Matthew Berman Checks His Clawdbot Token Costs

A short usage check reveals unexpectedly high model spending over two days.

MBMatthew Berman登壇者 · Forward Future
チャンネル
Matthew Berman
公開日
2026年1月26日
動画
0:24
読了時間
1 分
スライド
2
原文
英語
YouTube で開く
スクロールすると動画は右下に小さくなって再生を続けます。字幕は閲覧言語に合わせて切り替わります。
閲覧言語2 言語で読めます
この記事はまだ日本語に翻訳されていないため、英語の原文を表示しています。
要約

30 秒でわかる

Matthew Berman checks his model usage during an early Clawdbot session and finds that spending and token counts are higher than he expected. He says the figures are a reminder to watch costs; the clip does not establish a typical price for other users.

  1. 1Previous-day spendingBerman says the previous day cost about $130.
  2. 2Early spending todayHe reports that the current day had already reached about $32.
  3. 3High token volumeHe points to roughly 70 million tokens on the previous day and around 25 million so far today.

ポイント

  1. Berman reports roughly $130 of model spending on the previous day.
  2. By 9:30 a.m. the next day, he says the cost had reached about $32.
  3. Token usage and costs depend on the particular models and workload.
全文

チャプターごとに整えた全文を読む

文字起こしのみ
01

A surprise usage bill

Berman reacts to his previous and current day’s costs.

Previous-day model spending
スライド 1 / 2Previous-day model spendingThe dashboard shows a breakdown of model charges for the prior day.

I check my Clawdbot-related usage and am surprised by how much it cost. I say I paid about $130 the previous day and that the current day is already up to $32. The figures prompt me to be more careful about spending; they describe my own usage, not a standard cost of the software.

02

Token usage

He compares the token volumes shown on the usage dashboard.

Token usage by model
スライド 2 / 2Token usage by modelThe dashboard shows the prior day’s token volume split across two models.

The dashboard shows roughly 70 million tokens for the previous day and about 25 million so far today, even though it is only 9:30 a.m. These are rounded figures from my usage check; costs vary with model choice, token type and workload.

同じチャンネルの記事

スライド 12 枚34:21EN
Matthew Berman· 2026年10月27日Matthew Berman Examines Anthropic’s IPO Filing, AI Growth and GovernanceMatthew Berman, Sam Altman · Forward FutureThe presenter reviews the S-1’s financial metrics, compute strategy and voting structure while questioning the tension between rapid AI development and safety.AnthropicAI Safetyエンタープライズ AI+2
スライド 6 枚25:50EN
Matthew Berman· 2026年10月24日Kimi K3.1 Pro Tested: Strong 3D Demos, Uneven Results and Competitive PricingMatthew Berman · Forward FutureMatthew Berman tests the open-weight model on coding, 3D rendering and visual explanations, then compares benchmark results and prices.Open-weight modelsBenchmarksAI cost & performance+1
スライド 2 枚32:20EN
Matthew Berman· 2026年10月23日Who Is Local AI For? The Costs, Trade-offs and a Hybrid FutureMatthew Berman · Forward FutureMatthew Berman weighs data control and independence against hardware cost, setup complexity and inference speed.Local inferenceOpen-weight modelsAI cost & performance+1
スライド 6 枚1:03:37EN
Matthew Berman· 2026年10月23日Matthew Berman’s Team Tests Kimi K3.1 on Animation, Games, and ChartsMatthew Berman, Alex, Brian · Forward FutureA live team AMA turns into an informal test of Kimi K3.1, from personal-agent workflows to motion graphics, a browser game, and a benchmark chart.コーディングエージェントGenerative media評価(Evals)+2
0:53EN
Matthew Berman· 2026年10月22日Sam Altman on AI and the Discovery of New KnowledgeSam Altman · OpenAIAltman expects progress in mathematical discovery to extend to biology, materials and energy.AI for scienceMathematicsComputational Biology+1
スライド0:22EN
Matthew Berman· 2026年10月21日A Robot Bodyguard Video Shows Dramatic Rescue ScenariosMatthew Berman · Forward FutureMatthew Berman reacts to a short robot demonstration depicting fighting and vehicle-rescue scenarios.Robotics評価(Evals)