{
    "archive_path": "archive/1788473181.478047",
    "base_url": "inference-docs.cerebras.ai/models/overview",
    "basename": "overview",
    "bookmarked_date": "2026-09-03 22:06",
    "canonical": {
        "archive_org_path": "https://web.archive.org/web/inference-docs.cerebras.ai/models/overview",
        "dom_path": "output.html",
        "favicon_path": "favicon.ico",
        "git_path": "git/",
        "google_favicon_path": "https://www.google.com/s2/favicons?domain=inference-docs.cerebras.ai",
        "headers_path": "headers.json",
        "htmltotext_path": "htmltotext.txt",
        "index_path": "index.html",
        "media_path": "media/",
        "mercury_path": "mercury/content.html",
        "pdf_path": "output.pdf",
        "readability_path": "readability/content.html",
        "screenshot_path": "screenshot.png",
        "singlefile_path": "singlefile.html",
        "warc_path": "warc/",
        "wget_path": "inference-docs.cerebras.ai/models/overview.html"
    },
    "domain": "inference-docs.cerebras.ai",
    "extension": "",
    "hash": "1CZDGSJ3DGY0S7F1T97H",
    "history": {
        "archive_org": [],
        "dom": [],
        "favicon": [
            {
                "cmd": [
                    "curl",
                    "--silent",
                    "--location",
                    "--compressed",
                    "--max-time",
                    "120",
                    "--output",
                    "favicon.ico",
                    "--user-agent",
                    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/118.0.0.0 Safari/537.36 ArchiveBox/0.7.4 (+https://github.com/ArchiveBox/ArchiveBox/) curl/curl 8.14.1 (x86_64-pc-linux-gnu)",
                    "https://www.google.com/s2/favicons?domain=inference-docs.cerebras.ai"
                ],
                "cmd_version": "curl 8.14.1 (x86_64-pc-linux-gnu)",
                "end_ts": "2026-09-03T22:07:21.732617+00:00",
                "index_texts": null,
                "output": "favicon.ico",
                "pwd": "/data/archive/1788473181.478047",
                "schema": "ArchiveResult",
                "start_ts": "2026-09-03T22:07:21.346626+00:00",
                "status": "succeeded"
            }
        ],
        "git": [],
        "headers": [
            {
                "cmd": [
                    "curl",
                    "--silent",
                    "--location",
                    "--compressed",
                    "--head",
                    "--max-time",
                    "120",
                    "--user-agent",
                    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/118.0.0.0 Safari/537.36 ArchiveBox/0.7.4 (+https://github.com/ArchiveBox/ArchiveBox/) curl/curl 8.14.1 (x86_64-pc-linux-gnu)",
                    "https://inference-docs.cerebras.ai/models/overview"
                ],
                "cmd_version": "curl 8.14.1 (x86_64-pc-linux-gnu)",
                "end_ts": "2026-09-03T22:07:22.152546+00:00",
                "index_texts": null,
                "output": "headers.json",
                "pwd": "/data/archive/1788473181.478047",
                "schema": "ArchiveResult",
                "start_ts": "2026-09-03T22:07:21.741706+00:00",
                "status": "succeeded"
            }
        ],
        "htmltotext": [],
        "media": [],
        "mercury": [
            {
                "cmd": [
                    "/app/node_modules/@postlight/parser/cli.js",
                    "https://inference-docs.cerebras.ai/models/overview"
                ],
                "cmd_version": "1.0.0",
                "end_ts": "2026-09-03T22:07:40.632608+00:00",
                "index_texts": null,
                "output": "mercury",
                "pwd": "/data/archive/1788473181.478047",
                "schema": "ArchiveResult",
                "start_ts": "2026-09-03T22:07:36.736600+00:00",
                "status": "succeeded"
            }
        ],
        "pdf": [],
        "readability": [
            {
                "cmd": [
                    "/app/node_modules/readability-extractor/readability-extractor",
                    "/tmp/tmpm2ne4doy",
                    "https://inference-docs.cerebras.ai/models/overview"
                ],
                "cmd_version": "0.0.11",
                "end_ts": "2026-09-03T22:07:36.729158+00:00",
                "index_texts": [
                    "Model CatalogBrowse all models available on Cerebras public endpoints.Models on Cerebras public endpoints are available on the free trial and pay-as-you-go tiers, subject to rate limits and pricing. For additional model families, reserved capacity, higher throughput, and production SLAs, see Dedicated Endpoints.\nAvailable Models\n\n\nModel Compression\nThis section provides transparency about the compression state of each model available on our platform.\nWe host a variety of open-source models from the community. We do not currently host pruned models on our public endpoints. All models served through our public endpoints are the original, unpruned versions.\nWhile we conduct research on pruning techniques like REAP (Router-weighted Expert Activation Pruning), these pruned models are shared with the research community on Hugging Face but are not available through our shared API. You can read more about REAP in our research blog. All of our public models are unpruned.\nCerebras uses selective weight-only quantization only during storage to preserve maximal quality. This means that the weights are stored in partial 16-bit / 8-bit / 4-bit, in-line with industry standards. For quality, sensitive layers are stored at full precision with dequantization on the fly, so operations are done in high precision. The activations, attention, and kv cache remain in full precision and unquantized.Frequently Asked Questions\nWill you change a model's architecture without notice?No. We are committed to serving the original models for all existing endpoints, without modification. We do not alter model architectures via pruning on our hosted portfolio. If we explore additional compression techniques (like pruning) in the future, these would be offered as separate endpoints with pruning-specific names, ensuring complete transparency and allowing you to choose which version best fits your needs.\nWhere can I find your REAP pruned models?Our REAP pruned models are available on Hugging Face for research and experimentation purposes: Cerebras REAP Collection. These models demonstrate our pruning research but are not served through our production API.\nWhat are compression, quantization, and pruning?Compression is an umbrella term for techniques that reduce model size or computational requirements. Common compression techniques include:\nQuantization: Reducing the precision of numbers used to represent model weights (e.g., converting from FP16 to FP8). This reduces memory usage without changing the model\u2019s architecture.\nPruning: Permanently removing parts of a model, like layers or experts, to reduce model size. This changes the model\u2019s architecture and creates a different model."
                ],
                "output": "readability",
                "pwd": "/data/archive/1788473181.478047",
                "schema": "ArchiveResult",
                "start_ts": "2026-09-03T22:07:34.243965+00:00",
                "status": "succeeded"
            }
        ],
        "screenshot": [],
        "singlefile": [],
        "title": [
            {
                "cmd": [
                    "curl",
                    "--silent",
                    "--location",
                    "--compressed",
                    "--max-time",
                    "120",
                    "--user-agent",
                    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/118.0.0.0 Safari/537.36 ArchiveBox/0.7.4 (+https://github.com/ArchiveBox/ArchiveBox/) curl/curl 8.14.1 (x86_64-pc-linux-gnu)",
                    "https://inference-docs.cerebras.ai/models/overview"
                ],
                "cmd_version": "curl 8.14.1 (x86_64-pc-linux-gnu)",
                "end_ts": "2026-09-03T22:07:34.235947+00:00",
                "index_texts": null,
                "output": "Model Catalog - Cerebras Inference",
                "pwd": "/data/archive/1788473181.478047",
                "schema": "ArchiveResult",
                "start_ts": "2026-09-03T22:07:34.201184+00:00",
                "status": "succeeded"
            }
        ],
        "wget": [
            {
                "cmd": [
                    "wget",
                    "--no-verbose",
                    "--adjust-extension",
                    "--convert-links",
                    "--force-directories",
                    "--backup-converted",
                    "--span-hosts",
                    "--no-parent",
                    "-e",
                    "robots=off",
                    "--timeout=120",
                    "--restrict-file-names=windows",
                    "--warc-file=/data/archive/1788473181.478047/warc/1788473242",
                    "--page-requisites",
                    "--user-agent=Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/118.0.0.0 Safari/537.36 ArchiveBox/0.7.4 (+https://github.com/ArchiveBox/ArchiveBox/) wget/GNU Wget 1.21.3",
                    "--compression=auto",
                    "https://inference-docs.cerebras.ai/models/overview"
                ],
                "cmd_version": "GNU Wget 1.21.3",
                "end_ts": "2026-09-03T22:07:34.190812+00:00",
                "index_texts": null,
                "output": "inference-docs.cerebras.ai/models/overview.html",
                "pwd": "/data/archive/1788473181.478047",
                "schema": "ArchiveResult",
                "start_ts": "2026-09-03T22:07:22.163661+00:00",
                "status": "succeeded"
            }
        ]
    },
    "icons": null,
    "is_archived": true,
    "is_static": false,
    "latest": {
        "archive_org": null,
        "dom": null,
        "favicon": "favicon.ico",
        "git": null,
        "media": null,
        "pdf": null,
        "screenshot": null,
        "singlefile": null,
        "title": "Model Catalog - Cerebras Inference",
        "warc": null,
        "wget": "inference-docs.cerebras.ai/models/overview.html"
    },
    "link_dir": "/data/archive/1788473181.478047",
    "newest_archive_date": "2026-09-03T22:07:36.736600+00:00",
    "num_failures": 0,
    "num_outputs": 6,
    "oldest_archive_date": "2026-09-03T22:07:21.346626+00:00",
    "path": "/models/overview",
    "schema": "Link",
    "scheme": "https",
    "snapshot_id": "e59aa07d-8105-40d7-85fe-657d0dae9969",
    "sources": [
        "/data/sources/1788473181-import.txt"
    ],
    "tags": null,
    "tags_str": "",
    "timestamp": "1788473181.478047",
    "title": "Model Catalog - Cerebras Inference",
    "updated": "2026-09-03T22:07:21.346162+00:00",
    "updated_date": "2026-09-03 22:07",
    "url": "https://inference-docs.cerebras.ai/models/overview"
}