indictrans2-en-indic-1B?
1.61 s?
Last Update: 1.13 min ago

BAAI5

@cf/baai/bge-base-en-v1.5?
138 ms?
Last Update: 1.11 min ago
1 Day
164 ms
30 Days
232 ms
90 Days
176 ms
24H Peak: 634 ms
From 1:30:41 AM - 1:30:41 AM
@cf/baai/bge-large-en-v1.5?
236 ms?
Last Update: 1.10 min ago
1 Day
161 ms
30 Days
277 ms
90 Days
212 ms
24H Peak: 472 ms
From 11:37:41 PM - 11:37:41 PM
@cf/baai/bge-m3?
152 ms?
Last Update: 1.16 min ago
1 Day
137 ms
30 Days
258 ms
90 Days
223 ms
24H Peak: 1.13 s
From 1:40:40 PM - 1:40:41 PM
@cf/baai/bge-reranker-base?
423 ms?
Last Update: 1.16 min ago
1 Day
309 ms
30 Days
309 ms
90 Days
309 ms
24H Peak: 22.76 s
From 2:44:13 PM - 2:44:35 PM
@cf/baai/bge-small-en-v1.5?
147 ms?
Last Update: 1.10 min ago
1 Day
214 ms
30 Days
262 ms
90 Days
228 ms
24H Peak: 522 ms
From 9:10:42 PM - 9:10:42 PM

Black Forest Labs1

@cf/black-forest-labs/flux-1-schnell?
1.38 s?
Last Update: 1.09 min ago
1 Day
1.95 s
30 Days
2.00 s
90 Days
1.71 s
24H Peak: 15.84 s
From 6:01:20 AM - 6:01:35 AM

Bytedance1

@cf/bytedance/stable-diffusion-xl-lightning?
6.38 s?
Last Update: 1.03 min ago
1 Day
4.12 s
30 Days
4.12 s
90 Days
4.20 s
24H Peak: 11.05 s
From 12:33:55 PM - 12:34:06 PM

Cloudflare4

@cf/cloudflare/clairic?
202 ms?
Last Update: 1.21 min ago
1 Day
224 ms
30 Days
233 ms
90 Days
233 ms
24H Peak: 1.17 s
From 9:01:37 AM - 9:01:38 AM
@cf/cloudflare/clef?
258 ms?
Last Update: 1.22 min ago
1 Day
338 ms
30 Days
332 ms
90 Days
332 ms
24H Peak: 38.79 s
From 9:07:14 AM - 9:07:52 AM
@cf/cloudflare/clef-flash?
280 ms?
Last Update: 1.22 min ago
1 Day
304 ms
30 Days
310 ms
90 Days
310 ms
24H Peak: 2.20 s
From 5:09:38 PM - 5:09:40 PM
@cf/cloudflare/clef-omni?
167 ms?
Last Update: 1.22 min ago
1 Day
191 ms
30 Days
205 ms
90 Days
205 ms
24H Peak: 2.78 s
From 6:44:37 PM - 6:44:39 PM

Daily1

@cf/daily-co/phonellm-mini-alpha-2?
1.02 s?
Last Update: 1.05 min ago
1 Day
1.08 s
30 Days
908 ms
90 Days
908 ms
24H Peak: 5.42 s
From 1:12:51 AM - 1:12:56 AM

DeepSeek3

@cf/deepseek-ai/deepseek-r1-distill-qwen-32b?
3.76 s?
Last Update: 1.01 min ago
1 Day
2.98 s
30 Days
3.57 s
90 Days
3.39 s
24H Peak: 31.39 s
From 7:25:14 AM - 7:25:45 AM
@cf/deepseek-ai/deepseek-v4-flash-0731?
1.73 s?
Last Update: 1.04 min ago
1 Day
2.24 s
30 Days
2.22 s
90 Days
2.06 s
24H Peak: 38.16 s
From 7:31:22 AM - 7:32:00 AM
@cf/deepseek-ai/deepseek-v4-pro-0813?
2.43 s?
Last Update: 1.03 min ago
1 Day
2.93 s
30 Days
3.28 s
90 Days
3.35 s
24H Peak: 29.49 s
From 7:43:12 AM - 7:43:41 AM

Google4

@cf/google/embeddinggemma-300m?
246 ms?
Last Update: 1.09 min ago
1 Day
261 ms
30 Days
386 ms
90 Days
347 ms
24H Peak: 844 ms
From 10:55:42 PM - 10:55:42 PM
@cf/google/gemma-2b-it-lora?
2.54 s?
Last Update: 1.03 min ago
1 Day
2.45 s
30 Days
2.55 s
90 Days
2.53 s
24H Peak: 3.87 s
From 10:22:47 PM - 10:22:50 PM
@cf/google/gemma-4-26b-a4b-it?
2.43 s?
Last Update: 42.95 s ago
1 Day
2.35 s
30 Days
2.40 s
90 Days
1.85 s
24H Peak: 20.84 s
From 8:26:05 AM - 8:26:25 AM
@cf/google/gemma-7b-it-lora?
8.07 s?
Last Update: 55.49 s ago
1 Day
7.97 s
30 Days
8.08 s
90 Days
7.99 s
24H Peak: 9.51 s
From 6:36:53 PM - 6:37:02 PM

Hugging Face1

@cf/huggingface/distilbert-sst-2-int8?
199 ms?
Last Update: 1.17 min ago
1 Day
273 ms
30 Days
354 ms
90 Days
312 ms
24H Peak: 820 ms
From 5:05:38 PM - 5:05:38 PM

IBM1

@cf/ibm-granite/granite-4.0-h-micro?
3.07 s?
Last Update: 59.75 s ago
1 Day
3.03 s
30 Days
3.09 s
90 Days
3.13 s
24H Peak: 4.67 s
From 7:39:51 AM - 7:39:55 AM

LLaVA1

@cf/llava-hf/llava-1.5-7b-hf?
12.10 s?
Last Update: 53.55 s ago
1 Day
7.34 s
30 Days
7.33 s
90 Days
6.02 s
24H Peak: 37.28 s
From 1:26:17 PM - 1:26:54 PM

Lykon1

@cf/lykon/dreamshaper-8-lcm?
3.69 s?
Last Update: 1.09 min ago
1 Day
3.58 s
30 Days
3.25 s
90 Days
2.98 s
24H Peak: 12.05 s
From 3:41:55 AM - 3:42:07 AM

Meta10

@cf/meta/llama-3.1-70b-instruct?
3.87 s?
Last Update: 58.68 s ago
1 Day
4.04 s
30 Days
4.05 s
90 Days
3.96 s
24H Peak: 12.22 s
From 6:20:56 AM - 6:21:08 AM
@cf/meta/llama-3.1-8b-instruct-fast?
1.13 s?
Last Update: 1.03 min ago
1 Day
937 ms
30 Days
951 ms
90 Days
881 ms
24H Peak: 2.27 s
From 2:32:47 PM - 2:32:49 PM
@cf/meta/llama-3.1-8b-instruct-fp8?
7.01 s?
Last Update: 55.50 s ago
1 Day
5.61 s
30 Days
5.67 s
90 Days
5.43 s
24H Peak: 22.71 s
From 3:52:08 PM - 3:52:30 PM
@cf/meta/llama-3.2-11b-vision-instruct?
2.42 s?
Last Update: 1.19 min ago
1 Day
2.67 s
30 Days
2.56 s
90 Days
2.31 s
24H Peak: 13.85 s
From 12:01:47 AM - 12:02:00 AM
@cf/meta/llama-3.2-1b-instruct?
1.10 s?
Last Update: 1.02 min ago
1 Day
1.02 s
30 Days
1.07 s
90 Days
1.04 s
24H Peak: 4.43 s
From 1:12:50 PM - 1:12:54 PM
@cf/meta/llama-3.2-3b-instruct?
609 ms?
Last Update: 1.02 min ago
1 Day
713 ms
30 Days
773 ms
90 Days
785 ms
24H Peak: 1.59 s
From 12:15:47 AM - 12:15:48 AM
@cf/meta/llama-3.3-70b-instruct-fp8-fast?
2.07 s?
Last Update: 59.71 s ago
1 Day
2.11 s
30 Days
2.25 s
90 Days
2.12 s
24H Peak: 10.96 s
From 1:18:59 PM - 1:19:09 PM
@cf/meta/llama-4-scout-17b-16e-instruct?
3.38 s?
Last Update: 58.17 s ago
1 Day
3.08 s
30 Days
2.81 s
90 Days
2.21 s
24H Peak: 33.04 s
From 1:20:21 AM - 1:20:54 AM
@cf/meta/llama-guard-3-8b?
530 ms?
Last Update: 1.23 min ago
1 Day
553 ms
30 Days
527 ms
90 Days
454 ms
24H Peak: 25.99 s
From 6:02:09 PM - 6:02:34 PM
@cf/meta/m2m100-1.2b?
1.09 s?
Last Update: 1.13 min ago
1 Day
1.39 s
30 Days
1.54 s
90 Days
1.60 s
24H Peak: 5.33 s
From 12:31:43 AM - 12:31:48 AM

Meta1

@cf/meta-llama/llama-2-7b-chat-hf-lora?
6.11 s?
Last Update: 57.04 s ago
1 Day
6.51 s
30 Days
6.48 s
90 Days
6.41 s
24H Peak: 9.89 s
From 5:01:55 PM - 5:02:04 PM

Microsoft1

@cf/microsoft/resnet-50?
316 ms?
Last Update: 1.19 min ago
1 Day
256 ms
30 Days
198 ms
90 Days
265 ms
24H Peak: 686 ms
From 3:41:37 PM - 3:41:37 PM

Mistral1

@cf/mistral/mistral-7b-instruct-v0.2-lora?
5.82 s?
Last Update: 55.44 s ago
1 Day
5.96 s
30 Days
6.14 s
90 Days
6.34 s
24H Peak: 7.44 s
From 6:57:53 PM - 6:58:00 PM

Mistral1

@cf/mistralai/mistral-small-3.1-24b-instruct?
2.16 s?
Last Update: 54.10 s ago
1 Day
2.52 s
30 Days
2.87 s
90 Days
2.79 s
24H Peak: 7.48 s
From 3:39:54 PM - 3:40:01 PM

Moondream1

@cf/moondream/moondream3.1-9B-A2B?
2.24 s?
Last Update: 1.13 min ago

MyShell1

@cf/myshell-ai/melotts?
1.50 s?
Last Update: 1.10 min ago
1 Day
1.44 s
30 Days
1.52 s
90 Days
1.50 s
24H Peak: 4.06 s
From 12:35:39 PM - 12:35:43 PM

NVIDIA1

@cf/nvidia/nemotron-3-120b-a12b?
1.49 s?
Last Update: 58.42 s ago
1 Day
1.69 s
30 Days
1.55 s
90 Days
1.60 s
24H Peak: 22.91 s
From 12:40:10 AM - 12:40:32 AM

OpenAI5

@cf/openai/gpt-oss-120b?
1.86 s?
Last Update: 1.20 min ago
1 Day
1.75 s
30 Days
26.55 s
90 Days
26.11 s
24H Peak: 20.07 s
From 12:10:13 AM - 12:10:33 AM
@cf/openai/gpt-oss-20b?
1.22 s?
Last Update: 44.31 s ago
1 Day
1.24 s
30 Days
7.60 s
90 Days
7.55 s
24H Peak: 33.67 s
From 12:37:10 AM - 12:37:43 AM
@cf/openai/whisper?
1.19 s?
Last Update: 1.04 min ago
1 Day
1.18 s
30 Days
1.11 s
90 Days
992 ms
24H Peak: 29.31 s
From 12:25:20 AM - 12:25:49 AM
@cf/openai/whisper-large-v3-turbo?
1.34 s?
Last Update: 1.18 min ago
1 Day
1.84 s
30 Days
1.94 s
90 Days
1.61 s
24H Peak: 7.79 s
From 11:35:43 AM - 11:35:50 AM
@cf/openai/whisper-tiny-en?
1.03 s?
Last Update: 1.09 min ago
1 Day
1.19 s
30 Days
1.22 s
90 Days
1.17 s
24H Peak: 3.34 s
From 4:17:44 PM - 4:17:47 PM

PFN1

@cf/pfnet/plamo-embedding-1b?
414 ms?
Last Update: 1.08 min ago
1 Day
352 ms
30 Days
456 ms
90 Days
449 ms
24H Peak: 5.37 s
From 1:09:50 AM - 1:09:55 AM

Pipecat1

@cf/pipecat-ai/smart-turn-v2?
241 ms?
Last Update: 1.19 min ago
1 Day
454 ms
30 Days
451 ms
90 Days
451 ms
24H Peak: 1.22 s
From 9:41:37 AM - 9:41:38 AM

Qwen5

@cf/qwen/qwen2.5-coder-32b-instruct?
3.27 s?
Last Update: 56.18 s ago
1 Day
3.34 s
30 Days
3.42 s
90 Days
3.38 s
24H Peak: 9.69 s
From 8:50:58 AM - 8:51:07 AM
@cf/qwen/qwen3-30b-a3b-fp8?
1.17 s?
Last Update: 58.38 s ago
1 Day
1.14 s
30 Days
1.01 s
90 Days
1.01 s
24H Peak: 2.85 s
From 1:00:51 PM - 1:00:53 PM
@cf/qwen/qwen3-embedding-0.6b?
1.34 s?
Last Update: 59.37 s ago
1 Day
645 ms
30 Days
1.06 s
90 Days
1.39 s
24H Peak: 13.20 s
From 7:09:04 AM - 7:09:17 AM
@cf/qwen/qwen3.8-27b?
2.99 s?
Last Update: 46.22 s ago
1 Day
2.49 s
30 Days
2.79 s
90 Days
2.73 s
24H Peak: 39.18 s
From 6:04:27 AM - 6:05:06 AM
@cf/qwen/qwq-32b?
3.31 s?
Last Update: 55.96 s ago
1 Day
3.32 s
30 Days
3.38 s
90 Days
3.31 s
24H Peak: 7.58 s
From 1:13:00 AM - 1:13:07 AM

Runwayml1

@cf/runwayml/stable-diffusion-v1-5-inpainting?
4.31 s?
Last Update: 59.77 s ago
1 Day
3.71 s
30 Days
6.58 s
90 Days
4.61 s
24H Peak: 12.55 s
From 8:12:01 AM - 8:12:13 AM

Stabilityai1

@cf/stabilityai/stable-diffusion-xl-base-1.0?
11.94 s?
Last Update: 28.68 s ago
1 Day
14.04 s
30 Days
12.31 s
90 Days
10.32 s
24H Peak: 39.50 s
From 4:48:19 PM - 4:48:58 PM