[
  {
    "id": "groq-docs-1",
    "tier": "claimed-docs",
    "url": "https://console.groq.com/docs/overview",
    "excerpt": "Fast LLM inference, OpenAI-compatible. Simple to integrate, easy to scale. Start building in minutes.",
    "fetchedAt": "2026-09-04T21:01:05.823Z"
  },
  {
    "id": "groq-docs-2",
    "tier": "claimed-docs",
    "url": "https://console.groq.com/docs/openai.md",
    "excerpt": "pass your Groq API key to the `api_key` parameter and change the `base_url` to `https://api.groq.com/openai/v1`",
    "fetchedAt": "2026-09-04T21:01:05.823Z"
  },
  {
    "id": "groq-docs-3",
    "tier": "claimed-docs",
    "url": "https://console.groq.com/docs/models.md",
    "excerpt": "GPT-OSS 120B is OpenAI's flagship open-weight language model with 120 billion parameters, built in browser search and code execution, and reasoning capabilities.",
    "fetchedAt": "2026-09-04T21:01:05.823Z"
  },
  {
    "id": "groq-docs-4",
    "tier": "claimed-docs",
    "url": "https://console.groq.com/docs/structured-outputs.md",
    "excerpt": "With strict: true, the model uses constrained decoding to guarantee that the output will always match your schema exactly.",
    "fetchedAt": "2026-09-04T21:01:05.823Z"
  },
  {
    "id": "groq-docs-5",
    "tier": "claimed-docs",
    "url": "https://console.groq.com/docs/tool-use/overview.md",
    "excerpt": "Tool use (or function calling) is what transforms a language model from a conversational interface into an autonomous agent capable of taking action",
    "fetchedAt": "2026-09-04T21:01:05.823Z"
  },
  {
    "id": "groq-docs-6",
    "tier": "claimed-docs",
    "url": "https://console.groq.com/docs/tool-use/remote-mcp.md",
    "excerpt": "point to an MCP server URL and the Groq API will start using its tools without you having to implement any tool logic yourself",
    "fetchedAt": "2026-09-04T21:01:05.823Z"
  },
  {
    "id": "groq-docs-7",
    "tier": "claimed-docs",
    "url": "https://console.groq.com/docs/batch.md",
    "excerpt": "Batch processing lets you run thousands of API requests at scale by submitting your workload as an asynchronous batch of requests to Groq with 50% lower cost",
    "fetchedAt": "2026-09-04T21:01:05.823Z"
  },
  {
    "id": "groq-docs-8",
    "tier": "claimed-docs",
    "url": "https://console.groq.com/docs/service-tiers.md",
    "excerpt": "Groq offers multiple service tiers so you can tune for latency, throughput, and reliability.",
    "fetchedAt": "2026-09-04T21:01:05.823Z"
  },
  {
    "id": "groq-docs-9",
    "tier": "claimed-docs",
    "url": "https://console.groq.com/docs/flex-processing.md",
    "excerpt": "Flex processing is available for all models to paid customers only with 10x higher rate limits compared to on-demand processing.",
    "fetchedAt": "2026-09-04T21:01:05.823Z"
  },
  {
    "id": "groq-docs-10",
    "tier": "claimed-docs",
    "url": "https://console.groq.com/docs/text-chat.md",
    "excerpt": "To enable streaming, set the parameter stream=True. The completion function will then return an iterator of completion deltas",
    "fetchedAt": "2026-09-04T21:01:05.823Z"
  },
  {
    "id": "groq-docs-11",
    "tier": "claimed-docs",
    "url": "https://console.groq.com/docs/lora.md",
    "excerpt": "Upload your existing LoRA adapters to run specialized inference while maintaining the performance and efficiency of Groq's infrastructure.",
    "fetchedAt": "2026-09-04T21:01:05.823Z"
  },
  {
    "id": "groq-docs-12",
    "tier": "claimed-docs",
    "url": "https://console.groq.com/docs/billing-faqs.md",
    "excerpt": "Spend Limits: Set automated spending limits and receive budget alerts",
    "fetchedAt": "2026-09-04T21:01:05.823Z"
  },
  {
    "id": "groq-docs-13",
    "tier": "claimed-docs",
    "url": "https://console.groq.com/docs/responses-api.md",
    "excerpt": "The Responses API supports both text and image inputs while producing text outputs, stateful conversations, and function calling to connect with external systems.",
    "fetchedAt": "2026-09-04T21:01:05.823Z"
  },
  {
    "id": "groq-gh-1",
    "tier": "github",
    "url": "https://github.com/groq/groq-typescript",
    "excerpt": "Request parameters that correspond to file uploads can be passed in many different forms",
    "fetchedAt": "2026-09-04T21:01:05.823Z"
  },
  {
    "id": "groq-docs-14",
    "tier": "claimed-docs",
    "url": "https://console.groq.com/docs/text-chat.md",
    "excerpt": "Generating text with Groq's Chat Completions API enables you to have natural, conversational interactions with Groq's large language models.",
    "fetchedAt": "2026-09-04T21:03:08.699Z"
  },
  {
    "id": "groq-docs-15",
    "tier": "claimed-docs",
    "url": "https://console.groq.com/docs/text-chat.md",
    "excerpt": "To enable streaming, set the parameter `stream=True`.",
    "fetchedAt": "2026-09-04T21:03:08.699Z"
  },
  {
    "id": "groq-docs-16",
    "tier": "claimed-docs",
    "url": "https://console.groq.com/docs/structured-outputs.md",
    "excerpt": "Structured Outputs is a feature that ensures your model responses conform to your provided JSON Schema",
    "fetchedAt": "2026-09-04T21:03:08.699Z"
  },
  {
    "id": "groq-docs-17",
    "tier": "claimed-docs",
    "url": "https://console.groq.com/docs/tool-use/remote-mcp.md",
    "excerpt": "you simply point to an MCP server URL and the Groq API will start using its tools without you having to implement any tool logic yourself",
    "fetchedAt": "2026-09-04T21:03:08.699Z"
  },
  {
    "id": "groq-docs-18",
    "tier": "claimed-docs",
    "url": "https://console.groq.com/docs/flex-processing.md",
    "excerpt": "Flex Processing is a service tier optimized for high-throughput workloads that prioritizes fast inference and can handle occasional request failures.",
    "fetchedAt": "2026-09-04T21:03:08.699Z"
  },
  {
    "id": "groq-docs-19",
    "tier": "claimed-docs",
    "url": "https://console.groq.com/docs/service-tiers.md",
    "excerpt": "auto: Pass this if you dont want to think about tiers and you want to leverage the best tier available to you at any given moment.",
    "fetchedAt": "2026-09-04T21:03:08.699Z"
  },
  {
    "id": "groq-docs-20",
    "tier": "claimed-docs",
    "url": "https://console.groq.com/docs/lora.md",
    "excerpt": "With LoRA inference on Groq, you can: Run inference with your pre-made LoRA adapters",
    "fetchedAt": "2026-09-04T21:03:08.699Z"
  },
  {
    "id": "groq-gh-2",
    "tier": "github",
    "url": "https://github.com/groq/groq-typescript",
    "excerpt": "await client.audio.transcriptions.create({\n  model: 'whisper-large-v3-turbo',\n  file: fs.createReadStream('/path/to/file'),\n});",
    "fetchedAt": "2026-09-04T21:03:08.699Z"
  },
  {
    "id": "groq-docs-21",
    "tier": "claimed-docs",
    "url": "https://console.groq.com/docs/structured-outputs.md",
    "excerpt": "With `strict: true`, the model uses constrained decoding to guarantee that the output will always match your schema exactly",
    "fetchedAt": "2026-09-04T21:05:04.762Z"
  },
  {
    "id": "groq-docs-22",
    "tier": "claimed-docs",
    "url": "https://console.groq.com/docs/text-chat.md",
    "excerpt": "you can stream the model's response in real-time. This allows your application to display the response as it's being generated",
    "fetchedAt": "2026-09-04T21:05:04.762Z"
  },
  {
    "id": "groq-docs-23",
    "tier": "claimed-docs",
    "url": "https://console.groq.com/docs/responses-api.md",
    "excerpt": "Groq's Responses API is fully compatible with OpenAI's Responses API, making it easy to integrate advanced conversational AI capabilities into your applications.",
    "fetchedAt": "2026-09-04T21:05:04.762Z"
  },
  {
    "id": "groq-docs-24",
    "tier": "claimed-docs",
    "url": "https://console.groq.com/docs/billing-faqs.md",
    "excerpt": "Spend Limits:** Set automated spending limits and receive budget alerts",
    "fetchedAt": "2026-09-04T21:05:04.762Z"
  },
  {
    "id": "groq-docs-25",
    "tier": "claimed-docs",
    "url": "https://console.groq.com/docs/openai.md",
    "excerpt": "To start using Groq with OpenAI's client libraries, pass your Groq API key to the api_key parameter and change the base_url to https://api.groq.com/openai/v1",
    "fetchedAt": "2026-09-04T21:07:13.109Z"
  },
  {
    "id": "groq-docs-26",
    "tier": "claimed-docs",
    "url": "https://console.groq.com/docs/text-chat.md",
    "excerpt": "To enable streaming, set the parameter stream=True. The completion function will then return an iterator of completion deltas rather than a single, full completion.",
    "fetchedAt": "2026-09-04T21:07:13.109Z"
  },
  {
    "id": "groq-docs-27",
    "tier": "claimed-docs",
    "url": "https://console.groq.com/docs/tool-use/overview.md",
    "excerpt": "To use tools, the model must be provided with tool definitions. These tool definitions are in JSON schema format and are passed to the model via the tools parameter",
    "fetchedAt": "2026-09-04T21:07:13.109Z"
  },
  {
    "id": "groq-docs-28",
    "tier": "claimed-docs",
    "url": "https://console.groq.com/docs/tool-use/remote-mcp.md",
    "excerpt": "Groq's Responses API supports remote tool use via MCP servers via HTTPS where Groq handles all orchestration... You don't implement anything - just provide the MCP server URL and authentication.",
    "fetchedAt": "2026-09-04T21:07:13.109Z"
  },
  {
    "id": "groq-docs-29",
    "tier": "claimed-docs",
    "url": "https://console.groq.com/docs/batch.md",
    "excerpt": "Batch processing lets you run thousands of API requests at scale by submitting your workload as an asynchronous batch of requests to Groq with 50% lower cost, no impact to your standard rate limits, and 24-hour to 7 day processing window.",
    "fetchedAt": "2026-09-04T21:07:13.109Z"
  },
  {
    "id": "groq-docs-30",
    "tier": "claimed-docs",
    "url": "https://console.groq.com/docs/flex-processing.md",
    "excerpt": "Flex processing is available for all models to paid customers only with 10x higher rate limits compared to on-demand processing. Pricing matches the on-demand tier.",
    "fetchedAt": "2026-09-04T21:07:13.109Z"
  },
  {
    "id": "groq-docs-31",
    "tier": "claimed-docs",
    "url": "https://console.groq.com/docs/service-tiers.md",
    "excerpt": "Groq offers multiple service tiers so you can tune for latency, throughput, and reliability. You can distinguish these by providing the service_tier parameter.",
    "fetchedAt": "2026-09-04T21:07:13.109Z"
  },
  {
    "id": "groq-docs-32",
    "tier": "claimed-docs",
    "url": "https://console.groq.com/docs/lora.md",
    "excerpt": "Groq provides inference services for pre-made Low-Rank Adaptation (LoRA) adapters... Upload your existing LoRA adapters to run specialized inference while maintaining the performance and efficiency of Groq's infrastructure.",
    "fetchedAt": "2026-09-04T21:07:13.109Z"
  },
  {
    "id": "groq-gh-3",
    "tier": "github",
    "url": "https://github.com/groq/groq-typescript",
    "excerpt": "If you have access to Node fs we recommend using fs.createReadStream()... Or if you have the web File API you can pass a File instance",
    "fetchedAt": "2026-09-04T21:07:13.109Z"
  },
  {
    "id": "groq-comm-1",
    "tier": "community",
    "url": "https://hn.algolia.com/api/v1/items/39428880",
    "excerpt": "Incredible tool. The Mixtral 8x7B model running on their hardware did 491.40 T/s for me\u2026",
    "fetchedAt": "2026-09-04T21:09:01.859Z"
  },
  {
    "id": "groq-comm-2",
    "tier": "community",
    "url": "https://hn.algolia.com/api/v1/items/39428880",
    "excerpt": "I'm achieving consistent 450+ tokens/sec for Mixtral 8x7b 32k and ~200 tps for Llama 2 70B-4k.",
    "fetchedAt": "2026-09-04T21:09:01.859Z"
  },
  {
    "id": "groq-comm-3",
    "tier": "community",
    "url": "https://hn.algolia.com/api/v1/items/39428880",
    "excerpt": "Groq AMA: 'Unlike with graphics processors, which really need data parallelism to get good throughput, our LPU architecture allows us to deliver good throughput even at batch size 1.'",
    "fetchedAt": "2026-09-04T21:09:01.859Z"
  },
  {
    "id": "groq-comm-4",
    "tier": "community",
    "url": "https://hn.algolia.com/api/v1/items/39428880",
    "excerpt": "Groq staff: our system is deterministic, no need for waiting or queuing anywhere, and we can have very low latency interconnect between cards.",
    "fetchedAt": "2026-09-04T21:09:01.859Z"
  },
  {
    "id": "groq-comm-5",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=39428880",
    "excerpt": "Jesus that makes chatgpt and even gemini seem slow AF",
    "fetchedAt": "2026-09-04T21:09:01.859Z"
  },
  {
    "id": "groq-comm-6",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=39428880",
    "excerpt": "Very impressed with the speed. This is one of the most impressive tech demos I've ever seen in my life... surreal to see the thing spitting out tokens at such a crazy rate.",
    "fetchedAt": "2026-09-04T21:09:01.859Z"
  },
  {
    "id": "groq-comm-7",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=39428880",
    "excerpt": "Very impressive! I am even more impressed by the API pricing though - 0.27/1M tokens seems like an order of magnitude cheaper than the GPT-3.5 API.",
    "fetchedAt": "2026-09-04T21:09:01.859Z"
  },
  {
    "id": "groq-comm-8",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=39428880",
    "excerpt": "The main problem with the Groq LPUs is they don't have any HBM at all, just 230 MiB of SRAM, meaning you need ~256 LPUs (4 full server racks) to serve a single model, versus a single H200.",
    "fetchedAt": "2026-09-04T21:09:01.859Z"
  },
  {
    "id": "groq-comm-9",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=39428880",
    "excerpt": "However, the hardware requirements and cost make this inaccessible for anyone but large companies.",
    "fetchedAt": "2026-09-04T21:09:01.859Z"
  },
  {
    "id": "groq-comm-10",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=39428880",
    "excerpt": "Switching the model between Mixtral and Llama I get word for word the same responses. Is this expected?",
    "fetchedAt": "2026-09-04T21:09:01.859Z"
  },
  {
    "id": "groq-comm-11",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=39428880",
    "excerpt": "I asked it to generate a large prime and it got stuck in a repetitive loop, printing the same digit pattern over and over; further testing with 1024-bit prime requests also caused odd repetitive loops.",
    "fetchedAt": "2026-09-04T21:09:01.859Z"
  },
  {
    "id": "groq-comm-12",
    "tier": "community",
    "url": "https://hn.algolia.com/api/v1/items/48364620",
    "excerpt": "My company had a really terrible experience trying to use Groq, and I would NOT recommend anyone use their service if you need reliability. So many random errors, so many silly quirks.",
    "fetchedAt": "2026-09-04T21:09:01.859Z"
  },
  {
    "id": "groq-comm-13",
    "tier": "community",
    "url": "https://hn.algolia.com/api/v1/items/48364620",
    "excerpt": "There's a trail of complaints going back years now, and they rounded out the bottom of Kimi's verification program. Groq hosted models were/are always worse than traditional hosts.",
    "fetchedAt": "2026-09-04T21:09:01.859Z"
  },
  {
    "id": "groq-comm-14",
    "tier": "community",
    "url": "https://hn.algolia.com/api/v1/items/48364620",
    "excerpt": "I don't really get the value proposition of groq as a user, the performance is really poor for the token price.",
    "fetchedAt": "2026-09-04T21:09:01.859Z"
  },
  {
    "id": "groq-comm-15",
    "tier": "community",
    "url": "https://hn.algolia.com/api/v1/items/48364620",
    "excerpt": "I wanted to use Kimi K2 fast for coding and Groq was the only fast provider at the time... Definitely recommend cerebras tho now that groq's been eaten up from inside basically.",
    "fetchedAt": "2026-09-04T21:09:01.859Z"
  },
  {
    "id": "groq-comm-16",
    "tier": "community",
    "url": "https://hn.algolia.com/api/v1/items/48364620",
    "excerpt": "As soon as i saw they switched to 'call us for quotes' for the new models, i knew they are over.",
    "fetchedAt": "2026-09-04T21:09:01.859Z"
  },
  {
    "id": "groq-comm-17",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=46379183",
    "excerpt": "I just stopped my Groq API. Sad to see competition being eaten up by shitty Nvidia. I like their products but Jensen is an absolute mfer with deceitful marketing.",
    "fetchedAt": "2026-09-04T21:09:01.859Z"
  },
  {
    "id": "groq-comm-18",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=46379183",
    "excerpt": "Damn. Was hoping Groq and Cerebras would give the giants a run for their money.",
    "fetchedAt": "2026-09-04T21:09:01.859Z"
  },
  {
    "id": "groq-probe-1",
    "tier": "probe",
    "url": "https://console.groq.com/llms.txt",
    "excerpt": "PROBE llms.txt: HTTP 200 at https://console.groq.com/llms.txt # https://console.groq.com llms.txt\n\n- [JigsawStack \ud83e\udde9](https://console.groq.com/docs/jigsawstack): The JigsawStack \ud83e\udde9 d",
    "fetchedAt": "2026-09-04T21:10:07.290Z"
  },
  {
    "id": "groq-probe-2",
    "tier": "probe",
    "url": "https://console.groq.com/docs/overview.md",
    "excerpt": "PROBE docs-md: HTTP 200 at https://console.groq.com/docs/overview.md ---\ndescription: Fast LLM inference, OpenAI-compatible. Simple to integrate, easy to scale. Start building in minutes.\nt",
    "fetchedAt": "2026-09-04T21:10:07.290Z"
  },
  {
    "id": "groq-probe-3",
    "tier": "probe",
    "url": "https://console.groq.com/openapi.json",
    "excerpt": "PROBE openapi: all candidate paths 404 (https://console.groq.com/openapi.json, https://console.groq.com/swagger.json, https://console.groq.com/api/openapi.json, https://console.groq.com/.well-known/openapi.json)",
    "fetchedAt": "2026-09-04T21:10:07.290Z"
  },
  {
    "id": "groq-probe-4",
    "tier": "probe",
    "url": "https://console.groq.com/docs/mcp",
    "excerpt": "official MCP server documented at https://console.groq.com/docs/mcp",
    "fetchedAt": "2026-09-04T21:10:07.290Z"
  },
  {
    "id": "groq-probe-rt-1",
    "tier": "probe",
    "url": "https://api.groq.com/openai/v1/models",
    "excerpt": "PROBE models-endpoint (2026-09-04): GET https://api.groq.com/openai/v1/models without a key returned HTTP 401 ({\"error\":{\"message\":\"Invalid API Key\",\"type\":\"invalid_request_error\",\"code\":\"invalid_api_key\"}}) \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": "groq-probe-rt-2",
    "tier": "probe",
    "url": "https://groqstatus.com",
    "excerpt": "PROBE status-page (2026-09-04): https://groqstatus.com returns HTTP 200 and renders a public service-status page (page body includes \"operational\").",
    "fetchedAt": "2026-09-04T21:11:21.000Z"
  }
]