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
  • @cf/meta/llama-3.2-3b-instruct
    1.31 second(s)
    Last Update: 3.11 minute(s) ago
    Last 24H Peak:
    3.87 second(s)
    From 8:58:53 PM - 8:58:56 PM
    90 Days Median: 1.20 second(s)
  • @cf/meta/llama-3.3-70b-instruct-fp8-fast
    2.96 second(s)
    Last Update: 3.05 minute(s) ago
    Last 24H Peak:
    4.36 second(s)
    From 11:23:45 AM - 11:23:49 AM
    90 Days Median: 3.32 second(s)
  • @cf/meta/llama-4-scout-17b-16e-instruct
    1.68 second(s)
    Last Update: 3.07 minute(s) ago
    Last 24H Peak:
    25.34 second(s)
    From 5:45:08 AM - 5:45:33 AM
    90 Days Median: 2.00 second(s)
  • @cf/google/embeddinggemma-300m
    0.32 second(s)
    Last Update: 3.08 minute(s) ago
    Last 24H Peak:
    2.57 second(s)
    From 5:00:51 PM - 5:00:53 PM
    90 Days Median: 0.42 second(s)
  • @cf/meta/llama-3.2-1b-instruct
    0.81 second(s)
    Last Update: 3.10 minute(s) ago
    Last 24H Peak:
    2.04 second(s)
    From 3:35:33 PM - 3:35:35 PM
    90 Days Median: 0.95 second(s)
  • @cf/baai/omni-bge-m3
    0.39 second(s)
    Last Update: 3.12 minute(s) ago
    Last 24H Peak:
    0.78 second(s)
    From 1:26:36 PM - 1:26:36 PM
    90 Days Median: 0.43 second(s)
  • @cf/meta/llama-guard-3-8b
    0.56 second(s)
    Last Update: 3.12 minute(s) ago
    Last 24H Peak:
    9.06 second(s)
    From 12:51:57 AM - 12:52:06 AM
    90 Days Median: 0.55 second(s)
  • @hf/mistral/mistral-7b-instruct-v0.2
    7.46 second(s)
    Last Update: 3.00 minute(s) ago
    Last 24H Peak:
    8.34 second(s)
    From 5:00:47 PM - 5:00:55 PM
    90 Days Median: 6.96 second(s)
  • @cf/baai/omni-bge-base-en-v1.5
    0.44 second(s)
    Last Update: 346.12 hour(s) ago
    90 Days Median: 0.35 second(s)
  • @cf/deepgram/nova-3
    0.00 second(s)
    Last Update: 235.87 hour(s) ago
    90 Days Median:
  • @cf/baai/bge-m3
    0.36 second(s)
    Last Update: 3.12 minute(s) ago
    Last 24H Peak:
    0.69 second(s)
    From 3:21:41 PM - 3:21:41 PM
    90 Days Median: 0.34 second(s)
  • @cf/black-forest-labs/flux-1-schnell
    1.56 second(s)
    Last Update: 3.08 minute(s) ago
    Last 24H Peak:
    5.40 second(s)
    From 8:09:31 AM - 8:09:36 AM
    90 Days Median: 2.27 second(s)
  • @cf/bytedance/stable-diffusion-xl-lightning
    3.75 second(s)
    Last Update: 3.04 minute(s) ago
    Last 24H Peak:
    6.70 second(s)
    From 11:12:25 PM - 11:12:31 PM
    90 Days Median: 4.00 second(s)
  • @cf/deepseek-ai/deepseek-math-7b-instruct
    6.43 second(s)
    Last Update: 3.00 minute(s) ago
    Last 24H Peak:
    7.80 second(s)
    From 2:08:04 PM - 2:08:11 PM
    90 Days Median: 6.38 second(s)
  • @cf/defog/sqlcoder-7b-2
    6.19 second(s)
    Last Update: 2.99 minute(s) ago
    Last 24H Peak:
    7.23 second(s)
    From 7:53:39 PM - 7:53:46 PM
    90 Days Median: 6.31 second(s)
  • @cf/facebook/bart-large-cnn
    0.89 second(s)
    Last Update: 3.08 minute(s) ago
    Last 24H Peak:
    1.57 second(s)
    From 6:10:12 PM - 6:10:13 PM
    90 Days Median: 0.72 second(s)
  • @cf/fblgit/una-cybertron-7b-v2-bf16
    4.11 second(s)
    Last Update: 3.06 minute(s) ago
    Last 24H Peak:
    5.78 second(s)
    From 10:55:44 AM - 10:55:49 AM
    90 Days Median: 4.20 second(s)
  • @cf/meta/llama-3.1-70b-instruct
    3.77 second(s)
    Last Update: 3.02 minute(s) ago
    Last 24H Peak:
    19.50 second(s)
    From 5:10:11 PM - 5:10:30 PM
    90 Days Median: 3.86 second(s)
  • @cf/meta/llama-3.1-8b-instruct-awq
    2.83 second(s)
    Last Update: 3.06 minute(s) ago
    Last 24H Peak:
    4.20 second(s)
    From 6:13:07 PM - 6:13:11 PM
    90 Days Median: 2.95 second(s)
  • @cf/meta/llama-3.1-8b-instruct-fast
    1.08 second(s)
    Last Update: 3.07 minute(s) ago
    Last 24H Peak:
    1.70 second(s)
    From 7:00:00 PM - 7:00:01 PM
    90 Days Median: 1.12 second(s)
  • @cf/meta/llama-3.1-8b-instruct-fp8
    4.68 second(s)
    Last Update: 3.03 minute(s) ago
    Last 24H Peak:
    7.80 second(s)
    From 8:35:44 PM - 8:35:51 PM
    90 Days Median: 4.58 second(s)
  • @cf/meta/llama-3.2-11b-vision-instruct
    4.01 second(s)
    Last Update: 3.03 minute(s) ago
    Last 24H Peak:
    6.76 second(s)
    From 5:23:57 PM - 5:24:03 PM
    90 Days Median: 2.68 second(s)
  • @cf/openchat/openchat-3.5-0106
    6.61 second(s)
    Last Update: 2.98 minute(s) ago
    Last 24H Peak:
    8.31 second(s)
    From 4:37:00 PM - 4:37:08 PM
    90 Days Median: 6.83 second(s)
  • @cf/qwen/qwen1.5-0.5b-chat
    1.42 second(s)
    Last Update: 3.11 minute(s) ago
    Last 24H Peak:
    2.86 second(s)
    From 8:22:05 AM - 8:22:07 AM
    90 Days Median: 1.43 second(s)
  • @cf/qwen/qwen1.5-1.8b-chat
    2.23 second(s)
    Last Update: 3.06 minute(s) ago
    Last 24H Peak:
    3.23 second(s)
    From 2:09:23 PM - 2:09:26 PM
    90 Days Median: 2.17 second(s)
  • @cf/qwen/qwen1.5-14b-chat-awq
    5.04 second(s)
    Last Update: 3.01 minute(s) ago
    Last 24H Peak:
    20.09 second(s)
    From 11:33:49 PM - 11:34:09 PM
    90 Days Median: 5.13 second(s)
  • @cf/qwen/qwen1.5-7b-chat-awq
    3.15 second(s)
    Last Update: 3.06 minute(s) ago
    Last 24H Peak:
    4.89 second(s)
    From 8:45:47 AM - 8:45:51 AM
    90 Days Median: 3.14 second(s)
  • @cf/qwen/qwen2.5-coder-32b-instruct
    3.26 second(s)
    Last Update: 3.05 minute(s) ago
    Last 24H Peak:
    5.98 second(s)
    From 4:37:24 AM - 4:37:29 AM
    90 Days Median: 3.35 second(s)
  • @cf/qwen/qwq-32b
    3.68 second(s)
    Last Update: 3.03 minute(s) ago
    Last 24H Peak:
    11.96 second(s)
    From 12:34:30 AM - 12:34:41 AM
    90 Days Median: 3.47 second(s)
  • @cf/runwayml/stable-diffusion-v1-5-img2img
    3.73 second(s)
    Last Update: 2.99 minute(s) ago
    Last 24H Peak:
    5.45 second(s)
    From 3:07:18 PM - 3:07:23 PM
    90 Days Median: 3.38 second(s)
  • @cf/runwayml/stable-diffusion-v1-5-inpainting
    3.75 second(s)
    Last Update: 3.04 minute(s) ago
    Last 24H Peak:
    5.57 second(s)
    From 10:36:02 PM - 10:36:07 PM
    90 Days Median: 3.42 second(s)
  • @cf/stabilityai/stable-diffusion-xl-base-1.0
    10.29 second(s)
    Last Update: 2.92 minute(s) ago
    Last 24H Peak:
    22.92 second(s)
    From 7:18:03 PM - 7:18:25 PM
    90 Days Median: 10.37 second(s)
  • @cf/thebloke/discolm-german-7b-v1-awq
    2.77 second(s)
    Last Update: 3.07 minute(s) ago
    Last 24H Peak:
    3.96 second(s)
    From 11:52:01 PM - 11:52:04 PM
    90 Days Median: 2.79 second(s)
  • @cf/tiiuae/falcon-7b-instruct
    6.72 second(s)
    Last Update: 3.00 minute(s) ago
    Last 24H Peak:
    7.82 second(s)
    From 11:01:55 AM - 11:02:02 AM
    90 Days Median: 6.69 second(s)
  • @cf/tinyllama/tinyllama-1.1b-chat-v1.0
    1.83 second(s)
    Last Update: 3.10 minute(s) ago
    Last 24H Peak:
    3.23 second(s)
    From 8:23:26 AM - 8:23:29 AM
    90 Days Median: 1.91 second(s)
  • @cf/unum/uform-gen2-qwen-500m
    2.96 second(s)
    Last Update: 3.02 minute(s) ago
    Last 24H Peak:
    13.78 second(s)
    From 3:15:58 PM - 3:16:11 PM
    90 Days Median: 2.49 second(s)
  • @hf/google/gemma-7b-it
    8.42 second(s)
    Last Update: 2.96 minute(s) ago
    Last 24H Peak:
    9.49 second(s)
    From 10:30:24 AM - 10:30:33 AM
    90 Days Median: 8.43 second(s)
  • @hf/meta-llama/meta-llama-3-8b-instruct
    6.80 second(s)
    Last Update: 2.98 minute(s) ago
    Last 24H Peak:
    7.73 second(s)
    From 5:39:57 PM - 5:40:04 PM
    90 Days Median: 6.80 second(s)
  • @cf/meta/m2m100-1.2b
    2.07 second(s)
    Last Update: 3.06 minute(s) ago
    Last 24H Peak:
    7.50 second(s)
    From 8:50:42 PM - 8:50:49 PM
    90 Days Median: 1.63 second(s)
  • @cf/microsoft/phi-2
    3.38 second(s)
    Last Update: 3.04 minute(s) ago
    Last 24H Peak:
    3.82 second(s)
    From 5:49:34 PM - 5:49:37 PM
    90 Days Median: 3.10 second(s)
  • @cf/microsoft/resnet-50
    0.33 second(s)
    Last Update: 3.10 minute(s) ago
    Last 24H Peak:
    0.76 second(s)
    From 2:18:55 PM - 2:18:55 PM
    90 Days Median: 0.31 second(s)
  • @cf/myshell-ai/melotts
    1.77 second(s)
    Last Update: 3.10 minute(s) ago
    Last 24H Peak:
    2.58 second(s)
    From 3:20:31 AM - 3:20:33 AM
    90 Days Median: 1.43 second(s)
  • @cf/openai/gpt-oss-120b
    16.39 second(s)
    Last Update: 2.83 minute(s) ago
    Last 24H Peak:
    27.97 second(s)
    From 4:01:07 PM - 4:01:34 PM
    90 Days Median: 16.96 second(s)
  • @cf/openai/gpt-oss-20b
    7.62 second(s)
    Last Update: 2.74 minute(s) ago
    Last 24H Peak:
    36.41 second(s)
    From 12:17:36 PM - 12:18:12 PM
    90 Days Median: 8.10 second(s)
  • @cf/openai/whisper
    1.17 second(s)
    Last Update: 3.10 minute(s) ago
    Last 24H Peak:
    8.45 second(s)
    From 8:33:56 PM - 8:34:04 PM
    90 Days Median: 1.16 second(s)
  • @cf/openai/whisper-large-v3-turbo
    0.84 second(s)
    Last Update: 3.07 minute(s) ago
    Last 24H Peak:
    2.50 second(s)
    From 1:47:51 AM - 1:47:53 AM
    90 Days Median: 1.13 second(s)
  • @cf/openai/whisper-tiny-en
    0.94 second(s)
    Last Update: 3.07 minute(s) ago
    Last 24H Peak:
    1.49 second(s)
    From 10:41:25 PM - 10:41:26 PM
    90 Days Median: 0.97 second(s)
  • @cf/baai/bge-large-en-v1.5
    0.33 second(s)
    Last Update: 3.08 minute(s) ago
    Last 24H Peak:
    2.85 second(s)
    From 6:24:24 PM - 6:24:26 PM
    90 Days Median: 0.37 second(s)
  • @cf/baai/bge-small-en-v1.5
    0.28 second(s)
    Last Update: 3.10 minute(s) ago
    Last 24H Peak:
    0.66 second(s)
    From 5:52:52 PM - 5:52:52 PM
    90 Days Median: 0.36 second(s)
  • @cf/deepseek-ai/deepseek-r1-distill-qwen-32b
    3.05 second(s)
    Last Update: 3.07 minute(s) ago
    Last 24H Peak:
    20.89 second(s)
    From 9:17:19 PM - 9:17:39 PM
    90 Days Median: 3.00 second(s)
  • @cf/baai/bge-base-en-v1.5
    0.38 second(s)
    Last Update: 3.10 minute(s) ago
    Last 24H Peak:
    0.71 second(s)
    From 3:40:13 PM - 3:40:13 PM
    90 Days Median: 0.35 second(s)
  • @hf/nexusflow/starling-lm-7b-beta
    7.06 second(s)
    Last Update: 3.01 minute(s) ago
    Last 24H Peak:
    8.42 second(s)
    From 11:30:10 PM - 11:30:18 PM
    90 Days Median: 7.12 second(s)
  • @hf/nousresearch/hermes-2-pro-mistral-7b
    7.07 second(s)
    Last Update: 2.99 minute(s) ago
    Last 24H Peak:
    11.40 second(s)
    From 1:29:49 PM - 1:30:00 PM
    90 Days Median: 7.05 second(s)
  • @hf/thebloke/deepseek-coder-6.7b-base-awq
    2.63 second(s)
    Last Update: 3.07 minute(s) ago
    Last 24H Peak:
    15.46 second(s)
    From 4:29:40 PM - 4:29:55 PM
    90 Days Median: 2.68 second(s)
  • @hf/thebloke/deepseek-coder-6.7b-instruct-awq
    2.72 second(s)
    Last Update: 3.05 minute(s) ago
    Last 24H Peak:
    4.07 second(s)
    From 7:01:45 PM - 7:01:49 PM
    90 Days Median: 2.83 second(s)
  • @hf/thebloke/llama-2-13b-chat-awq
    4.29 second(s)
    Last Update: 3.04 minute(s) ago
    Last 24H Peak:
    5.77 second(s)
    From 12:09:53 PM - 12:09:58 PM
    90 Days Median: 4.50 second(s)
  • @hf/thebloke/llamaguard-7b-awq
    1.47 second(s)
    Last Update: 3.10 minute(s) ago
    Last 24H Peak:
    3.03 second(s)
    From 8:52:00 AM - 8:52:03 AM
    90 Days Median: 1.93 second(s)
  • @hf/thebloke/mistral-7b-instruct-v0.1-awq
    2.69 second(s)
    Last Update: 3.07 minute(s) ago
    Last 24H Peak:
    4.00 second(s)
    From 12:23:44 PM - 12:23:47 PM
    90 Days Median: 2.77 second(s)
  • @hf/thebloke/neural-chat-7b-v3-1-awq
    2.51 second(s)
    Last Update: 3.09 minute(s) ago
    Last 24H Peak:
    3.71 second(s)
    From 5:54:20 PM - 5:54:23 PM
    90 Days Median: 2.97 second(s)
  • @hf/thebloke/openhermes-2.5-mistral-7b-awq
    2.94 second(s)
    Last Update: 3.05 minute(s) ago
    Last 24H Peak:
    4.39 second(s)
    From 3:25:06 AM - 3:25:10 AM
    90 Days Median: 2.77 second(s)
  • @hf/thebloke/zephyr-7b-beta-awq
    2.82 second(s)
    Last Update: 3.06 minute(s) ago
    Last 24H Peak:
    4.26 second(s)
    From 10:31:12 PM - 10:31:16 PM
    90 Days Median: 2.79 second(s)
  • @cf/google/gemma-2b-it-lora
    7.76 second(s)
    Last Update: 3.00 minute(s) ago
    Last 24H Peak:
    16.77 second(s)
    From 12:50:29 AM - 12:50:45 AM
    90 Days Median: 9.14 second(s)
  • @cf/google/gemma-3-12b-it
    1.86 second(s)
    Last Update: 3.06 minute(s) ago
    Last 24H Peak:
    4.91 second(s)
    From 2:44:34 PM - 2:44:38 PM
    90 Days Median: 1.76 second(s)
  • @cf/google/gemma-7b-it-lora
    8.39 second(s)
    Last Update: 2.96 minute(s) ago
    Last 24H Peak:
    9.35 second(s)
    From 1:43:36 PM - 1:43:45 PM
    90 Days Median: 8.50 second(s)
  • @cf/huggingface/distilbert-sst-2-int8
    0.51 second(s)
    Last Update: 3.12 minute(s) ago
    Last 24H Peak:
    1.20 second(s)
    From 4:55:54 PM - 4:55:55 PM
    90 Days Median: 0.52 second(s)
  • @cf/llava-hf/llava-1.5-7b-hf
    5.79 second(s)
    Last Update: 3.01 minute(s) ago
    Last 24H Peak:
    7.02 second(s)
    From 8:23:31 AM - 8:23:38 AM
    90 Days Median: 6.03 second(s)
  • @cf/lykon/dreamshaper-8-lcm
    4.44 second(s)
    Last Update: 3.01 minute(s) ago
    Last 24H Peak:
    8.42 second(s)
    From 1:06:04 PM - 1:06:12 PM
    90 Days Median: 3.61 second(s)
  • @cf/meta-llama/llama-2-7b-chat-hf-lora
    6.21 second(s)
    Last Update: 3.01 minute(s) ago
    Last 24H Peak:
    7.46 second(s)
    From 7:47:21 PM - 7:47:28 PM
    90 Days Median: 6.39 second(s)
  • @cf/meta/llama-2-7b-chat-fp16
    6.30 second(s)
    Last Update: 3.02 minute(s) ago
    Last 24H Peak:
    7.51 second(s)
    From 5:33:24 PM - 5:33:31 PM
    90 Days Median: 6.47 second(s)
  • @cf/meta/llama-2-7b-chat-int8
    3.09 second(s)
    Last Update: 3.06 minute(s) ago
    Last 24H Peak:
    4.46 second(s)
    From 3:17:08 PM - 3:17:12 PM
    90 Days Median: 3.19 second(s)
  • @cf/meta/llama-3-8b-instruct
    6.86 second(s)
    Last Update: 3.02 minute(s) ago
    Last 24H Peak:
    7.55 second(s)
    From 3:49:52 PM - 3:49:59 PM
    90 Days Median: 6.86 second(s)
  • @cf/meta/llama-3-8b-instruct-awq
    3.07 second(s)
    Last Update: 3.05 minute(s) ago
    Last 24H Peak:
    4.09 second(s)
    From 5:43:05 PM - 5:43:09 PM
    90 Days Median: 3.15 second(s)
  • @cf/mistral/mistral-7b-instruct-v0.1
    6.81 second(s)
    Last Update: 3.01 minute(s) ago
    Last 24H Peak:
    7.76 second(s)
    From 5:00:47 PM - 5:00:54 PM
    90 Days Median: 6.92 second(s)
  • @cf/mistral/mistral-7b-instruct-v0.2-lora
    6.97 second(s)
    Last Update: 3.01 minute(s) ago
    Last 24H Peak:
    7.60 second(s)
    From 2:52:54 AM - 2:53:01 AM
    90 Days Median: 6.95 second(s)
  • @cf/mistralai/mistral-small-3.1-24b-instruct
    2.38 second(s)
    Last Update: 3.05 minute(s) ago
    Last 24H Peak:
    3.95 second(s)
    From 5:20:49 PM - 5:20:52 PM
    90 Days Median: 2.33 second(s)