[
  {
    "id": "cerebras-docs-1",
    "tier": "claimed-docs",
    "url": "https://inference-docs.cerebras.ai/quickstart",
    "excerpt": "Make your first Cerebras API call in just minutes.",
    "fetchedAt": "2026-09-04T21:02:00.914Z"
  },
  {
    "id": "cerebras-docs-2",
    "tier": "claimed-docs",
    "url": "https://inference-docs.cerebras.ai/quickstart",
    "excerpt": "Use the playground in the Cloud Console \u2014 no key or install needed.",
    "fetchedAt": "2026-09-04T21:02:00.914Z"
  },
  {
    "id": "cerebras-docs-3",
    "tier": "claimed-docs",
    "url": "https://inference-docs.cerebras.ai/resources/openai.md",
    "excerpt": "Existing applications can use Cerebras by changing the API key, base URL, and model ID.",
    "fetchedAt": "2026-09-04T21:02:00.914Z"
  },
  {
    "id": "cerebras-docs-4",
    "tier": "claimed-docs",
    "url": "https://www.cerebras.ai/inference",
    "excerpt": "OpenAI API compatibility lets developers build on Cerebras with just two code changes.",
    "fetchedAt": "2026-09-04T21:02:00.914Z"
  },
  {
    "id": "cerebras-docs-5",
    "tier": "claimed-docs",
    "url": "https://inference-docs.cerebras.ai/capabilities/streaming.md",
    "excerpt": "The Cerebras API supports streaming responses, which send messages back in chunks and display them incrementally as the model generates them.",
    "fetchedAt": "2026-09-04T21:02:00.914Z"
  },
  {
    "id": "cerebras-docs-6",
    "tier": "claimed-docs",
    "url": "https://inference-docs.cerebras.ai/capabilities/structured-outputs.md",
    "excerpt": "Structured Outputs constrains model responses to a JSON schema so applications can process generated data reliably.",
    "fetchedAt": "2026-09-04T21:02:00.914Z"
  },
  {
    "id": "cerebras-docs-7",
    "tier": "claimed-docs",
    "url": "https://inference-docs.cerebras.ai/capabilities/tool-use.md",
    "excerpt": "Tool calling, also known as tool use or function calling, lets a model request functions that your application defines.",
    "fetchedAt": "2026-09-04T21:02:00.914Z"
  },
  {
    "id": "cerebras-docs-8",
    "tier": "claimed-docs",
    "url": "https://inference-docs.cerebras.ai/capabilities/batch.md",
    "excerpt": "The Batch API lets you process groups of requests asynchronously, making it perfect for workloads where you don't need immediate results",
    "fetchedAt": "2026-09-04T21:02:00.914Z"
  },
  {
    "id": "cerebras-docs-9",
    "tier": "claimed-docs",
    "url": "https://inference-docs.cerebras.ai/dedicated/overview.md",
    "excerpt": "A dedicated endpoint is a private, provisioned instance of the Cerebras Inference service reserved exclusively for your organization.",
    "fetchedAt": "2026-09-04T21:02:00.914Z"
  },
  {
    "id": "cerebras-docs-10",
    "tier": "claimed-docs",
    "url": "https://inference-docs.cerebras.ai/dedicated/overview.md",
    "excerpt": "Deploy your custom fine-tuned models alongside standard model variants.",
    "fetchedAt": "2026-09-04T21:02:00.914Z"
  },
  {
    "id": "cerebras-docs-11",
    "tier": "claimed-docs",
    "url": "https://inference-docs.cerebras.ai/models/choose-a-model.md",
    "excerpt": "Use this guide to find the right model for your use case on Cerebras.",
    "fetchedAt": "2026-09-04T21:02:00.914Z"
  },
  {
    "id": "cerebras-docs-12",
    "tier": "claimed-docs",
    "url": "https://inference-docs.cerebras.ai/support/rate-limits.md",
    "excerpt": "Cached tokens don't count toward your uncached TPM limit, so a higher cache hit rate lets you process far more total tokens within the same uncached limit.",
    "fetchedAt": "2026-09-04T21:02:00.914Z"
  },
  {
    "id": "cerebras-docs-13",
    "tier": "claimed-docs",
    "url": "https://www.cerebras.ai/pricing",
    "excerpt": "Get started with $5 in free credits after making an account",
    "fetchedAt": "2026-09-04T21:02:00.914Z"
  },
  {
    "id": "cerebras-docs-14",
    "tier": "claimed-docs",
    "url": "https://www.cerebras.ai/pricing",
    "excerpt": "Self-serve payment starting at just $10 * 10x higher rate limits than free tier * Higher priority processing",
    "fetchedAt": "2026-09-04T21:02:00.914Z"
  },
  {
    "id": "cerebras-docs-15",
    "tier": "claimed-docs",
    "url": "https://inference-docs.cerebras.ai/resources/openai.md",
    "excerpt": "The standard OpenAI `image_url` content shape is supported. Supply the image as a base64 data URI",
    "fetchedAt": "2026-09-04T21:02:00.914Z"
  },
  {
    "id": "cerebras-docs-16",
    "tier": "claimed-docs",
    "url": "https://inference-docs.cerebras.ai/support/pricing.md",
    "excerpt": "Get access to Cerebras Inference through our partner APIs",
    "fetchedAt": "2026-09-04T21:02:00.914Z"
  },
  {
    "id": "cerebras-gh-1",
    "tier": "github",
    "url": "https://github.com/Cerebras/cerebras-cloud-sdk-node",
    "excerpt": "This SDK has a mechanism that sends a few requests to `/v1/tcp_warming` upon construction to reduce the TTFT.",
    "fetchedAt": "2026-09-04T21:02:00.914Z"
  },
  {
    "id": "cerebras-docs-17",
    "tier": "claimed-docs",
    "url": "https://inference-docs.cerebras.ai/quickstart",
    "excerpt": "pip install --upgrade cerebras_cloud_sdk",
    "fetchedAt": "2026-09-04T21:04:06.853Z"
  },
  {
    "id": "cerebras-docs-18",
    "tier": "claimed-docs",
    "url": "https://inference-docs.cerebras.ai/models/choose-a-model.md",
    "excerpt": "Find the right open-source model for your workload on Cerebras, including alternatives for Claude, GPT, and Gemini.",
    "fetchedAt": "2026-09-04T21:04:06.853Z"
  },
  {
    "id": "cerebras-docs-19",
    "tier": "claimed-docs",
    "url": "https://inference-docs.cerebras.ai/support/rate-limits.md",
    "excerpt": "a higher cache hit rate lets you process far more total tokens within the same uncached limit",
    "fetchedAt": "2026-09-04T21:04:06.853Z"
  },
  {
    "id": "cerebras-docs-20",
    "tier": "claimed-docs",
    "url": "https://www.cerebras.ai/pricing",
    "excerpt": "Self-serve payment starting at just $10 ... 10x higher rate limits than free tier ... Higher priority processing",
    "fetchedAt": "2026-09-04T21:04:06.853Z"
  },
  {
    "id": "cerebras-gh-2",
    "tier": "github",
    "url": "https://github.com/Cerebras/cerebras-cloud-sdk-node",
    "excerpt": "This library provides convenient access to the Cerebras REST API from server-side TypeScript or JavaScript.",
    "fetchedAt": "2026-09-04T21:04:06.853Z"
  },
  {
    "id": "cerebras-docs-21",
    "tier": "claimed-docs",
    "url": "https://inference-docs.cerebras.ai/models/overview.md",
    "excerpt": "Browse all models available on Cerebras public endpoints.",
    "fetchedAt": "2026-09-04T21:06:16.322Z"
  },
  {
    "id": "cerebras-docs-22",
    "tier": "claimed-docs",
    "url": "https://inference-docs.cerebras.ai/support/rate-limits.md",
    "excerpt": "Improving your cache hit rate lets the same uncached limit serve significantly more total tokens",
    "fetchedAt": "2026-09-04T21:06:16.322Z"
  },
  {
    "id": "cerebras-gh-3",
    "tier": "github",
    "url": "https://github.com/Cerebras/cerebras-cloud-sdk-node",
    "excerpt": "Build commercially with high throughput",
    "fetchedAt": "2026-09-04T21:06:16.322Z"
  },
  {
    "id": "cerebras-docs-23",
    "tier": "claimed-docs",
    "url": "https://www.cerebras.ai/inference",
    "excerpt": "OpenAI API compatibility lets developers build on Cerebras with just two code changes.\u200b",
    "fetchedAt": "2026-09-04T21:08:10.872Z"
  },
  {
    "id": "cerebras-docs-24",
    "tier": "claimed-docs",
    "url": "https://inference-docs.cerebras.ai/dedicated/overview.md",
    "excerpt": "Your endpoint runs on reserved capacity that is not shared with other customers, so your performance is never impacted by other workloads.",
    "fetchedAt": "2026-09-04T21:08:10.872Z"
  },
  {
    "id": "cerebras-docs-25",
    "tier": "claimed-docs",
    "url": "https://www.cerebras.ai/inference",
    "excerpt": "Get started with $5 in free credit after creating an account. Prototype prompts, agents, and real-time apps before you spend a dollar.",
    "fetchedAt": "2026-09-04T21:08:10.872Z"
  },
  {
    "id": "cerebras-docs-26",
    "tier": "claimed-docs",
    "url": "https://www.cerebras.ai/pricing",
    "excerpt": "10x higher rate limits than free tier",
    "fetchedAt": "2026-09-04T21:08:10.872Z"
  },
  {
    "id": "cerebras-comm-1",
    "tier": "community",
    "url": "https://hn.algolia.com/api/v1/items/49554520",
    "excerpt": "I used their Coding Plan for a few months. It is genuinely difficult to keep up with the models. The output is so fast. Qwen 3.8 27B is likely one of the strongest models they've hosted so far.",
    "fetchedAt": "2026-09-04T21:09:39.952Z"
  },
  {
    "id": "cerebras-comm-2",
    "tier": "community",
    "url": "https://hn.algolia.com/api/v1/items/49554520",
    "excerpt": "I really wish they had their customer support somewhere else than Discord, which seems to think I'm a bot and doesn't accept my email or phone number",
    "fetchedAt": "2026-09-04T21:09:39.952Z"
  },
  {
    "id": "cerebras-comm-3",
    "tier": "community",
    "url": "https://hn.algolia.com/api/v1/items/49554520",
    "excerpt": "support@ replied and said my email domain is on their blacklist. It was just me (and I've resolved it) - onboarding fell into a redirect loop when creating an account.",
    "fetchedAt": "2026-09-04T21:09:39.952Z"
  },
  {
    "id": "cerebras-comm-4",
    "tier": "community",
    "url": "https://hn.algolia.com/api/v1/items/49554520",
    "excerpt": "Noticed they are present in OpenRouter, but Qwen 3.8 is not there yet... the context size they allow for Qwen is just 128k. Still interesting as a specialized sub-agent but not really well suited for long tasks.",
    "fetchedAt": "2026-09-04T21:09:39.952Z"
  },
  {
    "id": "cerebras-comm-5",
    "tier": "community",
    "url": "https://hn.algolia.com/api/v1/items/49554520",
    "excerpt": "apologies we just got a sudden burst of new users and traffic, it's scaling up now.",
    "fetchedAt": "2026-09-04T21:09:39.952Z"
  },
  {
    "id": "cerebras-comm-6",
    "tier": "community",
    "url": "https://hn.algolia.com/api/v1/items/49554520",
    "excerpt": "The DFlash2 draft model we're using was trained on a lot of code, so if you use it in a coding agent you'll probably notice it run a lot faster (we've seen it break 300 tok/s).",
    "fetchedAt": "2026-09-04T21:09:39.952Z"
  },
  {
    "id": "cerebras-comm-7",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=42178761",
    "excerpt": "This is astonishingly fast. I'm struggling to get over 100 tok/s on my own Llama 3.1 70b implementation on an 8x H100 cluster.",
    "fetchedAt": "2026-09-04T21:09:39.952Z"
  },
  {
    "id": "cerebras-comm-8",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=42178761",
    "excerpt": "They have a waitlist for trying their API. You have to be a bit skeptical when a company makes claims but does not offer their services to buy.",
    "fetchedAt": "2026-09-04T21:09:39.952Z"
  },
  {
    "id": "cerebras-comm-9",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=42178761",
    "excerpt": "This gets tons of press and discussion here on HN, but frankly AMD has a better overall product... companies like Cerebras are trying to compete on a single usecase and doing a poor job of it because they can only offer a tightly controlled API.",
    "fetchedAt": "2026-09-04T21:09:39.952Z"
  },
  {
    "id": "cerebras-comm-10",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=44762959",
    "excerpt": "It generates code faster than I can inspect it. In other words, it's needlessly fast.",
    "fetchedAt": "2026-09-04T21:09:39.952Z"
  },
  {
    "id": "cerebras-comm-11",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=44762959",
    "excerpt": "It hits the request per minute limit instantly and then you wait a minute. (API Error: 422 ... wrong_api_format when integrating with claude-code-router)",
    "fetchedAt": "2026-09-04T21:09:39.952Z"
  },
  {
    "id": "cerebras-comm-12",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=44762959",
    "excerpt": "I've been waiting on this for a LONG time. Integration with Cursor when Cerebras released their earlier models was patchy at best, even through openrouter. It's nice to finally see official support.",
    "fetchedAt": "2026-09-04T21:09:39.952Z"
  },
  {
    "id": "cerebras-comm-13",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=41369705",
    "excerpt": "It's insanely fast. Here's an AI voice assistant I built that uses it: cerebras.vercel.app",
    "fetchedAt": "2026-09-04T21:09:39.952Z"
  },
  {
    "id": "cerebras-comm-14",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=41369705",
    "excerpt": "Ok that speed's fucking ridiculous are you kidding me?!?!?! I just tried the Chat trial wtf.",
    "fetchedAt": "2026-09-04T21:09:39.952Z"
  },
  {
    "id": "cerebras-comm-15",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=41941883",
    "excerpt": "Damn, that's some impressive speeds. At that rate it doesn't matter if the first try resulted in an unwanted answer, you'll be able to run once or twice more in fast succession.",
    "fetchedAt": "2026-09-04T21:09:39.952Z"
  },
  {
    "id": "cerebras-comm-16",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=41941883",
    "excerpt": "Here's a video of that running, it's very speedy - used llm-cerebras plugin with an API key from cloud.cerebras.ai, no waiting list needed at the time.",
    "fetchedAt": "2026-09-04T21:09:39.952Z"
  },
  {
    "id": "cerebras-comm-17",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=41369586",
    "excerpt": "Very interested in playing with their hardware and cloud. Also I wonder if it's possible to try cloud without contacting their sales.",
    "fetchedAt": "2026-09-04T21:09:39.952Z"
  },
  {
    "id": "cerebras-probe-1",
    "tier": "probe",
    "url": "https://inference-docs.cerebras.ai/llms.txt",
    "excerpt": "PROBE llms.txt: HTTP 200 at https://inference-docs.cerebras.ai/llms.txt # Cerebras Inference\n\n- [Quickstart](https://inference-docs.cerebras.ai/quickstart.md): Make your first Cerebras API cal",
    "fetchedAt": "2026-09-04T21:10:19.051Z"
  },
  {
    "id": "cerebras-probe-2",
    "tier": "probe",
    "url": "https://inference-docs.cerebras.ai/quickstart.md",
    "excerpt": "PROBE docs-md: HTTP 200 at https://inference-docs.cerebras.ai/quickstart.md > ## Documentation Index\n> Fetch the complete documentation index at: https://inference-docs.cerebras.ai/llms.txt\n> Use",
    "fetchedAt": "2026-09-04T21:10:19.051Z"
  },
  {
    "id": "cerebras-probe-3",
    "tier": "probe",
    "url": "https://inference-docs.cerebras.ai/openapi.json",
    "excerpt": "PROBE openapi: all candidate paths 404 (https://inference-docs.cerebras.ai/openapi.json, https://inference-docs.cerebras.ai/swagger.json, https://inference-docs.cerebras.ai/api/openapi.json, https://inference-docs.cerebras.ai/.well-known/openapi.json)",
    "fetchedAt": "2026-09-04T21:10:19.051Z"
  },
  {
    "id": "cerebras-probe-rt-1",
    "tier": "probe",
    "url": "https://api.cerebras.ai/v1/models",
    "excerpt": "PROBE models-endpoint (2026-09-04): GET https://api.cerebras.ai/v1/models without a key returned HTTP 403 ({\"detail\":\"Not authenticated\"}) \u2014 the OpenAI-style models endpoint is live and speaks JSON, but enumerating the catalog requires an API key.",
    "fetchedAt": "2026-09-04T21:11:21.000Z"
  },
  {
    "id": "cerebras-probe-rt-2",
    "tier": "probe",
    "url": "https://status.cerebras.ai",
    "excerpt": "PROBE status-page (2026-09-04): https://status.cerebras.ai returns HTTP 200 and renders a public service-status page (page body includes \"operational\").",
    "fetchedAt": "2026-09-04T21:11:21.000Z"
  }
]