🐦 Twitter Post Details

Viewing enriched Twitter post

@jerryjliu0

Fully solving document parsing includes covering every point on the Pareto curve of accuracy, cost, and latency: 1️⃣ High-accuracy parsing - requires 99%+ accuracy, price insensitive. Especially relevant in regulated industries like financial service and insurance. 2️⃣ Low cost, high volume parsing - requires inhaling a massive volume of documents as context for agents. Can run offline in a batch setting. 3️⃣Low latency and low cost parsing - these are use cases where the user is uploading a massive volume of files ad-hoc and in the agent loop (e.g. uploading 1k pdfs to claude cowork). Requires an extremely fast pass to make sense of the docs before a deeper dive LlamaParse covers the cost-accuracy modes for document OCR with our document agent harness. LiteParse, our OSS project, is designed to be in the agent loop, and can route to deeper VLM-enabled modes. I talked about this and other topics during the @aiDotEngineer talk today. Stay tuned for the slides! In the meantime, check out our full set of parsing results on ParseBench: https://t.co/PWczfhp0OX LlamaParse: https://t.co/XYZmx5TFz8 LiteParse: https://t.co/JNER0mVcB8

Media 1
Media 2

📊 Media Metadata

{
  "media": [
    {
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2072035931050426782/media_0.jpg",
      "media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2072035931050426782/media_0.jpg",
      "type": "photo",
      "filename": "media_0.jpg"
    },
    {
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2072035931050426782/media_1.jpg",
      "media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2072035931050426782/media_1.jpg",
      "type": "photo",
      "filename": "media_1.jpg"
    }
  ],
  "processed_at": "2026-07-01T06:00:49.241629",
  "pipeline_version": "2.0"
}

🔧 Raw API Response

{
  "type": "tweet",
  "id": "2072035931050426782",
  "url": "https://x.com/jerryjliu0/status/2072035931050426782",
  "twitterUrl": "https://twitter.com/jerryjliu0/status/2072035931050426782",
  "text": "Fully solving document parsing includes covering every point on the Pareto curve of accuracy, cost, and latency:\n1️⃣ High-accuracy parsing - requires 99%+ accuracy, price insensitive. Especially relevant in regulated industries like financial service and insurance.\n2️⃣ Low cost, high volume parsing - requires inhaling a massive volume of documents as context for agents. Can run offline in a batch setting.\n3️⃣Low latency and low cost parsing - these are use cases where the user is uploading a massive volume of files ad-hoc and in the agent loop (e.g. uploading 1k pdfs to claude cowork). Requires an extremely fast pass to make sense of the docs before a deeper dive\n\nLlamaParse covers the cost-accuracy modes for document OCR with our document agent harness. LiteParse, our OSS project, is designed to be in the agent loop, and can route to deeper VLM-enabled modes.\n\nI talked about this and other topics during the @aiDotEngineer talk today. Stay tuned for the slides!\n\nIn the meantime, check out our full set of parsing results on ParseBench: https://t.co/PWczfhp0OX\n\nLlamaParse: https://t.co/XYZmx5TFz8\nLiteParse: https://t.co/JNER0mVcB8",
  "source": "Twitter for iPhone",
  "retweetCount": 4,
  "replyCount": 6,
  "likeCount": 71,
  "quoteCount": 0,
  "viewCount": 4772,
  "createdAt": "Tue Jun 30 19:13:57 +0000 2026",
  "lang": "en",
  "bookmarkCount": 58,
  "isReply": false,
  "inReplyToId": null,
  "conversationId": "2072035931050426782",
  "displayTextRange": [
    0,
    279
  ],
  "inReplyToUserId": null,
  "inReplyToUsername": null,
  "author": {
    "type": "user",
    "userName": "jerryjliu0",
    "url": "https://x.com/jerryjliu0",
    "twitterUrl": "https://twitter.com/jerryjliu0",
    "id": "369777416",
    "name": "Jerry Liu",
    "isVerified": false,
    "isBlueVerified": true,
    "verifiedType": null,
    "profilePicture": "https://pbs.twimg.com/profile_images/1283610285031460864/1Q4zYhtb_normal.jpg",
    "coverPicture": "",
    "description": "",
    "location": "",
    "followers": 78396,
    "following": 1495,
    "status": "",
    "canDm": true,
    "canMediaTag": true,
    "createdAt": "Wed Sep 07 22:54:31 +0000 2011",
    "entities": {
      "description": {
        "urls": []
      },
      "url": {}
    },
    "fastFollowersCount": 0,
    "favouritesCount": 9258,
    "hasCustomTimelines": true,
    "isTranslator": false,
    "mediaCount": 1566,
    "statusesCount": 7231,
    "withheldInCountries": [],
    "affiliatesHighlightedLabel": {},
    "possiblySensitive": false,
    "pinnedTweetIds": [
      "2067679507126124858"
    ],
    "profile_bio": {
      "description": "Parsing the world's hardest PDFs @llama_index. cofounder/CEO\n\nCareers: https://t.co/EUnMNmbCtx\nEnterprise: https://t.co/Ht5jwxSrQB",
      "entities": {
        "description": {
          "urls": [
            {
              "display_url": "llamaindex.ai/careers",
              "expanded_url": "https://www.llamaindex.ai/careers",
              "indices": [
                71,
                94
              ],
              "url": "https://t.co/EUnMNmbCtx"
            },
            {
              "display_url": "llamaindex.ai/contact",
              "expanded_url": "https://www.llamaindex.ai/contact",
              "indices": [
                107,
                130
              ],
              "url": "https://t.co/Ht5jwxSrQB"
            }
          ],
          "user_mentions": [
            {
              "id_str": "",
              "indices": [
                33,
                45
              ],
              "name": "",
              "screen_name": "llama_index"
            }
          ]
        },
        "url": {
          "urls": [
            {
              "display_url": "llamaindex.ai",
              "expanded_url": "https://www.llamaindex.ai/",
              "indices": [
                0,
                23
              ],
              "url": "https://t.co/YiIfjVlzb6"
            }
          ]
        }
      }
    },
    "isAutomated": false,
    "automatedBy": null
  },
  "extendedEntities": {
    "media": [
      {
        "display_url": "pic.twitter.com/JQ4dqDdImA",
        "expanded_url": "https://twitter.com/jerryjliu0/status/2072035931050426782/photo/1",
        "ext_master_playlist_only": [],
        "ext_media_availability": {
          "status": "Available"
        },
        "ext_playlists": [],
        "features": {
          "large": {
            "faces": []
          },
          "orig": {
            "faces": []
          }
        },
        "id_str": "2072035292492754944",
        "indices": [
          280,
          303
        ],
        "media_key": "3_2072035292492754944",
        "media_results": {
          "id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAARzBWR7TGnAACgACHMFZs4AbQZ4AAA==",
          "result": {
            "__typename": "ApiMedia",
            "id": "QXBpTWVkaWE6DAABCgABHMFZHtMacAAKAAIcwVmzgBtBngAA",
            "media_key": "3_2072035292492754944"
          }
        },
        "media_url_https": "https://pbs.twimg.com/media/HMFZHtMacAAsrQW.jpg",
        "original_info": {
          "focus_rects": [
            {
              "h": 1346,
              "w": 2404,
              "x": 0,
              "y": 0
            },
            {
              "h": 1346,
              "w": 1346,
              "x": 829,
              "y": 0
            },
            {
              "h": 1346,
              "w": 1181,
              "x": 912,
              "y": 0
            },
            {
              "h": 1346,
              "w": 673,
              "x": 1166,
              "y": 0
            },
            {
              "h": 1346,
              "w": 2404,
              "x": 0,
              "y": 0
            }
          ],
          "height": 1346,
          "width": 2404
        },
        "sizes": {
          "large": {
            "h": 1147,
            "w": 2048
          }
        },
        "type": "photo",
        "url": "https://t.co/JQ4dqDdImA"
      }
    ]
  },
  "card": null,
  "place": {},
  "entities": {
    "hashtags": [],
    "symbols": [],
    "urls": [
      {
        "display_url": "parsebench.ai",
        "expanded_url": "https://www.parsebench.ai/",
        "indices": [
          1051,
          1074
        ],
        "url": "https://t.co/PWczfhp0OX"
      },
      {
        "display_url": "cloud.llamaindex.ai",
        "expanded_url": "https://cloud.llamaindex.ai/",
        "indices": [
          1088,
          1111
        ],
        "url": "https://t.co/XYZmx5TFz8"
      },
      {
        "display_url": "github.com/run-llama/lite…",
        "expanded_url": "https://github.com/run-llama/liteparse",
        "indices": [
          1123,
          1146
        ],
        "url": "https://t.co/JNER0mVcB8"
      }
    ],
    "user_mentions": [
      {
        "id_str": "1376308155626360837",
        "indices": [
          922,
          936
        ],
        "name": "AI Engineer",
        "screen_name": "aiDotEngineer"
      }
    ]
  },
  "quoted_tweet": null,
  "retweeted_tweet": null,
  "isLimitedReply": false,
  "communityInfo": null,
  "article": null
}