Cloudflare AI Jobs

Monitoring the performance and errors of various Cloudflare Models. The inputs are random to avoid caching but roughly the same and we limit text LLMs to 100 output tokens. More data to be exposed in the future (like TPS).

Overview
Popular Models 4
  • @cf/moonshotai/kimi-k2.6 ?
    2.12 second(s)?
    Last Update: 1.39 minute(s) ago
    1 Day
    2.18 second(s)
    30 Days
    2.71 second(s)
    90 Days
    2.83 second(s)
    24H Peak: 21.29 second(s)
    From 12:59:57 AM - 1:00:18 AM
  • @cf/moonshotai/kimi-k2.7-code ?
    1.64 second(s)?
    Last Update: 1.42 minute(s) ago
    1 Day
    2.00 second(s)
    30 Days
    2.85 second(s)
    90 Days
    2.88 second(s)
    24H Peak: 30.78 second(s)
    From 3:31:09 PM - 3:31:39 PM
  • @cf/zai-org/glm-4.7-flash ?
    1.17 second(s)?
    Last Update: 1.41 minute(s) ago
    1 Day
    1.42 second(s)
    30 Days
    1.80 second(s)
    90 Days
    1.37 second(s)
    24H Peak: 29.14 second(s)
    From 7:05:05 PM - 7:05:34 PM
  • @cf/zai-org/glm-5.2 ?
    1.86 second(s)?
    Last Update: 1.39 minute(s) ago
    1 Day
    2.56 second(s)
    30 Days
    3.83 second(s)
    90 Days
    3.75 second(s)
    24H Peak: 39.92 second(s)
    From 2:01:16 PM - 2:01:55 PM
Aisingapore 1
  • @cf/aisingapore/gemma-sea-lion-v4-27b-it ?
    2.14 second(s)?
    Last Update: 1.39 minute(s) ago
    1 Day
    1.99 second(s)
    30 Days
    2.01 second(s)
    90 Days
    1.94 second(s)
    24H Peak: 3.15 second(s)
    From 2:11:39 AM - 2:11:42 AM
BAAI 4
  • @cf/baai/bge-base-en-v1.5 ?
    0.15 second(s)?
    Last Update: 1.42 minute(s) ago
    1 Day
    0.14 second(s)
    30 Days
    0.14 second(s)
    90 Days
    0.12 second(s)
    24H Peak: 1.35 second(s)
    From 4:42:38 AM - 4:42:39 AM
  • @cf/baai/bge-large-en-v1.5 ?
    0.14 second(s)?
    Last Update: 1.40 minute(s) ago
    1 Day
    0.17 second(s)
    30 Days
    0.18 second(s)
    90 Days
    0.18 second(s)
    24H Peak: 2.36 second(s)
    From 2:19:39 AM - 2:19:41 AM
  • @cf/baai/bge-m3 ?
    0.34 second(s)?
    Last Update: 1.44 minute(s) ago
    1 Day
    0.26 second(s)
    30 Days
    0.26 second(s)
    90 Days
    0.19 second(s)
    24H Peak: 1.72 second(s)
    From 3:00:36 PM - 3:00:37 PM
  • @cf/baai/bge-small-en-v1.5 ?
    0.19 second(s)?
    Last Update: 1.42 minute(s) ago
    1 Day
    0.20 second(s)
    30 Days
    0.22 second(s)
    90 Days
    0.20 second(s)
    24H Peak: 1.37 second(s)
    From 4:39:37 AM - 4:39:38 AM
Black Forest Labs 1
  • @cf/black-forest-labs/flux-1-schnell ?
    1.47 second(s)?
    Last Update: 1.41 minute(s) ago
    1 Day
    1.48 second(s)
    30 Days
    1.42 second(s)
    90 Days
    1.42 second(s)
    24H Peak: 3.88 second(s)
    From 2:51:40 AM - 2:51:43 AM
Bytedance 1
  • @cf/bytedance/stable-diffusion-xl-lightning ?
    3.76 second(s)?
    Last Update: 1.36 minute(s) ago
    1 Day
    4.28 second(s)
    30 Days
    4.02 second(s)
    90 Days
    3.98 second(s)
    24H Peak: 14.98 second(s)
    From 7:31:59 PM - 7:32:13 PM
DeepSeek 1
Google 4
  • @cf/google/embeddinggemma-300m ?
    0.52 second(s)?
    Last Update: 1.40 minute(s) ago
    1 Day
    0.29 second(s)
    30 Days
    0.34 second(s)
    90 Days
    0.30 second(s)
    24H Peak: 0.91 second(s)
    From 2:26:38 PM - 2:26:38 PM
  • @cf/google/gemma-2b-it-lora ?
    2.52 second(s)?
    Last Update: 1.41 minute(s) ago
    1 Day
    2.49 second(s)
    30 Days
    2.50 second(s)
    90 Days
    2.54 second(s)
    24H Peak: 3.33 second(s)
    From 2:55:38 PM - 2:55:41 PM
  • @cf/google/gemma-4-26b-a4b-it ?
    1.94 second(s)?
    Last Update: 54.80 second(s) ago
    1 Day
    1.83 second(s)
    30 Days
    1.68 second(s)
    90 Days
    1.44 second(s)
    24H Peak: 35.00 second(s)
    From 2:17:11 PM - 2:17:46 PM
  • @cf/google/gemma-7b-it-lora ?
    7.83 second(s)?
    Last Update: 1.29 minute(s) ago
    1 Day
    7.87 second(s)
    30 Days
    7.91 second(s)
    90 Days
    7.84 second(s)
    24H Peak: 8.89 second(s)
    From 2:41:45 PM - 2:41:53 PM
Hugging Face 1
  • @cf/huggingface/distilbert-sst-2-int8 ?
    0.35 second(s)?
    Last Update: 1.44 minute(s) ago
    1 Day
    0.28 second(s)
    30 Days
    0.29 second(s)
    90 Days
    0.29 second(s)
    24H Peak: 1.10 second(s)
    From 1:05:35 AM - 1:05:36 AM
Ibm Granite 1
  • @cf/ibm-granite/granite-4.0-h-micro ?
    3.64 second(s)?
    Last Update: 1.36 minute(s) ago
    1 Day
    3.53 second(s)
    30 Days
    3.59 second(s)
    90 Days
    3.47 second(s)
    24H Peak: 5.26 second(s)
    From 3:55:40 PM - 3:55:45 PM
Llava Hf 1
  • @cf/llava-hf/llava-1.5-7b-hf ?
    5.98 second(s)?
    Last Update: 1.34 minute(s) ago
    1 Day
    5.68 second(s)
    30 Days
    5.75 second(s)
    90 Days
    5.73 second(s)
    24H Peak: 7.18 second(s)
    From 6:28:42 PM - 6:28:49 PM
Lykon 1
  • @cf/lykon/dreamshaper-8-lcm ?
    2.84 second(s)?
    Last Update: 1.34 minute(s) ago
    1 Day
    2.76 second(s)
    30 Days
    2.74 second(s)
    90 Days
    2.68 second(s)
    24H Peak: 5.08 second(s)
    From 12:17:45 PM - 12:17:50 PM
Meta 1
  • @cf/meta-llama/llama-2-7b-chat-hf-lora ?
    7.20 second(s)?
    Last Update: 1.31 minute(s) ago
    1 Day
    6.39 second(s)
    30 Days
    6.43 second(s)
    90 Days
    6.31 second(s)
    24H Peak: 10.95 second(s)
    From 5:14:46 PM - 5:14:56 PM
Meta 10
  • @cf/meta/llama-3.1-70b-instruct ?
    3.74 second(s)?
    Last Update: 1.34 minute(s) ago
    1 Day
    3.88 second(s)
    30 Days
    3.86 second(s)
    90 Days
    3.87 second(s)
    24H Peak: 7.64 second(s)
    From 2:23:45 AM - 2:23:52 AM
  • @cf/meta/llama-3.1-8b-instruct-fast ?
    0.68 second(s)?
    Last Update: 1.39 minute(s) ago
    1 Day
    0.77 second(s)
    30 Days
    0.80 second(s)
    90 Days
    0.77 second(s)
    24H Peak: 3.02 second(s)
    From 8:19:40 AM - 8:19:43 AM
  • @cf/meta/llama-3.1-8b-instruct-fp8 ?
    5.00 second(s)?
    Last Update: 1.34 minute(s) ago
    1 Day
    5.11 second(s)
    30 Days
    5.13 second(s)
    90 Days
    4.83 second(s)
    24H Peak: 13.81 second(s)
    From 12:38:52 AM - 12:39:05 AM
  • @cf/meta/llama-3.2-11b-vision-instruct ?
    1.91 second(s)?
    Last Update: 1.38 minute(s) ago
    1 Day
    2.12 second(s)
    30 Days
    2.17 second(s)
    90 Days
    2.07 second(s)
    24H Peak: 38.97 second(s)
    From 4:06:16 AM - 4:06:54 AM
  • @cf/meta/llama-3.2-1b-instruct ?
    0.90 second(s)?
    Last Update: 1.41 minute(s) ago
    1 Day
    0.98 second(s)
    30 Days
    0.98 second(s)
    90 Days
    0.92 second(s)
    24H Peak: 7.41 second(s)
    From 1:04:42 PM - 1:04:49 PM
  • @cf/meta/llama-3.2-3b-instruct ?
    0.78 second(s)?
    Last Update: 1.43 minute(s) ago
    1 Day
    0.87 second(s)
    30 Days
    0.84 second(s)
    90 Days
    0.89 second(s)
    24H Peak: 3.58 second(s)
    From 6:34:38 AM - 6:34:41 AM
  • @cf/meta/llama-3.3-70b-instruct-fp8-fast ?
    2.19 second(s)?
    Last Update: 1.39 minute(s) ago
    1 Day
    4.56 second(s)
    30 Days
    2.19 second(s)
    90 Days
    2.82 second(s)
    24H Peak: 16.94 second(s)
    From 5:35:01 AM - 5:35:17 AM
  • @cf/meta/llama-4-scout-17b-16e-instruct ?
    1.62 second(s)?
    Last Update: 1.39 minute(s) ago
    1 Day
    1.68 second(s)
    30 Days
    2.40 second(s)
    90 Days
    2.11 second(s)
    24H Peak: 36.43 second(s)
    From 9:04:17 AM - 9:04:53 AM
  • @cf/meta/llama-guard-3-8b ?
    0.51 second(s)?
    Last Update: 1.44 minute(s) ago
    1 Day
    0.39 second(s)
    30 Days
    0.40 second(s)
    90 Days
    0.34 second(s)
    24H Peak: 27.17 second(s)
    From 9:00:05 PM - 9:00:32 PM
  • @cf/meta/m2m100-1.2b ?
    1.19 second(s)?
    Last Update: 1.40 minute(s) ago
    1 Day
    1.37 second(s)
    30 Days
    1.49 second(s)
    90 Days
    1.44 second(s)
    24H Peak: 3.08 second(s)
    From 6:21:41 AM - 6:21:44 AM
Microsoft 1
  • @cf/microsoft/resnet-50 ?
    0.15 second(s)?
    Last Update: 1.42 minute(s) ago
    1 Day
    0.23 second(s)
    30 Days
    0.25 second(s)
    90 Days
    0.23 second(s)
    24H Peak: 1.11 second(s)
    From 9:49:38 PM - 9:49:39 PM
Mistral 1
  • @cf/mistral/mistral-7b-instruct-v0.2-lora ?
    6.58 second(s)?
    Last Update: 1.34 minute(s) ago
    1 Day
    6.65 second(s)
    30 Days
    6.64 second(s)
    90 Days
    6.70 second(s)
    24H Peak: 7.85 second(s)
    From 2:39:42 PM - 2:39:49 PM
Mistral 1
MyShell 1
  • @cf/myshell-ai/melotts ?
    1.52 second(s)?
    Last Update: 1.43 minute(s) ago
    1 Day
    1.54 second(s)
    30 Days
    1.48 second(s)
    90 Days
    1.36 second(s)
    24H Peak: 4.66 second(s)
    From 8:58:38 PM - 8:58:42 PM
NVIDIA 1
  • @cf/nvidia/nemotron-3-120b-a12b ?
    2.24 second(s)?
    Last Update: 1.38 minute(s) ago
    1 Day
    1.71 second(s)
    30 Days
    2.01 second(s)
    90 Days
    1.68 second(s)
    24H Peak: 24.67 second(s)
    From 7:11:00 PM - 7:11:24 PM
OpenAI 5
  • @cf/openai/gpt-oss-120b ?
    23.42 second(s)?
    Last Update: 52.01 second(s) ago
    1 Day
    22.04 second(s)
    30 Days
    20.40 second(s)
    90 Days
    20.80 second(s)
    24H Peak: 39.31 second(s)
    From 7:03:15 AM - 7:03:54 AM
  • @cf/openai/gpt-oss-20b ?
    4.79 second(s)?
    Last Update: 1.24 minute(s) ago
    1 Day
    6.69 second(s)
    30 Days
    6.92 second(s)
    90 Days
    6.47 second(s)
    24H Peak: 29.15 second(s)
    From 4:16:06 PM - 4:16:35 PM
  • @cf/openai/whisper ?
    0.95 second(s)?
    Last Update: 1.43 minute(s) ago
    1 Day
    0.95 second(s)
    30 Days
    0.82 second(s)
    90 Days
    0.80 second(s)
    24H Peak: 13.59 second(s)
    From 1:01:58 AM - 1:02:11 AM
  • @cf/openai/whisper-large-v3-turbo ?
    1.04 second(s)?
    Last Update: 1.40 minute(s) ago
    1 Day
    1.05 second(s)
    30 Days
    1.04 second(s)
    90 Days
    1.11 second(s)
    24H Peak: 4.59 second(s)
    From 9:18:42 AM - 9:18:46 AM
  • @cf/openai/whisper-tiny-en ?
    1.01 second(s)?
    Last Update: 1.40 minute(s) ago
    1 Day
    1.07 second(s)
    30 Days
    1.14 second(s)
    90 Days
    1.09 second(s)
    24H Peak: 2.02 second(s)
    From 7:44:38 AM - 7:44:40 AM
PFN 1
  • @cf/pfnet/plamo-embedding-1b ?
    0.42 second(s)?
    Last Update: 1.43 minute(s) ago
    1 Day
    0.34 second(s)
    30 Days
    0.34 second(s)
    90 Days
    0.37 second(s)
    24H Peak: 1.10 second(s)
    From 7:05:35 PM - 7:05:36 PM
Qwen 3
  • @cf/qwen/qwen2.5-coder-32b-instruct ?
    3.49 second(s)?
    Last Update: 1.36 minute(s) ago
    1 Day
    3.28 second(s)
    30 Days
    3.38 second(s)
    90 Days
    3.32 second(s)
    24H Peak: 4.87 second(s)
    From 1:47:41 PM - 1:47:45 PM
  • @cf/qwen/qwen3-embedding-0.6b ?
    0.49 second(s)?
    Last Update: 1.43 minute(s) ago
    1 Day
    1.00 second(s)
    30 Days
    0.91 second(s)
    90 Days
    0.53 second(s)
    24H Peak: 8.47 second(s)
    From 10:01:43 PM - 10:01:51 PM
  • @cf/qwen/qwq-32b ?
    3.26 second(s)?
    Last Update: 1.36 minute(s) ago
    1 Day
    3.29 second(s)
    30 Days
    3.28 second(s)
    90 Days
    3.28 second(s)
    24H Peak: 3.97 second(s)
    From 12:42:41 PM - 12:42:44 PM
Runwayml 2
Stabilityai 1
  • @cf/stabilityai/stable-diffusion-xl-base-1.0 ?
    9.64 second(s)?
    Last Update: 1.26 minute(s) ago
    1 Day
    10.11 second(s)
    30 Days
    10.06 second(s)
    90 Days
    10.05 second(s)
    24H Peak: 29.62 second(s)
    From 7:45:12 PM - 7:45:41 PM