Catalog Changes
Version history starts when recording is enabled. Versions are created when reported values, array items or listing availability change. Array differences align positions, not inferred identities. The first observation is a baseline; unchanged downloads update last observation time.
Catalog Changes
-
nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 · 2026-10-15 00:04:23.550774 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 445.8 326.8 Providers[0] · Throughput 246.63764647599527 318.0305543404482 -
Qwen/Qwen3-235B-A22B-Instruct-2507 · 2026-10-15 00:04:23.540476 UTC
Current Model ListingHugging Face
4 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 627.6 429.4 Providers[0] · Throughput 55.3264380049093 82.60232519689933 Providers[1] · First Token Latency Ms 233.4 429.4 Providers[1] · Throughput 19.575197155530766 17.015581042115283 -
MiniMaxAI/MiniMax-M1-80k · 2026-10-15 00:04:23.530726 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 1042 1023.4 Providers[0] · Throughput 40.117218669781046 50.13242638212681 -
zai-org/GLM-4.5V-FP8 · 2026-10-15 00:04:23.520569 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 1927.75 1989 Providers[0] · Throughput 62.89563379757317 57.95719339813129 -
deepseek-ai/DeepSeek-V4-Flash-0731 · 2026-10-15 00:04:23.509132 UTC
Current Model ListingHugging Face
10 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 1043.6 807.6 Providers[0] · Throughput 90.73732165258617 79.59270941207521 Providers[1] · First Token Latency Ms 399 734 Providers[1] · Throughput 46.010858562620776 29.7415004915864 Providers[3] · First Token Latency Ms 1866.5 4585 -
meta-llama/Llama-4-Scout-17B-16E-Instruct · 2026-10-15 00:04:23.497714 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[1] · First Token Latency Ms 351.8 487.2 Providers[1] · Throughput 23.900867455634405 20.562478491905257 -
deepseek-ai/DeepSeek-R1-0528 · 2026-10-15 00:04:23.486756 UTC
Current Model ListingHugging Face
5 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 1071.2 1191.8 Providers[0] · Supports Structured Output False True Providers[0] · Throughput 17.070920596390387 22.030811187589915 Providers[2] · First Token Latency Ms 751.6 645.4 Providers[2] · Throughput 32.87359514697633 27.579617037347457 -
zai-org/GLM-4.7 · 2026-10-15 00:04:23.475499 UTC
Current Model ListingHugging Face
4 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 2954.3333333333335 3770.6 Providers[0] · Throughput 26.24701343608422 25.058819093781903 Providers[2] · First Token Latency Ms 3355.2 711.2 Providers[2] · Throughput 16.179213235643775 22.556692195921197 -
meta-llama/Llama-3.1-8B-Instruct · 2026-10-15 00:04:23.464516 UTC
Current Model ListingHugging Face
4 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 519.8 632.5 Providers[0] · Throughput 168.5839481457384 110.68786505365318 Providers[2] · First Token Latency Ms 310.8 404.8 Providers[2] · Throughput 18.15044121379689 14.561985271669803 -
inclusionAI/Ling-3.0-flash-Fin · 2026-10-15 00:04:23.453579 UTC
Current Model ListingHugging Face
3 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 896.4 909.8 Providers[0] · Throughput 110.22366269071165 108.27817505050396 Providers[1] · Supports Structured Output True False -
deepseek-ai/DeepSeek-V3 · 2026-10-15 00:04:23.437327 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 514 1601.2 Providers[0] · Throughput 34.98745754902952 31.795256282162843 -
zai-org/GLM-5.3-Flash-BF16 · 2026-10-15 00:04:23.426077 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 2575.6 2082.8 Providers[0] · Throughput 40.33227567124337 49.40331382628225 -
nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4 · 2026-10-15 00:04:23.349217 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 385.2 563 Providers[0] · Throughput 104.33474626459353 82.43343500123649 -
Anthropic: Claude Sonnet 4 (retires Oct 15) · 2026-10-15 00:04:20.656499 UTC
Current Model ListingKilo
2 Changed Fields
Field / Array Position Previous Value Observed Value Expiration Date Explicit Null 2026-10-15 Name Anthropic: Claude Sonnet 4 Anthropic: Claude Sonnet 4 (retires Oct 15) -
Mistral: Mistral Small 3.2 24B · 2026-10-15 00:04:20.611262 UTC
Current Model ListingKilo
1 Changed Fields
Field / Array Position Previous Value Observed Value Top Provider · Context Length 256000 128000 -
Qwen: Qwen3 Coder 30B A3B Instruct · 2026-10-15 00:04:20.528583 UTC
Current Model ListingKilo
8 Changed Fields
Field / Array Position Previous Value Observed Value Supported Parameters[3] stop structured_outputs Supported Parameters[4] structured_outputs temperature Supported Parameters[5] temperature tool_choice Supported Parameters[6] tool_choice tools Supported Parameters[7] tools top_k -
Z.ai: GLM 5 · 2026-10-15 00:04:20.138663 UTC
Current Model ListingKilo
5 Changed Fields
Field / Array Position Previous Value Observed Value Output Price · USD/Token 0.00000192 0.0000032 Pricing · Input Cache Read 0.00000012 0.0000002 Input Price · USD/Token 0.0000006 0.000001 Top Provider · Context Length 198000 202752 Top Provider · Max Completion Tokens 128000 131072 -
MiniMax: MiniMax M2.5 · 2026-10-15 00:04:20.128282 UTC
Current Model ListingKilo
2 Changed Fields
Field / Array Position Previous Value Observed Value Top Provider · Context Length 200000 198000 Top Provider · Max Completion Tokens 128000 32768 -
Z.ai: GLM 5.1 · 2026-10-15 00:04:19.918277 UTC
Current Model ListingKilo
2 Changed Fields
Field / Array Position Previous Value Observed Value Top Provider · Context Length 202745 200000 Top Provider · Max Completion Tokens 131072 128000 -
Qwen: Qwen3.6 35B A3B · 2026-10-15 00:04:19.824882 UTC
Current Model ListingKilo
4 Changed Fields
Field / Array Position Previous Value Observed Value Output Price · USD/Token 0.00000095 0.000001 Pricing · Input Cache Read 0.0000001 0.00000005 Input Price · USD/Token 0.0000001 0.00000015 Top Provider · Max Completion Tokens 65536 235929 - Next 20 Changes →