diff --git a/src/content/writings/en/gpt-5-6-token-station.md b/src/content/writings/en/gpt-5-6-token-station.md index ad9fc15..f579d46 100644 --- a/src/content/writings/en/gpt-5-6-token-station.md +++ b/src/content/writings/en/gpt-5-6-token-station.md @@ -80,12 +80,14 @@ For coding agents, cache accounting matters because repository context repeats. Token Station normalizes GPT-5.6 `cache_write_tokens` usage so cache writes are charged in the cache-creation bucket without double-counting them as ordinary input tokens. -A practical price frame inside Token Station: - -- GPT-5.6 Sol / `openai/gpt-5.6`: $5/M input, $30/M output, $0.50/M cached input, and $6.25/M cache writes up to 272K input tokens. -- GPT-5.6 Terra: $2.50/M input and $15/M output up to 272K input tokens. -- GPT-5.6 Luna: $1/M input and $6/M output up to 272K input tokens. -- Claude Fable 5: $10/M input, $50/M output, $1/M cache reads, $12.50/M prompt-cache writes, and $20/M one-hour cache writes. +A practical price frame inside Token Station (GPT-5.6 rates are for up to 272K input tokens): + +| Model | Input | Output | Cached input | Cache writes | +|---|---|---|---|---| +| GPT-5.6 Sol (`openai/gpt-5.6`) | $5/M | $30/M | $0.50/M | $6.25/M | +| GPT-5.6 Terra | $2.50/M | $15/M | - | - | +| GPT-5.6 Luna | $1/M | $6/M | - | - | +| Claude Fable 5 | $10/M | $50/M | $1/M cache reads | $12.50/M prompt-cache, $20/M 1-hour | Above 272K input tokens, GPT-5.6 uses a long-context tier: Sol doubles input and cached-input prices and moves output to $45/M; Terra moves to $5/M input and $22.50/M output; Luna moves to $2/M input and $9/M output. diff --git a/src/content/writings/ja/gpt-5-6-token-station.md b/src/content/writings/ja/gpt-5-6-token-station.md index 7a24f86..29e2089 100644 --- a/src/content/writings/ja/gpt-5-6-token-station.md +++ b/src/content/writings/ja/gpt-5-6-token-station.md @@ -78,12 +78,14 @@ coding agent は repository context を何度も送ります。file summaries、 Token Station は GPT-5.6 の `cache_write_tokens` を cache-creation bucket に正規化し、ordinary input tokens と二重計上しないようにします。 -実用的な価格フレーム： - -- GPT-5.6 Sol / `openai/gpt-5.6`: $5/M input、$30/M output、$0.50/M cached input、$6.25/M cache writes（272K input tokens まで）。 -- GPT-5.6 Terra: $2.50/M input、$15/M output（272K まで）。 -- GPT-5.6 Luna: $1/M input、$6/M output（272K まで）。 -- Claude Fable 5: $10/M input、$50/M output、$1/M cache reads、$12.50/M prompt-cache writes、$20/M one-hour cache writes。 +実用的な価格フレーム（GPT-5.6 の価格は 272K input tokens まで）： + +| モデル | Input | Output | Cached input | Cache writes | +|---|---|---|---|---| +| GPT-5.6 Sol（`openai/gpt-5.6`） | $5/M | $30/M | $0.50/M | $6.25/M | +| GPT-5.6 Terra | $2.50/M | $15/M | - | - | +| GPT-5.6 Luna | $1/M | $6/M | - | - | +| Claude Fable 5 | $10/M | $50/M | $1/M cache reads | $12.50/M prompt-cache、$20/M one-hour | 272K input tokens を超えると GPT-5.6 は long-context tier になります。Sol は input と cached-input が倍になり、output は $45/M。Terra は $5/M input と $22.50/M output、Luna は $2/M input と $9/M output です。 diff --git a/src/content/writings/ko/gpt-5-6-token-station.md b/src/content/writings/ko/gpt-5-6-token-station.md index 65bf8c8..0a6cdbc 100644 --- a/src/content/writings/ko/gpt-5-6-token-station.md +++ b/src/content/writings/ko/gpt-5-6-token-station.md @@ -78,12 +78,14 @@ coding agent는 repository context를 반복해서 보냅니다. file summaries, Token Station은 GPT-5.6 `cache_write_tokens`를 cache-creation bucket으로 정규화해 ordinary input tokens와 이중 계산되지 않게 합니다. -실용적인 가격 프레임: - -- GPT-5.6 Sol / `openai/gpt-5.6`: $5/M input, $30/M output, $0.50/M cached input, $6.25/M cache writes up to 272K input tokens. -- GPT-5.6 Terra: $2.50/M input, $15/M output up to 272K. -- GPT-5.6 Luna: $1/M input, $6/M output up to 272K. -- Claude Fable 5: $10/M input, $50/M output, $1/M cache reads, $12.50/M prompt-cache writes, $20/M one-hour cache writes. +실용적인 가격 프레임 (GPT-5.6 가격은 272K input tokens 이내 기준): + +| 모델 | Input | Output | Cached input | Cache writes | +|---|---|---|---|---| +| GPT-5.6 Sol (`openai/gpt-5.6`) | $5/M | $30/M | $0.50/M | $6.25/M | +| GPT-5.6 Terra | $2.50/M | $15/M | - | - | +| GPT-5.6 Luna | $1/M | $6/M | - | - | +| Claude Fable 5 | $10/M | $50/M | $1/M cache reads | $12.50/M prompt-cache, $20/M one-hour | 272K input tokens를 넘으면 GPT-5.6은 long-context tier를 사용합니다. Sol은 input과 cached-input이 두 배가 되고 output은 $45/M, Terra는 $5/M input과 $22.50/M output, Luna는 $2/M input과 $9/M output입니다. diff --git a/src/content/writings/zh/gpt-5-6-token-station.md b/src/content/writings/zh/gpt-5-6-token-station.md index 9c54619..3a04efc 100644 --- a/src/content/writings/zh/gpt-5-6-token-station.md +++ b/src/content/writings/zh/gpt-5-6-token-station.md @@ -80,12 +80,14 @@ Token Station 暴露 GPT-5.6 的关键价格类别：input、output、cached inp Token Station 会规范 GPT-5.6 的 `cache_write_tokens` 用法，让 cache write 进入 cache-creation bucket，而不是被重复算成普通 input tokens。 -Token Station 里的实用价格框架： - -- GPT-5.6 Sol / `openai/gpt-5.6`：$5/M input、$30/M output、$0.50/M cached input、$6.25/M cache writes，适用于 272K input tokens 以内。 -- GPT-5.6 Terra：$2.50/M input、$15/M output，适用于 272K input tokens 以内。 -- GPT-5.6 Luna：$1/M input、$6/M output，适用于 272K input tokens 以内。 -- Claude Fable 5：$10/M input、$50/M output、$1/M cache reads、$12.50/M prompt-cache writes、$20/M one-hour cache writes。 +Token Station 里的实用价格框架（GPT-5.6 价格适用于 272K input tokens 以内）： + +| 模型 | Input | Output | Cached input | Cache writes | +|---|---|---|---|---| +| GPT-5.6 Sol（`openai/gpt-5.6`） | $5/M | $30/M | $0.50/M | $6.25/M | +| GPT-5.6 Terra | $2.50/M | $15/M | - | - | +| GPT-5.6 Luna | $1/M | $6/M | - | - | +| Claude Fable 5 | $10/M | $50/M | $1/M cache reads | $12.50/M prompt-cache、$20/M one-hour | 超过 272K input tokens 后，GPT-5.6 使用 long-context tier：Sol 的 input 和 cached-input 价格翻倍，output 变为 $45/M；Terra 变为 $5/M input 和 $22.50/M output；Luna 变为 $2/M input 和 $9/M output。 diff --git a/src/layouts/WritingLayout.astro b/src/layouts/WritingLayout.astro index 1c62020..431dd7b 100644 --- a/src/layouts/WritingLayout.astro +++ b/src/layouts/WritingLayout.astro @@ -89,7 +89,10 @@ const dateText = new Intl.DateTimeFormat(lang === 'zh' ? 'zh-CN' : lang === 'ja' .prose img { display:block; width:100%; max-width:100%; height:auto; object-fit:contain; } .prose pre { background:#fff; border:1px solid #e4e4e7; border-radius:12px; padding:20px 24px; overflow-x:auto; margin:32px 0; max-width:100%; } .prose code { white-space:pre-wrap; overflow-wrap:anywhere; } - .prose table { display:block; max-width:100%; overflow-x:auto; border-collapse:collapse; } + .prose table { display:block; max-width:100%; overflow-x:auto; border-collapse:collapse; margin:32px 0; font-family:system-ui,sans-serif; font-size:15px; } + .prose th,.prose td { border:1px solid #e4e4e7; padding:10px 14px; text-align:left; vertical-align:top; white-space:nowrap; } + .prose th { background:#f4f4f5; font-weight:600; } + .prose tbody td:first-child,.prose td:first-child { white-space:normal; } footer { max-width:1200px; margin:0 auto; padding:48px 24px; display:flex; justify-content:space-between; gap:24px; font-family:system-ui,sans-serif; color:#71717a; } @media (max-width:1024px){ .page-grid{grid-template-columns:1fr; max-width:760px;} .sidebar-left,.sidebar-right{display:none;} } @media (max-width:640px){ body > nav{padding:0 16px;} .nav-hide-sm{display:none;} .article-header{padding-top:48px;} .prose{font-size:17px;} footer{flex-direction:column;} }