[
  {
    "id": "fireworks-ai-docs-1",
    "tier": "claimed-docs",
    "url": "https://docs.fireworks.ai/getting-started/introduction",
    "excerpt": "Drop-in replacement for inference and training \u2014 same API, same SFT data format",
    "fetchedAt": "2026-09-04T21:01:43.890Z"
  },
  {
    "id": "fireworks-ai-docs-2",
    "tier": "claimed-docs",
    "url": "https://docs.fireworks.ai/guides/function-calling.md",
    "excerpt": "Tool calling (also known as function calling) enables models to intelligently select and use external tools based on user input.",
    "fetchedAt": "2026-09-04T21:01:43.890Z"
  },
  {
    "id": "fireworks-ai-docs-3",
    "tier": "claimed-docs",
    "url": "https://docs.fireworks.ai/structured-responses/structured-response-formatting.md",
    "excerpt": "Structured outputs ensure model responses conform to your specified format, making them easy to parse and integrate into your application.",
    "fetchedAt": "2026-09-04T21:01:43.890Z"
  },
  {
    "id": "fireworks-ai-docs-4",
    "tier": "claimed-docs",
    "url": "https://docs.fireworks.ai/guides/batch-inference.md",
    "excerpt": "Process large volumes of requests asynchronously at 50% off Serverless per-token prices.",
    "fetchedAt": "2026-09-04T21:01:43.890Z"
  },
  {
    "id": "fireworks-ai-docs-5",
    "tier": "claimed-docs",
    "url": "https://docs.fireworks.ai/deployments/autoscaling.md",
    "excerpt": "Scale to zero when idle to minimize costs",
    "fetchedAt": "2026-09-04T21:01:43.890Z"
  },
  {
    "id": "fireworks-ai-docs-6",
    "tier": "claimed-docs",
    "url": "https://docs.fireworks.ai/serverless/overview.md",
    "excerpt": "Priority \u2014 higher reliability during peak periods. Opt in by setting service_tier: \"priority\" on chat completions.",
    "fetchedAt": "2026-09-04T21:01:43.890Z"
  },
  {
    "id": "fireworks-ai-docs-7",
    "tier": "claimed-docs",
    "url": "https://docs.fireworks.ai/models/uploading-custom-models.md",
    "excerpt": "Upload your own models from Hugging Face or elsewhere to deploy trained or custom-trained models optimized for your use case.",
    "fetchedAt": "2026-09-04T21:01:43.890Z"
  },
  {
    "id": "fireworks-ai-docs-8",
    "tier": "claimed-docs",
    "url": "https://docs.fireworks.ai/fine-tuning/deploying-loras.md",
    "excerpt": "Live merge is the simplest way to deploy a trained model. Fireworks automatically merges the LoRA weights into the base model at deployment time",
    "fetchedAt": "2026-09-04T21:01:43.890Z"
  },
  {
    "id": "fireworks-ai-docs-9",
    "tier": "claimed-docs",
    "url": "https://docs.fireworks.ai/deployments/benchmarking.md",
    "excerpt": "Use our open-source benchmarking tool to measure and optimize your deployment's performance",
    "fetchedAt": "2026-09-04T21:01:43.890Z"
  },
  {
    "id": "fireworks-ai-docs-10",
    "tier": "claimed-docs",
    "url": "https://docs.fireworks.ai/getting-started/introduction",
    "excerpt": "Boost model quality with supervised and reinforcement fine-tuning of models up to 1T+ parameters.",
    "fetchedAt": "2026-09-04T21:01:43.890Z"
  },
  {
    "id": "fireworks-ai-docs-11",
    "tier": "claimed-docs",
    "url": "https://fireworks.ai",
    "excerpt": "A drop-in replacement for closed-model APIs. Route to the best open or closed model for every task, and cut your AI coding spend 50 to 75%.",
    "fetchedAt": "2026-09-04T21:01:43.890Z"
  },
  {
    "id": "fireworks-ai-docs-12",
    "tier": "claimed-docs",
    "url": "https://fireworks.ai",
    "excerpt": "Get instant access to the most popular OSS models, optimized for cost, speed, and quality.",
    "fetchedAt": "2026-09-04T21:01:43.890Z"
  },
  {
    "id": "fireworks-ai-docs-13",
    "tier": "claimed-docs",
    "url": "https://docs.fireworks.ai/serverless/overview.md",
    "excerpt": "Optional sticky-routing key. Pin repeated requests to the same replica to maximize prompt-cache hit rate.",
    "fetchedAt": "2026-09-04T21:01:43.890Z"
  },
  {
    "id": "fireworks-ai-docs-14",
    "tier": "claimed-docs",
    "url": "https://docs.fireworks.ai/guides/ondemand-deployments.md",
    "excerpt": "Better performance \u2013 Lower latency, higher throughput, and predictable performance unaffected by other users",
    "fetchedAt": "2026-09-04T21:01:43.890Z"
  },
  {
    "id": "fireworks-ai-docs-15",
    "tier": "claimed-docs",
    "url": "https://docs.fireworks.ai/getting-started/introduction",
    "excerpt": "Migrate from OpenAI: Drop-in replacement for inference and training \u2014 same API, same SFT data format",
    "fetchedAt": "2026-09-04T21:03:38.255Z"
  },
  {
    "id": "fireworks-ai-docs-16",
    "tier": "claimed-docs",
    "url": "https://fireworks.ai",
    "excerpt": "Run the latest open models with a single line of code",
    "fetchedAt": "2026-09-04T21:03:38.255Z"
  },
  {
    "id": "fireworks-ai-docs-17",
    "tier": "claimed-docs",
    "url": "https://docs.fireworks.ai/serverless/overview.md",
    "excerpt": "You point your client at `api.fireworks.ai`, send tokens, and pay only for what you use \u2014 no GPUs to size, no autoscaler to tune, no cold starts to wait through.",
    "fetchedAt": "2026-09-04T21:03:38.255Z"
  },
  {
    "id": "fireworks-ai-docs-18",
    "tier": "claimed-docs",
    "url": "https://docs.fireworks.ai/serverless/overview.md",
    "excerpt": "Priority \u2014 higher reliability during peak periods. Opt in by setting `service_tier: \"priority\"` on chat completions.",
    "fetchedAt": "2026-09-04T21:03:38.255Z"
  },
  {
    "id": "fireworks-ai-docs-19",
    "tier": "claimed-docs",
    "url": "https://docs.fireworks.ai/structured-responses/structured-response-formatting.md",
    "excerpt": "Force model output to conform to a JSON schema",
    "fetchedAt": "2026-09-04T21:03:38.255Z"
  },
  {
    "id": "fireworks-ai-docs-20",
    "tier": "claimed-docs",
    "url": "https://docs.fireworks.ai/guides/batch-inference.md",
    "excerpt": "Process large volumes of requests asynchronously at **50% off** Serverless per-token prices.",
    "fetchedAt": "2026-09-04T21:03:38.255Z"
  },
  {
    "id": "fireworks-ai-docs-21",
    "tier": "claimed-docs",
    "url": "https://docs.fireworks.ai/guides/ondemand-deployments.md",
    "excerpt": "On-demand deployments give you dedicated GPUs for your models, providing several advantages over serverless: **Better performance**...**No hard rate limits**",
    "fetchedAt": "2026-09-04T21:03:38.255Z"
  },
  {
    "id": "fireworks-ai-docs-22",
    "tier": "claimed-docs",
    "url": "https://docs.fireworks.ai/deployments/benchmarking.md",
    "excerpt": "Fireworks Benchmark Tool: Use our open-source benchmarking tool to measure and optimize your deployment's performance",
    "fetchedAt": "2026-09-04T21:03:38.255Z"
  },
  {
    "id": "fireworks-ai-docs-23",
    "tier": "claimed-docs",
    "url": "https://docs.fireworks.ai/fine-tuning/deploying-loras.md",
    "excerpt": "Deploy your LoRA trained model with a single command: firectl deployment create \"accounts//models/\"",
    "fetchedAt": "2026-09-04T21:03:38.255Z"
  },
  {
    "id": "fireworks-ai-docs-24",
    "tier": "claimed-docs",
    "url": "https://docs.fireworks.ai/fine-tuning/deploying-loras.md",
    "excerpt": "Multi-LoRA: Base model is deployed with addon support; LoRA adapters are loaded dynamically at request time",
    "fetchedAt": "2026-09-04T21:03:38.255Z"
  },
  {
    "id": "fireworks-ai-docs-25",
    "tier": "claimed-docs",
    "url": "https://docs.fireworks.ai/serverless/overview.md",
    "excerpt": "x-session-affinity: Optional sticky-routing key. Pin repeated requests to the same replica to maximize prompt-cache hit rate.",
    "fetchedAt": "2026-09-04T21:03:38.255Z"
  },
  {
    "id": "fireworks-ai-docs-26",
    "tier": "claimed-docs",
    "url": "https://docs.fireworks.ai/getting-started/introduction",
    "excerpt": "Boost model quality with supervised and reinforcement fine-tuning of models up to 1T+ parameters. Start training in minutes, deploy immediately.",
    "fetchedAt": "2026-09-04T21:03:38.255Z"
  },
  {
    "id": "fireworks-ai-docs-27",
    "tier": "claimed-docs",
    "url": "https://docs.fireworks.ai/getting-started/introduction",
    "excerpt": "Migrate from OpenAI \u2014 Drop-in replacement for inference and training \u2014 same API, same SFT data format",
    "fetchedAt": "2026-09-04T21:05:52.623Z"
  },
  {
    "id": "fireworks-ai-docs-28",
    "tier": "claimed-docs",
    "url": "https://docs.fireworks.ai/getting-started/introduction",
    "excerpt": "100+ Supported Models - Text, vision, audio, image, and embeddings",
    "fetchedAt": "2026-09-04T21:05:52.623Z"
  },
  {
    "id": "fireworks-ai-docs-29",
    "tier": "claimed-docs",
    "url": "https://docs.fireworks.ai/getting-started/introduction",
    "excerpt": "Vision Models - Analyze images and documents",
    "fetchedAt": "2026-09-04T21:05:52.623Z"
  },
  {
    "id": "fireworks-ai-docs-30",
    "tier": "claimed-docs",
    "url": "https://docs.fireworks.ai/deployments/autoscaling.md",
    "excerpt": "Set to 0 for scale-to-zero",
    "fetchedAt": "2026-09-04T21:05:52.623Z"
  },
  {
    "id": "fireworks-ai-docs-31",
    "tier": "claimed-docs",
    "url": "https://fireworks.ai",
    "excerpt": "Get a guided path. Describe the task, review the plan and cost, approve the run, and get a trained model.",
    "fetchedAt": "2026-09-04T21:05:52.623Z"
  },
  {
    "id": "fireworks-ai-docs-32",
    "tier": "claimed-docs",
    "url": "https://docs.fireworks.ai/fine-tuning/deploying-loras.md",
    "excerpt": "Fireworks supports two deployment methods for LoRA trained models: live merge and multi-LoRA.",
    "fetchedAt": "2026-09-04T21:05:52.623Z"
  },
  {
    "id": "fireworks-ai-docs-33",
    "tier": "claimed-docs",
    "url": "https://docs.fireworks.ai/models/uploading-custom-models.md",
    "excerpt": "Upload from local files or directly from S3 buckets or Azure Blob Storage",
    "fetchedAt": "2026-09-04T21:05:52.623Z"
  },
  {
    "id": "fireworks-ai-docs-34",
    "tier": "claimed-docs",
    "url": "https://docs.fireworks.ai/serverless/overview.md",
    "excerpt": "Fast \u2014 high-speed deployments for latency-sensitive workloads. Selected by switching the model ID to a Fast variant",
    "fetchedAt": "2026-09-04T21:05:52.623Z"
  },
  {
    "id": "fireworks-ai-docs-35",
    "tier": "claimed-docs",
    "url": "https://docs.fireworks.ai/getting-started/introduction",
    "excerpt": "Migrate from OpenAI Drop-in replacement for inference and training \u2014 same API, same SFT data format",
    "fetchedAt": "2026-09-04T21:07:54.098Z"
  },
  {
    "id": "fireworks-ai-docs-36",
    "tier": "claimed-docs",
    "url": "https://docs.fireworks.ai/guides/querying-text-models.md",
    "excerpt": "Fireworks provides fast, cost-effective access to leading open-source text models through OpenAI-compatible APIs.",
    "fetchedAt": "2026-09-04T21:07:54.098Z"
  },
  {
    "id": "fireworks-ai-docs-37",
    "tier": "claimed-docs",
    "url": "https://docs.fireworks.ai/getting-started/introduction",
    "excerpt": "Use embeddings & reranking in search & context retrieval",
    "fetchedAt": "2026-09-04T21:07:54.098Z"
  },
  {
    "id": "fireworks-ai-docs-38",
    "tier": "claimed-docs",
    "url": "https://docs.fireworks.ai/guides/ondemand-deployments.md",
    "excerpt": "On-demand deployments give you dedicated GPUs for your models, providing several advantages over serverless",
    "fetchedAt": "2026-09-04T21:07:54.098Z"
  },
  {
    "id": "fireworks-ai-docs-39",
    "tier": "claimed-docs",
    "url": "https://docs.fireworks.ai/fine-tuning/deploying-loras.md",
    "excerpt": "Live merge is the simplest way to deploy a trained model. Fireworks automatically merges the LoRA weights into the base model at deployment time, producing a model that performs identically to a natively trained model with no inference overhead.",
    "fetchedAt": "2026-09-04T21:07:54.098Z"
  },
  {
    "id": "fireworks-ai-comm-1",
    "tier": "community",
    "url": "https://hn.algolia.com/api/v1/items/45305173",
    "excerpt": "Fireworks AI is one of the most overpriced model hosting companies. Tried fine-tuning with 10k records SFT on gpt-oss-20b, ran for 8 mins, billed $192. Equivalent A100 time on Lambda would cost ~$0.17. Biggest markup I've seen in the industry; service is overall just mediocre.",
    "fetchedAt": "2026-09-04T21:09:19.191Z"
  },
  {
    "id": "fireworks-ai-probe-1",
    "tier": "probe",
    "url": "https://docs.fireworks.ai/llms.txt",
    "excerpt": "PROBE llms.txt: HTTP 200 at https://docs.fireworks.ai/llms.txt # Fireworks AI Docs\n\n- [Build with Fireworks AI](https://docs.fireworks.ai/getting-started/introduction.md): Fast infere",
    "fetchedAt": "2026-09-04T21:10:14.481Z"
  },
  {
    "id": "fireworks-ai-probe-2",
    "tier": "probe",
    "url": "https://docs.fireworks.ai/getting-started/introduction.md",
    "excerpt": "PROBE docs-md: HTTP 200 at https://docs.fireworks.ai/getting-started/introduction.md > ## Documentation Index\n> Fetch the complete documentation index at: https://docs.fireworks.ai/llms.txt\n> Use this file",
    "fetchedAt": "2026-09-04T21:10:14.481Z"
  },
  {
    "id": "fireworks-ai-probe-3",
    "tier": "probe",
    "url": "https://docs.fireworks.ai/openapi.json",
    "excerpt": "PROBE openapi: all candidate paths 404 (https://docs.fireworks.ai/openapi.json, https://docs.fireworks.ai/swagger.json, https://docs.fireworks.ai/api/openapi.json, https://docs.fireworks.ai/.well-known/openapi.json)",
    "fetchedAt": "2026-09-04T21:10:14.481Z"
  },
  {
    "id": "fireworks-ai-probe-rt-1",
    "tier": "probe",
    "url": "https://api.fireworks.ai/inference/v1/models",
    "excerpt": "PROBE models-endpoint (2026-09-04): GET https://api.fireworks.ai/inference/v1/models without a key returned HTTP 401 ({\"error\":{\"message\":\"You must provide an API key. See https://docs.fireworks.ai/api-reference/introduction#authenticatio) \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": "fireworks-ai-probe-rt-2",
    "tier": "probe",
    "url": "https://status.fireworks.ai",
    "excerpt": "PROBE status-page (2026-09-04): https://status.fireworks.ai returns HTTP 200 and renders a public service-status page (page body includes \"operational\").",
    "fetchedAt": "2026-09-04T21:11:21.000Z"
  }
]