🐦 Twitter Post Details

Viewing enriched Twitter post

@omarsar0

// When Cheaper Reasoning Models End Up Costing More // The model you think is cheaper might actually cost you more. New research quantifies exactly how misleading listed API prices are. Across 8 frontier reasoning models and 9 tasks, 21.8% of model-pair comparisons exhibit pricing reversal, where the cheaper-listed model costs more in practice. The magnitude reaches up to 28x. Gemini 3 Flash is listed 78% cheaper than GPT-5.2, yet its actual cost is 22% higher. Claude Opus 4.6 is listed at 2x Gemini 3.1 Pro but actually costs 35% less. The root cause: thinking token heterogeneity. On the same query, one model may use 900% more thinking tokens. Why does it matter? Anyone choosing reasoning models for production needs to benchmark actual costs, not listed prices. Removing thinking token costs reduces ranking reversals by 70%. The authors release code and data for per-task cost auditing. Paper: https://t.co/JKdbbqes6a Learn to build effective AI agents in our academy: https://t.co/1e8RZKs4uX

Media 1
Media 2
View on Twitter

📊 Media Metadata

{
  "media": [
    {
      "type": "photo",
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2038271724937224386/media_0.jpg",
      "filename": "media_0.jpg"
    },
    {
      "type": "photo",
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2038271724937224386/media_1.png",
      "filename": "media_1.png"
    }
  ],
  "processed_at": "2026-03-29T15:21:25.169679",
  "pipeline_version": "2.0"
}

🔧 Raw API Response

{
  "type": "tweet",
  "id": "2038271724937224386",
  "url": "https://x.com/omarsar0/status/2038271724937224386",
  "twitterUrl": "https://twitter.com/omarsar0/status/2038271724937224386",
  "text": "// When Cheaper Reasoning Models End Up Costing More //\n\nThe model you think is cheaper might actually cost you more. New research quantifies exactly how misleading listed API prices are.\n\nAcross 8 frontier reasoning models and 9 tasks, 21.8% of model-pair comparisons exhibit pricing reversal, where the cheaper-listed model costs more in practice.\n\nThe magnitude reaches up to 28x.\n\nGemini 3 Flash is listed 78% cheaper than GPT-5.2, yet its actual cost is 22% higher.\n\nClaude Opus 4.6 is listed at 2x Gemini 3.1 Pro but actually costs 35% less.\n\nThe root cause: thinking token heterogeneity.\n\nOn the same query, one model may use 900% more thinking tokens.\n\nWhy does it matter?\n\nAnyone choosing reasoning models for production needs to benchmark actual costs, not listed prices.\n\nRemoving thinking token costs reduces ranking reversals by 70%. The authors release code and data for per-task cost auditing.\n\nPaper: https://t.co/JKdbbqes6a\n\nLearn to build effective AI agents in our academy: https://t.co/1e8RZKs4uX",
  "source": "Twitter for iPhone",
  "retweetCount": 2,
  "replyCount": 4,
  "likeCount": 8,
  "quoteCount": 1,
  "viewCount": 654,
  "createdAt": "Sun Mar 29 15:07:03 +0000 2026",
  "lang": "en",
  "bookmarkCount": 3,
  "isReply": false,
  "inReplyToId": null,
  "conversationId": "2038271724937224386",
  "displayTextRange": [
    0,
    276
  ],
  "inReplyToUserId": null,
  "inReplyToUsername": null,
  "author": {
    "type": "user",
    "userName": "omarsar0",
    "url": "https://x.com/omarsar0",
    "twitterUrl": "https://twitter.com/omarsar0",
    "id": "3448284313",
    "name": "elvis",
    "isVerified": false,
    "isBlueVerified": true,
    "verifiedType": null,
    "profilePicture": "https://pbs.twimg.com/profile_images/939313677647282181/vZjFWtAn_normal.jpg",
    "coverPicture": "https://pbs.twimg.com/profile_banners/3448284313/1565974901",
    "description": "",
    "location": "DAIR.AI Academy",
    "followers": 295923,
    "following": 795,
    "status": "",
    "canDm": true,
    "canMediaTag": true,
    "createdAt": "Fri Sep 04 12:59:26 +0000 2015",
    "entities": {
      "description": {
        "urls": []
      },
      "url": {}
    },
    "fastFollowersCount": 0,
    "favouritesCount": 35231,
    "hasCustomTimelines": true,
    "isTranslator": true,
    "mediaCount": 4570,
    "statusesCount": 17540,
    "withheldInCountries": [],
    "affiliatesHighlightedLabel": {},
    "possiblySensitive": false,
    "pinnedTweetIds": [
      "2038015536253272145"
    ],
    "profile_bio": {
      "description": "Building @dair_ai • Prev: Meta AI, Elastic, PhD • New AI learning portal: https://t.co/1e8RZKs4uX",
      "entities": {
        "description": {
          "hashtags": [],
          "symbols": [],
          "urls": [
            {
              "display_url": "academy.dair.ai",
              "expanded_url": "https://academy.dair.ai/",
              "indices": [
                74,
                97
              ],
              "url": "https://t.co/1e8RZKs4uX"
            }
          ],
          "user_mentions": [
            {
              "id_str": "0",
              "indices": [
                9,
                17
              ],
              "name": "",
              "screen_name": "dair_ai"
            }
          ]
        },
        "url": {
          "urls": [
            {
              "display_url": "dair.ai",
              "expanded_url": "https://www.dair.ai/",
              "indices": [
                0,
                23
              ],
              "url": "https://t.co/XQto5ypSIk"
            }
          ]
        }
      }
    },
    "isAutomated": false,
    "automatedBy": null
  },
  "extendedEntities": {
    "media": [
      {
        "display_url": "pic.twitter.com/KiDHBzCCxJ",
        "expanded_url": "https://twitter.com/omarsar0/status/2038271724937224386/photo/1",
        "ext_media_availability": {
          "status": "Available"
        },
        "features": {
          "large": {
            "faces": []
          },
          "orig": {
            "faces": []
          }
        },
        "id_str": "2038271721439170560",
        "indices": [
          277,
          300
        ],
        "media_key": "3_2038271721439170560",
        "media_results": {
          "id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAARxJZVTYGxAACgACHEllVaibIMIAAA==",
          "result": {
            "__typename": "ApiMedia",
            "id": "QXBpTWVkaWE6DAABCgABHEllVNgbEAAKAAIcSWVVqJsgwgAA",
            "media_key": "3_2038271721439170560"
          }
        },
        "media_url_https": "https://pbs.twimg.com/media/HEllVNgbEAAbN8V.jpg",
        "original_info": {
          "focus_rects": [
            {
              "h": 810,
              "w": 1446,
              "x": 0,
              "y": 0
            },
            {
              "h": 1446,
              "w": 1446,
              "x": 0,
              "y": 0
            },
            {
              "h": 1626,
              "w": 1426,
              "x": 0,
              "y": 0
            },
            {
              "h": 1626,
              "w": 813,
              "x": 202,
              "y": 0
            },
            {
              "h": 1626,
              "w": 1446,
              "x": 0,
              "y": 0
            }
          ],
          "height": 1626,
          "width": 1446
        },
        "sizes": {
          "large": {
            "h": 1626,
            "w": 1446
          }
        },
        "type": "photo",
        "url": "https://t.co/KiDHBzCCxJ"
      }
    ]
  },
  "card": null,
  "place": {},
  "entities": {
    "hashtags": [],
    "symbols": [],
    "urls": [
      {
        "display_url": "arxiv.org/abs/2603.23971",
        "expanded_url": "https://arxiv.org/abs/2603.23971",
        "indices": [
          917,
          940
        ],
        "url": "https://t.co/JKdbbqes6a"
      },
      {
        "display_url": "academy.dair.ai",
        "expanded_url": "https://academy.dair.ai/",
        "indices": [
          993,
          1016
        ],
        "url": "https://t.co/1e8RZKs4uX"
      }
    ],
    "user_mentions": []
  },
  "quoted_tweet": null,
  "retweeted_tweet": null,
  "isLimitedReply": false,
  "article": null
}