llm-catalog-archive
RSS Repository

The archive

Everything

9,360 items derived by replay from git history over raw/, newest first. Every sentence names the artifact it was read out of and links those bytes at the commit that stored them.

The 12 most recently active threads, as tabs. The other 754 are in the threads index, uncapped. Where this browser can draw it, the same 12 tabs are a wall in three dimensions; the list is what they link, and the list is what is here when they are not.

What happened

Announcements, incidents, leaks, and models arriving or leaving a catalogue. The full stream below is chronological and includes these again, plus the routine catalogue activity they would otherwise be buried under.

  1. upstream_pr_opened A pull request numbered "vllm-project/vllm#64867" is titled "[Model][Doc] Add RTX PRO 6000 Blackwell support for DeepSeek-V4-Flash-Vision-Exp" in the collected search payload. observed
  2. model_removed The catalog id "poolside/laguna-s-2.1" left OpenRouter's catalog. origin
  3. model_removed The catalog id "poolside/laguna-s-2.1:free" left OpenRouter's catalog. origin
  4. model_removed The catalog id "poolside/laguna-xs-2.1" left OpenRouter's catalog. origin
  5. post_published The huggingface-blog-feed published a post titled "nemotron-halloween" at "https://huggingface.co/blog/nvidia/nemotron-halloween". observed
  6. post_listed The deepmind-sitemap index listed a URL it had not listed before: "https://deepmind.google/research/publications/279443/". observed
  7. upstream_pr_opened A pull request numbered "vllm-project/vllm#64672" is titled "[Model] Add Raon-1-mini support" in the collected search payload. observed
  8. upstream_pr_opened A pull request numbered "vllm-project/vllm#64683" is titled "[Model] Add Apriel Voice support" in the collected search payload. observed
By lab

minimax78 openai456 deepseek2,887 zai1,300 moonshot701 xai87 qwen446 anthropic617 google238 mistral488 perplexity108 together154 nvidia135 meta92 cohere1

Showing 150 items of 9,360: 4,183 held back so that no single capture fills the page, and 5,027 beyond this page's limit of 150. Nothing is dropped: every item is also on its micro-category page, on its lab page where it has one, and on the entity thread it attaches to where one could be resolved, and none of those are capped.

2026-11-01

  1. 4429af8 openrouter-models origin
    12 listed values moved across 5 models in this capture. Both numbers are the artifact's own; the percentage is this page's arithmetic over them. Each model links to its thread, which carries the full sentence and every other item recorded against it.
    FieldFromToChange
    minimax/minimax-m3.1-flash
    completion 0.0000006 0.0000003 50%
    input_cache_read 0.000000015 0.0000000075 50%
    prompt 0.00000015 0.000000075 50%
    openai/gpt-oss-120b
    completion 0.00000007 0.000000057 19%
    prompt 0.000000019 0.000000015 21%
    tencent/hy3
    completion 0.000000528 0.00000033 37%
    input_cache_read 0.000000033 0.000000020625 37%
    prompt 0.000000132 0.0000000825 37%
    tencent/hy4-preview
    completion 0.000002501 0.0000022509 10%
    input_cache_read 0.000000042 0.0000000378 10%
    prompt 0.000000834 0.0000007506 10%
    ~deepseek/deepseek-v4-flash-latest
    prompt 0.0000000434 0.000000059 36%
  2. 1a8037b openrouter-models origin
    5 listed values moved across 2 models in this capture. Both numbers are the artifact's own; the percentage is this page's arithmetic over them. Each model links to its thread, which carries the full sentence and every other item recorded against it.
    FieldFromToChange
    openai/gpt-oss-120b
    completion 0.000000078 0.00000007 10%
    prompt 0.000000021 0.000000019 10%
    z-ai/glm-5.3
    completion 0.0000014 0.0000036 157%
    input_cache_read 0.0000000689 0.000000076 10%
    prompt 0.0000000699 0.00000008 14%
  3. 8039245 openrouter-models origin
    12 listed values shown of 18 that moved across 6 models in this capture. Both numbers are the artifact's own; the percentage is this page's arithmetic over them. Each model links to its thread, which carries the full sentence and every other item recorded against it.
    FieldFromToChange
    moonshotai/kimi-k3
    completion 0.0000096 0.000015 56%
    input_cache_read 0.00000013 0.000000182 40%
    prompt 0.000000276 0.000000192 30%
    openai/gpt-oss-120b
    completion 0.0000006 0.000000078 87%
    input_cache_read 0.000000075 absent
    prompt 0.00000015 0.000000021 86%
    openai/gpt-oss-20b
    completion 0.00000009 0.00000013 44%
    input_cache_read 0.000000009 0.00000003 233%
    prompt 0.000000018 0.00000003 67%
    z-ai/glm-5.3-flash
    completion 0.0000001602 0.0000000923 42%
    input_cache_read 0.0000000136 0.0000000285 110%
    prompt 0.0000000136 0.0000000285 110%

    6 further items from this capture are not shown here. Every one of them is on its micro-category page, which is uncapped.

  4. 78a84eb vllm-pulls observed
    1. upstream_pr_opened confirmed-artifact

      A pull request numbered "vllm-project/vllm#64867" is titled "[Model][Doc] Add RTX PRO 6000 Blackwell support for DeepSeek-V4-Flash-Vision-Exp" in the collected search payload.

      observed · raw artifact at this commit

      held: no entity was mechanically extractable

      repositoryvllm-project/vllm
      pull request64867
      title[Model][Doc] Add RTX PRO 6000 Blackwell support for DeepSeek-V4-Flash-Vision-Exp
      architecture named in the titleRTX PRO 6000 Blackwell
      pull request URLhttps://github.com/vllm-project/vllm/pull/64867
      created_at2026-10-31T07:30:02Z
      stateopen

      Check for a published weights repository under this name: https://huggingface.co/api/models?search=RTX%20PRO%206000%20Blackwell. An empty array is a statement about that search, not about what exists.

  5. dcedc3b xai-llms-txt observed
    1. doc_added

      The xai-llms-txt index added an entry titled "Advanced API Usage — Output Watermarking" at "https://docs.x.ai/developers/advanced-api-usage/watermarking.md".

      observed · raw artifact at this commit

      api-surfacedocs.x.ai/developers/advanced-api-usage labxai

  6. 6516575 openrouter-models origin
    12 listed values shown of 25 that moved across 9 models in this capture. Both numbers are the artifact's own; the percentage is this page's arithmetic over them. Each model links to its thread, which carries the full sentence and every other item recorded against it.
    FieldFromToChange
    minimax/minimax-m3.1-flash
    completion 0.0000003 0.0000006 100%
    input_cache_read 0.0000000075 0.000000015 100%
    prompt 0.000000075 0.00000015 100%
    moonshotai/kimi-k3
    completion 0.000015 0.0000096 36%
    input_cache_read 0.000000182 0.00000013 29%
    prompt 0.000000192 0.000000276 44%
    qwen/qwen3.8-27b
    completion 0.0000023 0.000001875 18%
    input_cache_read 0.00000002 0.0000000375 87%
    prompt 0.00000004 0.00000015 275%
    tencent/hy3
    completion 0.00000033 0.000000528 60%
    input_cache_read 0.000000020625 0.000000033 60%
    prompt 0.0000000825 0.000000132 60%

    13 further items from this capture are not shown here. Every one of them is on its micro-category page, which is uncapped.

2026-10-31

  1. 9c371f1 openrouter-models origin
    8 listed values moved across 4 models in this capture. Both numbers are the artifact's own; the percentage is this page's arithmetic over them. Each model links to its thread, which carries the full sentence and every other item recorded against it.
    FieldFromToChange
    z-ai/glm-5.3-flash
    completion 0.0000001479 0.0000001543 4%
    input_cache_read 0.0000000163 0.0000000149 9%
    prompt 0.0000000163 0.0000000149 9%
    ~deepseek/deepseek-flash-latest
    completion 0.000000144 0.00000011 24%
    ~deepseek/deepseek-v4-flash-latest
    prompt 0.0000000566 0.0000000448 21%
    ~z-ai/glm-flash-latest
    completion 0.0000001479 0.0000001543 4%
    input_cache_read 0.0000000163 0.0000000149 9%
    prompt 0.0000000163 0.0000000149 9%
  2. 2ebe832 openrouter-models origin
    1. expiration_scheduled confirmed-artifact

      OpenRouter's catalog recorded an expiration_date of "2026-12-31" for "z-ai/glm-4.7".

      origin · raw artifact at this commit

      modelz-ai/glm-4.7 labzai

      catalog idz-ai/glm-4.7
      expiration_date2026-12-31
      sentinel checka year at or past 2090 is read as the vendor spelling "no expiry" and is not listed here
    2. expiration_set

      OpenRouter's catalog recorded an expiration_date of "2026-12-31" for "z-ai/glm-4.7".

      origin · raw artifact at this commit

      modelz-ai/glm-4.7 labzai

    10 listed values shown of 18 that moved across 6 models in this capture. Both numbers are the artifact's own; the percentage is this page's arithmetic over them. Each model links to its thread, which carries the full sentence and every other item recorded against it.
    FieldFromToChange
    deepseek/deepseek-v4-pro-0813
    completion 0.00000198 0.000004 102%
    input_cache_read 0.000000022 0.00000011 400%
    prompt 0.00000066 0.000000115 83%
    minimax/minimax-m3.1-flash
    completion 0.0000006 0.0000003 50%
    input_cache_read 0.000000015 0.0000000075 50%
    prompt 0.00000015 0.000000075 50%
    tencent/hy3
    completion 0.000000528 0.00000033 37%
    input_cache_read 0.000000033 0.000000020625 37%
    prompt 0.000000132 0.0000000825 37%
    tencent/hy4-preview
    completion 0.000002501 0.0000022509 10%

    8 further items from this capture are not shown here. Every one of them is on its micro-category page, which is uncapped.

  3. 7469728 openrouter-models origin
    1. model_removed

      The catalog id "poolside/laguna-s-2.1" left OpenRouter's catalog.

      origin · raw artifact at this commit

      modelpoolside/laguna-s-2.1

      last seen present31 October 2026 08:52 UTC
    2. model_removed

      The catalog id "poolside/laguna-s-2.1:free" left OpenRouter's catalog.

      origin · raw artifact at this commit

      modelpoolside/laguna-s-2.1:free

      last seen present31 October 2026 08:52 UTC
    3. model_removed

      The catalog id "poolside/laguna-xs-2.1" left OpenRouter's catalog.

      origin · raw artifact at this commit

      modelpoolside/laguna-xs-2.1

      last seen present31 October 2026 08:52 UTC
    4. model_removed

      The catalog id "poolside/laguna-xs-2.1:free" left OpenRouter's catalog.

      origin · raw artifact at this commit

      modelpoolside/laguna-xs-2.1:free

      last seen present31 October 2026 08:52 UTC
  4. 1192742 openrouter-models origin
    12 listed values shown of 20 that moved across 8 models in this capture. Both numbers are the artifact's own; the percentage is this page's arithmetic over them. Each model links to its thread, which carries the full sentence and every other item recorded against it.
    FieldFromToChange
    qwen/qwen3.8-27b
    completion 0.000001875 0.0000023 23%
    input_cache_read 0.0000000375 0.00000002 47%
    prompt 0.00000015 0.00000004 73%
    z-ai/glm-5.2
    completion 0.000007 0.0000068 3%
    z-ai/glm-5.3-flash
    completion 0.0000000625 0.0000001479 137%
    input_cache_read 0.0000000207 0.0000000163 21%
    prompt 0.0000000227 0.0000000163 28%
    ~deepseek/deepseek-flash-latest
    completion 0.000000274 0.000000144 47%
    input_cache_read 0.0000000189 0.000000013 31%
    prompt 0.0000000205 0.0000000141 31%
    ~deepseek/deepseek-pro-latest
    completion 0.000004 0.000008 100%
    ~deepseek/deepseek-v4-flash-latest
    completion 0.0000003 0.00000017292 42%

    8 further items from this capture are not shown here. Every one of them is on its micro-category page, which is uncapped.

  5. e0a0f5d huggingface-blog-feed observed
    1. post_published

      The huggingface-blog-feed published a post titled "nemotron-halloween" at "https://huggingface.co/blog/nvidia/nemotron-halloween".

      observed · raw artifact at this commit

      api-surfacehuggingface.co/blog/nvidia

  6. 3608991 deepmind-sitemap observed
    1. post_listed

      The deepmind-sitemap index listed a URL it had not listed before: "https://deepmind.google/research/publications/279443/".

      observed · raw artifact at this commit

      api-surfacedeepmind.google/research/publications

  7. b96d10f vllm-pulls observed
    1. upstream_pr_opened confirmed-artifact

      A pull request numbered "vllm-project/vllm#64672" is titled "[Model] Add Raon-1-mini support" in the collected search payload.

      observed · raw artifact at this commit

      held: no entity was mechanically extractable

      repositoryvllm-project/vllm
      pull request64672
      title[Model] Add Raon-1-mini support
      architecture named in the titleRaon-1-mini
      pull request URLhttps://github.com/vllm-project/vllm/pull/64672
      created_at2026-10-30T06:13:24Z
      stateopen

      Check for a published weights repository under this name: https://huggingface.co/api/models?search=Raon-1-mini. An empty array is a statement about that search, not about what exists.

    2. upstream_pr_opened confirmed-artifact

      A pull request numbered "vllm-project/vllm#64683" is titled "[Model] Add Apriel Voice support" in the collected search payload.

      observed · raw artifact at this commit

      held: no entity was mechanically extractable

      repositoryvllm-project/vllm
      pull request64683
      title[Model] Add Apriel Voice support
      architecture named in the titleApriel Voice
      pull request URLhttps://github.com/vllm-project/vllm/pull/64683
      created_at2026-10-30T06:51:39Z
      stateopen

      Check for a published weights repository under this name: https://huggingface.co/api/models?search=Apriel%20Voice. An empty array is a statement about that search, not about what exists.

    3. upstream_pr_opened confirmed-artifact

      A pull request numbered "vllm-project/vllm#64832" is titled "[Model] Add SenseNova Loop support" in the collected search payload.

      observed · raw artifact at this commit

      held: no entity was mechanically extractable

      repositoryvllm-project/vllm
      pull request64832
      title[Model] Add SenseNova Loop support
      architecture named in the titleSenseNova Loop
      pull request URLhttps://github.com/vllm-project/vllm/pull/64832
      created_at2026-10-31T00:23:08Z
      stateopen

      Check for a published weights repository under this name: https://huggingface.co/api/models?search=SenseNova%20Loop. An empty array is a statement about that search, not about what exists.

  8. 5cce12f openai-status origin
    1. incident_opened

      The openai-status feed listed an incident titled "Elevated errors for GPT Image 2 API image edits" at "https://status.openai.com//incidents/01M66KSDH67V5BQ73PE8AD2W8S".

      origin · raw artifact at this commit

      held: no entity was mechanically extractable

    2. incident_opened

      The openai-status feed listed an incident titled "Elevated errors with search in Dots, ChatGPT Work, and certain ChatGPT thinking experiences" at "https://status.openai.com//incidents/01M6754SR14HCQ3E9FX426E2N7".

      origin · raw artifact at this commit

      held: no entity was mechanically extractable

  9. 8e4d961 claude-llms-txt origin
    1. doc_added

      The claude-llms-txt index added an entry titled "Claude Tag (Beta)" at "https://platform.claude.com/docs/en/api/beta/organization/claude_tag.md".

      origin · raw artifact at this commit

      api-surfaceplatform.claude.com/docs/en/api/beta/organization labanthropic

    2. doc_added

      The claude-llms-txt index added an entry titled "Bundles (Beta)" at "https://platform.claude.com/docs/en/api/beta/organization/claude_tag/bundles.md".

      origin · raw artifact at this commit

      api-surfaceplatform.claude.com/docs/en/api/beta/organization/claude_tag labanthropic

    3. doc_added

      The claude-llms-txt index added an entry titled "List Bundles (Beta)" at "https://platform.claude.com/docs/en/api/beta/organization/claude_tag/bundles/list.md".

      origin · raw artifact at this commit

      api-surfaceplatform.claude.com/docs/en/api/beta/organization/claude_tag/bundles labanthropic

    4. doc_added

      The claude-llms-txt index added an entry titled "Get Bundle (Beta)" at "https://platform.claude.com/docs/en/api/beta/organization/claude_tag/bundles/retrieve.md".

      origin · raw artifact at this commit

      api-surfaceplatform.claude.com/docs/en/api/beta/organization/claude_tag/bundles labanthropic

    5. doc_added

      The claude-llms-txt index added an entry titled "Targets (Beta)" at "https://platform.claude.com/docs/en/api/beta/organization/claude_tag/bundles/targets.md".

      origin · raw artifact at this commit

      api-surfaceplatform.claude.com/docs/en/api/beta/organization/claude_tag/bundles labanthropic

    6. doc_added

      The claude-llms-txt index added an entry titled "Attach Bundle (Beta)" at "https://platform.claude.com/docs/en/api/beta/organization/claude_tag/bundles/targets/create.md".

      origin · raw artifact at this commit

      api-surfaceplatform.claude.com/docs/en/api/beta/organization/claude_tag/bundles/targets labanthropic

    7. doc_added

      The claude-llms-txt index added an entry titled "Detach Bundle (Beta)" at "https://platform.claude.com/docs/en/api/beta/organization/claude_tag/bundles/targets/delete.md".

      origin · raw artifact at this commit

      api-surfaceplatform.claude.com/docs/en/api/beta/organization/claude_tag/bundles/targets labanthropic

    8. doc_added

      The claude-llms-txt index added an entry titled "List Bundle Targets (Beta)" at "https://platform.claude.com/docs/en/api/beta/organization/claude_tag/bundles/targets/list.md".

      origin · raw artifact at this commit

      api-surfaceplatform.claude.com/docs/en/api/beta/organization/claude_tag/bundles/targets labanthropic

    9. doc_added

      The claude-llms-txt index added an entry titled "Get Bundle Target (Beta)" at "https://platform.claude.com/docs/en/api/beta/organization/claude_tag/bundles/targets/retrieve.md".

      origin · raw artifact at this commit

      api-surfaceplatform.claude.com/docs/en/api/beta/organization/claude_tag/bundles/targets labanthropic

    10. doc_added

      The claude-llms-txt index added an entry titled "Slack Channels (Beta)" at "https://platform.claude.com/docs/en/api/beta/organization/claude_tag/slack_channels.md".

      origin · raw artifact at this commit

      api-surfaceplatform.claude.com/docs/en/api/beta/organization/claude_tag labanthropic

    11. doc_added

      The claude-llms-txt index added an entry titled "Set Up Slack Channel (Beta)" at "https://platform.claude.com/docs/en/api/beta/organization/claude_tag/slack_channels/create.md".

      origin · raw artifact at this commit

      api-surfaceplatform.claude.com/docs/en/api/beta/organization/claude_tag/slack_channels labanthropic

    12. doc_added

      The claude-llms-txt index added an entry titled "Remove Slack Channel (Beta)" at "https://platform.claude.com/docs/en/api/beta/organization/claude_tag/slack_channels/delete.md".

      origin · raw artifact at this commit

      api-surfaceplatform.claude.com/docs/en/api/beta/organization/claude_tag/slack_channels labanthropic

    7 further items from this capture are not shown here. Every one of them is on its micro-category page, which is uncapped.

  10. 6abdfee openai-news-feed origin
    1. post_published

      The openai-news-feed published a post titled "Community safety report and new protections for teens" at "https://openai.com/index/community-safety-report-and-new-protections-for-teens".

      origin · raw artifact at this commit

      api-surfaceopenai.com/index labopenai

    2. post_published

      The openai-news-feed published a post titled "Credit Saison achieves 954% ROI in a ChatGPT Enterprise pilot" at "https://openai.com/index/credit-saison".

      origin · raw artifact at this commit

      api-surfaceopenai.com/index labopenai

    3. post_published

      The openai-news-feed published a post titled "Fair use benefits everyone" at "https://openai.com/index/fair-use-benefits-everyone".

      origin · raw artifact at this commit

      api-surfaceopenai.com/index labopenai

    4. post_published

      The openai-news-feed published a post titled "Making it easier for websites to express AI training preferences" at "https://openai.com/index/helping-websites-express-ai-training-preferences".

      origin · raw artifact at this commit

      api-surfaceopenai.com/index labopenai

  11. 18a9bcb openrouter-models origin
    12 listed values shown of 29 that moved across 11 models in this capture. Both numbers are the artifact's own; the percentage is this page's arithmetic over them. Each model links to its thread, which carries the full sentence and every other item recorded against it.
    FieldFromToChange
    minimax/minimax-m2.5
    completion 0.0000012 0.00000095 21%
    prompt 0.0000003 0.00000027 10%
    minimax/minimax-m3.1-flash
    completion 0.0000003 0.0000006 100%
    input_cache_read 0.0000000075 0.000000015 100%
    prompt 0.000000075 0.00000015 100%
    qwen/qwen3.6-27b
    completion 0.0000032 0.0000027 16%
    prompt 0.00000032 0.00000045 41%
    tencent/hy3
    completion 0.00000033 0.000000528 60%
    input_cache_read 0.000000020625 0.000000033 60%
    prompt 0.0000000825 0.000000132 60%
    tencent/hy4-preview
    completion 0.0000022509 0.000002501 11%
    input_cache_read 0.0000000378 0.000000042 11%

    17 further items from this capture are not shown here. Every one of them is on its micro-category page, which is uncapped.

2026-10-30

  1. 6775255 openrouter-models origin
    11 listed values moved across 4 models in this capture. Both numbers are the artifact's own; the percentage is this page's arithmetic over them. Each model links to its thread, which carries the full sentence and every other item recorded against it.
    FieldFromToChange
    deepseek/deepseek-v4-pro
    completion 0.0000018966 0.0000032 69%
    input_cache_read 0.000000079025 0.000000135 71%
    prompt 0.0000009483 0.0000016 69%
    z-ai/glm-5.3
    completion 0.0000036 0.000002769 23%
    input_cache_read 0.000000076 0.000000099 30%
    prompt 0.00000008 0.000000104 30%
    ~deepseek/deepseek-v4-flash-latest
    input_cache_read 0.0000000476 0.0000000321 33%
    prompt 0.0000000486 0.0000000331 32%
    ~moonshotai/kimi-latest
    completion 0.0000093388 0.0000105572 13%
    input_cache_read 0.00000016 0.00000015 6%
    prompt 0.0000001634 0.0000001529 6%
  2. 5548c8a openrouter-models origin
    12 listed values shown of 22 that moved across 8 models in this capture. Both numbers are the artifact's own; the percentage is this page's arithmetic over them. Each model links to its thread, which carries the full sentence and every other item recorded against it.
    FieldFromToChange
    google/gemma-4-26b-a4b-it
    completion 0.0000003 0.000000225 25%
    input_cache_read 0.00000005 0.0000000375 25%
    prompt 0.00000009 0.0000000675 25%
    particle-ai/particle-1
    completion 0.000001 0.0000005 50%
    prompt 0.0000001 0.00000005 50%
    tencent/hy3
    completion 0.000000528 0.00000033 37%
    input_cache_read 0.000000033 0.000000020625 37%
    prompt 0.000000132 0.0000000825 37%
    tencent/hy4-preview
    completion 0.000002501 0.0000022509 10%
    input_cache_read 0.000000042 0.0000000378 10%
    prompt 0.000000834 0.0000007506 10%
    z-ai/glm-5.3-flash
    completion 0.0000001402 0.0000001324 6%

    10 further items from this capture are not shown here. Every one of them is on its micro-category page, which is uncapped.

  3. e528d6a openrouter-models origin
    12 listed values shown of 32 that moved across 12 models in this capture. Both numbers are the artifact's own; the percentage is this page's arithmetic over them. Each model links to its thread, which carries the full sentence and every other item recorded against it.
    FieldFromToChange
    deepseek/deepseek-v3.2
    completion 0.00000042 0.00000038 10%
    input_cache_read 0.000000028 0.00000013 364%
    prompt 0.00000028 0.00000026 7%
    deepseek/deepseek-v4-pro-0813
    completion 0.00000396 0.00000198 50%
    input_cache_read 0.000000044 0.000000022 50%
    prompt 0.00000132 0.00000066 50%
    deepseek/deepseek-v4-pro
    completion 0.000001632468 0.0000018966 16%
    input_cache_read 0.0000000680195 0.000000079025 16%
    prompt 0.000000816234 0.0000009483 16%
    deepseek/deepseek-v4.1-flash-1017
    completion 0.0000012 0.0000006 50%
    input_cache_read 0.000000006 0.000000003 50%
    prompt 0.0000003 0.00000015 50%

    20 further items from this capture are not shown here. Every one of them is on its micro-category page, which is uncapped.

  4. 973f48b openrouter-models origin
    1 listed value shown of 17 that moved across 7 models in this capture. Both numbers are the artifact's own; the percentage is this page's arithmetic over them. Each model links to its thread, which carries the full sentence and every other item recorded against it.
    FieldFromToChange
    google/gemma-4-26b-a4b-it
    completion 0.000000255 0.0000003 18%

    16 further items from this capture are not shown here. Every one of them is on its micro-category page, which is uncapped.