[
  {
    "id": "deepinfra-docs-1",
    "tier": "claimed-docs",
    "url": "https://deepinfra.com/docs",
    "excerpt": "Point your existing OpenAI SDK to `https://api.deepinfra.com/v1/openai` and your code works without changes. No migration required.",
    "fetchedAt": "2026-09-04T21:02:12.907Z"
  },
  {
    "id": "deepinfra-docs-2",
    "tier": "claimed-docs",
    "url": "https://deepinfra.com/docs/inference",
    "excerpt": "OpenAI-compatible chat completions API \u2014 just change the base URL and model name.",
    "fetchedAt": "2026-09-04T21:02:12.907Z"
  },
  {
    "id": "deepinfra-docs-3",
    "tier": "claimed-docs",
    "url": "https://deepinfra.com/docs/inference",
    "excerpt": "To create a longer conversation, include the full message history in every request. The model uses this context to provide better answers.",
    "fetchedAt": "2026-09-04T21:02:12.907Z"
  },
  {
    "id": "deepinfra-docs-4",
    "tier": "claimed-docs",
    "url": "https://deepinfra.com/docs/inference",
    "excerpt": "Priority requests get faster time-to-first-token and higher throughput during peak demand.",
    "fetchedAt": "2026-09-04T21:02:12.907Z"
  },
  {
    "id": "deepinfra-docs-5",
    "tier": "claimed-docs",
    "url": "https://deepinfra.com/docs/inference",
    "excerpt": "It\u2019s ideal for non-production or lower-priority tasks such as model evaluations, data enrichment, and asynchronous workloads.",
    "fetchedAt": "2026-09-04T21:02:12.907Z"
  },
  {
    "id": "deepinfra-docs-6",
    "tier": "claimed-docs",
    "url": "https://deepinfra.com/docs/inference",
    "excerpt": "Set the optional `fail_fast` parameter to `true` to get an immediate HTTP 429 instead of waiting.",
    "fetchedAt": "2026-09-04T21:02:12.907Z"
  },
  {
    "id": "deepinfra-docs-7",
    "tier": "claimed-docs",
    "url": "https://deepinfra.com/docs/inference",
    "excerpt": "Controls reasoning depth for reasoning models. See [Reasoning Models](/chat/reasoning).",
    "fetchedAt": "2026-09-04T21:02:12.907Z"
  },
  {
    "id": "deepinfra-docs-8",
    "tier": "claimed-docs",
    "url": "https://deepinfra.com/docs",
    "excerpt": "Run your own fine-tuned LLM on A100 / H100 / H200 / B200 / B300 with autoscaling.",
    "fetchedAt": "2026-09-04T21:02:12.907Z"
  },
  {
    "id": "deepinfra-docs-9",
    "tier": "claimed-docs",
    "url": "https://deepinfra.com/docs",
    "excerpt": "Need to run your own fine-tuned weights, or require data isolation? Deploy a dedicated instance on A100/H100/H200/B200/B300 with autoscaling and a private endpoint",
    "fetchedAt": "2026-09-04T21:02:12.907Z"
  },
  {
    "id": "deepinfra-docs-10",
    "tier": "claimed-docs",
    "url": "https://deepinfra.com/docs",
    "excerpt": "GPU Clusters for training and full control. Rent a B200 or B300 cluster with SSH access and run whatever you want.",
    "fetchedAt": "2026-09-04T21:02:12.907Z"
  },
  {
    "id": "deepinfra-docs-11",
    "tier": "claimed-docs",
    "url": "https://deepinfra.com/docs",
    "excerpt": "DeepInfra is an AI inference cloud that makes it simple to run the latest machine learning models at scale \u2014 LLMs, vision, embeddings, image generation, video generation, speech, and more.",
    "fetchedAt": "2026-09-04T21:02:12.907Z"
  },
  {
    "id": "deepinfra-docs-12",
    "tier": "claimed-docs",
    "url": "https://deepinfra.com/docs",
    "excerpt": "You only pay per token \u2014 no idle GPU time, no minimums, no seat fees.",
    "fetchedAt": "2026-09-04T21:02:12.907Z"
  },
  {
    "id": "deepinfra-docs-13",
    "tier": "claimed-docs",
    "url": "https://deepinfra.com/docs",
    "excerpt": "FLUX, Stable Diffusion, text-to-video, and more.",
    "fetchedAt": "2026-09-04T21:02:12.907Z"
  },
  {
    "id": "deepinfra-docs-14",
    "tier": "claimed-docs",
    "url": "https://deepinfra.com/docs",
    "excerpt": "Point your existing OpenAI SDK to https://api.deepinfra.com/v1/openai and your code works without changes. No migration required.",
    "fetchedAt": "2026-09-04T21:04:19.757Z"
  },
  {
    "id": "deepinfra-docs-15",
    "tier": "claimed-docs",
    "url": "https://deepinfra.com/docs/inference",
    "excerpt": "The only changes you need to make from your existing OpenAI code:\n\n1.  Set `base_url` to `https://api.deepinfra.com/v1/openai`\n2.  Set `api_key` to your DeepInfra token\n3.  Set `model` to a model from our catalog",
    "fetchedAt": "2026-09-04T21:04:19.757Z"
  },
  {
    "id": "deepinfra-docs-16",
    "tier": "claimed-docs",
    "url": "https://deepinfra.com/docs/inference",
    "excerpt": "Flex inference is billed at a 20% discount off the model's standard per-token price.",
    "fetchedAt": "2026-09-04T21:04:19.757Z"
  },
  {
    "id": "deepinfra-docs-17",
    "tier": "claimed-docs",
    "url": "https://deepinfra.com/docs/inference",
    "excerpt": "`reasoning_effort`\n\nControls reasoning depth for reasoning models. See [Reasoning Models](/chat/reasoning).",
    "fetchedAt": "2026-09-04T21:04:19.757Z"
  },
  {
    "id": "deepinfra-docs-18",
    "tier": "claimed-docs",
    "url": "https://deepinfra.com/docs",
    "excerpt": "Deploy Private Models\n\nRun your own fine-tuned LLM on A100 / H100 / H200 / B200 / B300 with autoscaling.",
    "fetchedAt": "2026-09-04T21:04:19.757Z"
  },
  {
    "id": "deepinfra-docs-19",
    "tier": "claimed-docs",
    "url": "https://deepinfra.com/docs",
    "excerpt": "Embeddings & Reranking\n\nState-of-the-art embedding and reranker models for search and RAG.",
    "fetchedAt": "2026-09-04T21:04:19.757Z"
  },
  {
    "id": "deepinfra-docs-20",
    "tier": "claimed-docs",
    "url": "https://deepinfra.com/docs",
    "excerpt": "Image & Video Generation\n\nFLUX, Stable Diffusion, text-to-video, and more.",
    "fetchedAt": "2026-09-04T21:04:19.757Z"
  },
  {
    "id": "deepinfra-docs-21",
    "tier": "claimed-docs",
    "url": "https://deepinfra.com/docs",
    "excerpt": "Speech recognition (Whisper) and text-to-speech models.",
    "fetchedAt": "2026-09-04T21:04:19.757Z"
  },
  {
    "id": "deepinfra-docs-22",
    "tier": "claimed-docs",
    "url": "https://deepinfra.com/docs",
    "excerpt": "Vision & OCR\n\nMultimodal models for visual understanding and document text extraction.",
    "fetchedAt": "2026-09-04T21:04:19.757Z"
  },
  {
    "id": "deepinfra-docs-23",
    "tier": "claimed-docs",
    "url": "https://deepinfra.com",
    "excerpt": "With our zero retention policy your inputs, your outputs, and your user data stay private. DeepInfra is SOC 2 and ISO 27001 certified.",
    "fetchedAt": "2026-09-04T21:04:19.757Z"
  },
  {
    "id": "deepinfra-docs-24",
    "tier": "claimed-docs",
    "url": "https://deepinfra.com",
    "excerpt": "Low pay-as-you-go pricing - no long-term contracts, no hidden fees, no surprises.",
    "fetchedAt": "2026-09-04T21:04:19.757Z"
  },
  {
    "id": "deepinfra-docs-25",
    "tier": "claimed-docs",
    "url": "https://deepinfra.com/docs/inference",
    "excerpt": "The only changes you need to make from your existing OpenAI code: Set base_url to https://api.deepinfra.com/v1/openai",
    "fetchedAt": "2026-09-04T21:06:27.342Z"
  },
  {
    "id": "deepinfra-docs-26",
    "tier": "claimed-docs",
    "url": "https://deepinfra.com/docs/inference",
    "excerpt": "Set service_tier to \"priority\" to request priority inference on supported models. Priority requests get faster time-to-first-token and higher throughput during peak demand.",
    "fetchedAt": "2026-09-04T21:06:27.342Z"
  },
  {
    "id": "deepinfra-docs-27",
    "tier": "claimed-docs",
    "url": "https://deepinfra.com/docs/inference",
    "excerpt": "Set service_tier to \"flex\" to run Chat Completions requests at a lower cost in exchange for slower response times and occasional resource unavailability.",
    "fetchedAt": "2026-09-04T21:06:27.342Z"
  },
  {
    "id": "deepinfra-docs-28",
    "tier": "claimed-docs",
    "url": "https://deepinfra.com/docs/inference",
    "excerpt": "Set the optional fail_fast parameter to true to get an immediate HTTP 429 instead of waiting.",
    "fetchedAt": "2026-09-04T21:06:27.342Z"
  },
  {
    "id": "deepinfra-docs-29",
    "tier": "claimed-docs",
    "url": "https://deepinfra.com/docs/inference",
    "excerpt": "reasoning_effort Controls reasoning depth for reasoning models. See Reasoning Models.",
    "fetchedAt": "2026-09-04T21:06:27.342Z"
  },
  {
    "id": "deepinfra-docs-30",
    "tier": "claimed-docs",
    "url": "https://deepinfra.com/docs",
    "excerpt": "Drop-in OpenAI replacement. Point your existing OpenAI SDK to https://api.deepinfra.com/v1/openai and your code works without changes.",
    "fetchedAt": "2026-09-04T21:08:21.040Z"
  },
  {
    "id": "deepinfra-docs-31",
    "tier": "claimed-docs",
    "url": "https://deepinfra.com",
    "excerpt": "Low pay-as-you-go pricing - no long-term contracts, no hidden fees, no surprises. Startup? Enterprise? We can scale.",
    "fetchedAt": "2026-09-04T21:08:21.040Z"
  },
  {
    "id": "deepinfra-comm-1",
    "tier": "community",
    "url": "https://hn.algolia.com/api/v1/items/34874029",
    "excerpt": "Because this is popular model and many people use it, you will not experience the cold-start latency most likely. But in general it is <10s.",
    "fetchedAt": "2026-09-04T21:09:44.688Z"
  },
  {
    "id": "deepinfra-probe-1",
    "tier": "probe",
    "url": "https://deepinfra.com/llms.txt",
    "excerpt": "PROBE llms.txt: HTTP 404 at https://deepinfra.com/llms.txt",
    "fetchedAt": "2026-09-04T21:10:19.417Z"
  },
  {
    "id": "deepinfra-probe-2",
    "tier": "probe",
    "url": "https://deepinfra.com/docs.md",
    "excerpt": "PROBE docs-md: HTTP 404 at https://deepinfra.com/docs.md",
    "fetchedAt": "2026-09-04T21:10:19.417Z"
  },
  {
    "id": "deepinfra-probe-3",
    "tier": "probe",
    "url": "https://deepinfra.com/openapi.json",
    "excerpt": "PROBE openapi: all candidate paths 404 (https://deepinfra.com/openapi.json, https://deepinfra.com/swagger.json, https://deepinfra.com/api/openapi.json, https://deepinfra.com/.well-known/openapi.json)",
    "fetchedAt": "2026-09-04T21:10:19.417Z"
  },
  {
    "id": "deepinfra-probe-rt-1",
    "tier": "probe",
    "url": "https://api.deepinfra.com/v1/openai/models",
    "excerpt": "PROBE models-endpoint (2026-09-04): GET https://api.deepinfra.com/v1/openai/models with NO API key returned HTTP 200 with a machine-readable catalog of 189 models \u2014 an agent can enumerate the live model list keylessly via the OpenAI-compatible models endpoint.",
    "fetchedAt": "2026-09-04T21:11:21.000Z"
  },
  {
    "id": "deepinfra-probe-rt-2",
    "tier": "probe",
    "url": "https://status.deepinfra.com",
    "excerpt": "PROBE status-page (2026-09-04): https://status.deepinfra.com returns HTTP 200 and renders a public service-status page (page body includes \"operational\").",
    "fetchedAt": "2026-09-04T21:11:21.000Z"
  }
]