From 0636fb5f6868d626d7b8dfab6cd55e41679027fe Mon Sep 17 00:00:00 2001 From: Hu Xiao Wei Date: Mon, 13 Jul 2026 21:35:36 +0800 Subject: [PATCH 1/6] docs(blog): add GPT-5.6 Token Station article --- posts-ja.json | 7 + posts-ko.json | 7 + posts-zh.json | 7 + posts.json | 7 + .../writings/en/gpt-5-6-token-station.md | 144 ++++++++++++++++++ .../writings/ja/gpt-5-6-token-station.md | 138 +++++++++++++++++ .../writings/ko/gpt-5-6-token-station.md | 138 +++++++++++++++++ .../writings/zh/gpt-5-6-token-station.md | 144 ++++++++++++++++++ 8 files changed, 592 insertions(+) create mode 100644 src/content/writings/en/gpt-5-6-token-station.md create mode 100644 src/content/writings/ja/gpt-5-6-token-station.md create mode 100644 src/content/writings/ko/gpt-5-6-token-station.md create mode 100644 src/content/writings/zh/gpt-5-6-token-station.md diff --git a/posts-ja.json b/posts-ja.json index 9d42e40..7b3fed1 100644 --- a/posts-ja.json +++ b/posts-ja.json @@ -1,4 +1,11 @@ [ + { + "slug": "gpt-5-6-token-station", + "title": "GPT-5.6 が Token Station に登場：coding agent のルートでそのまま試す", + "summary": "Token Station は GPT-5.6 を OpenAI-compatible API、Codex、Copilot などの coding-agent ルートでサポートしました。1 つの endpoint から Sol、Terra、Luna、Claude Fable 5 を実際の workflow で比較できます。", + "category": "model-launches", + "date": "2026-07-13" + }, { "slug": "use-any-model-in-claude-code-through-token-station", "title": "Token Station 経由で Claude Code に任意のモデルを使う", diff --git a/posts-ko.json b/posts-ko.json index 8337c62..4d9343b 100644 --- a/posts-ko.json +++ b/posts-ko.json @@ -1,4 +1,11 @@ [ + { + "slug": "gpt-5-6-token-station", + "title": "GPT-5.6이 Token Station에 추가되었습니다: coding agent route에서 바로 테스트하기", + "summary": "Token Station은 GPT-5.6을 OpenAI-compatible API, Codex, Copilot 같은 coding-agent route에서 지원합니다. 하나의 endpoint로 Sol, Terra, Luna, Claude Fable 5를 실제 workflow에서 비교할 수 있습니다.", + "category": "model-launches", + "date": "2026-07-13" + }, { "slug": "use-any-model-in-claude-code-through-token-station", "title": "Token Station을 통해 Claude Code에서 어떤 모델이든 사용하기", diff --git a/posts-zh.json b/posts-zh.json index 97a42f1..401ca44 100644 --- a/posts-zh.json +++ b/posts-zh.json @@ -1,4 +1,11 @@ [ + { + "slug": "gpt-5-6-token-station", + "title": "GPT-5.6 已接入 Token Station：在你的 coding agent 路由里直接试用", + "summary": "Token Station 现在支持 GPT-5.6，覆盖 OpenAI-compatible API、Codex 和 Copilot 等 coding-agent 路由。用一个 endpoint 比较 Sol、Terra、Luna 和 Claude Fable 5 在真实工作流里的表现。", + "category": "model-launches", + "date": "2026-07-13" + }, { "slug": "use-token-station-in-cc-switch-for-claude-desktop", "title": "在 CC Switch 里用 Token Station 配置 Claude Desktop", diff --git a/posts.json b/posts.json index cf183ed..ac885bb 100644 --- a/posts.json +++ b/posts.json @@ -1,4 +1,11 @@ [ + { + "slug": "gpt-5-6-token-station", + "title": "GPT-5.6 is now on Token Station: try it in your coding agent routes", + "summary": "Token Station now supports GPT-5.6 across OpenAI-compatible API and coding-agent routes, including Codex and Copilot surfaces. Use one endpoint to compare Sol, Terra, Luna, and Claude Fable 5 in real workflows.", + "category": "model-launches", + "date": "2026-07-13" + }, { "slug": "use-any-model-in-claude-code-through-token-station", "title": "Use any model in Claude Code through Token Station", diff --git a/src/content/writings/en/gpt-5-6-token-station.md b/src/content/writings/en/gpt-5-6-token-station.md new file mode 100644 index 0000000..49655f7 --- /dev/null +++ b/src/content/writings/en/gpt-5-6-token-station.md @@ -0,0 +1,144 @@ +--- +slug: gpt-5-6-token-station +lang: en +title: "GPT-5.6 is now on Token Station: try it in your coding agent routes" +summary: "Token Station now supports GPT-5.6 across OpenAI-compatible API and coding-agent routes, including Codex and Copilot surfaces. Use one endpoint to compare Sol, Terra, Luna, and Claude Fable 5 in real workflows." +category: model-launches +date: 2026-07-13 +cta: https://models.bytefuture.ai/intro.html +--- + +GPT-5.6 is now available on Token Station. + +For coding-agent teams, the important part is not just that a new OpenAI model family exists. The important part is that GPT-5.6 can be tested through the routes developers already use: a direct OpenAI-compatible API, OpenAI Codex-style workflows, and GitHub Copilot routes where the supported catalog exposes the model. + +That turns GPT-5.6 from a launch announcement into something you can actually route, compare, and adopt without rebuilding your agent stack. + +## What Token Station supports + +Token Station exposes the GPT-5.6 family through direct OpenAI-compatible routes: + +- `openai/gpt-5.6` +- `openai/gpt-5.6-sol` +- `openai/gpt-5.6-terra` +- `openai/gpt-5.6-luna` + +It also exposes OpenAI Codex routes: + +- `openai-codex/gpt-5.6` +- `openai-codex/gpt-5.6-sol` +- `openai-codex/gpt-5.6-terra` +- `openai-codex/gpt-5.6-luna` + +And GitHub Copilot routes where the supported catalog publishes availability: + +- `github-copilot/gpt-5.6-sol` +- `github-copilot/gpt-5.6-terra` +- `github-copilot/gpt-5.6-luna` + +The result is simple: you can test the same model family from the surface that matches your workflow instead of treating each provider interface as a separate integration project. + +## Why this matters for AI coding agents + +A coding agent is not one API call. A real session may include planning, repository search, patch generation, test repair, code review, and delegated subtasks. Those steps do not all need the same model tier. + +A practical routing pattern looks like this: + +- Use a cheaper route for exploration, triage, and repeated iteration. +- Move to a stronger route for hard reasoning, risky patches, and final review. +- Keep the endpoint stable so your harness, agent, and evaluation scripts do not need to change every time you compare a model. + +That is where Token Station helps. Model choice becomes a route name, not a new integration project. + +## Try GPT-5.6 from one endpoint + +The endpoint is the standard Token Station OpenAI-compatible API: + +```bash +curl https://models.bytefuture.ai/v1/chat/completions \ + -H "Authorization: Bearer TOKEN_STATION_API_KEY" \ + -H "Content-Type: application/json" \ + -d '{ + "model": "openai/gpt-5.6-sol", + "messages": [ + {"role": "user", "content": "Plan a safe refactor for a pricing module and list the tests to run."} + ] + }' +``` + +To try Codex routing, change the model: + +```json +{ + "model": "openai-codex/gpt-5.6-terra" +} +``` + +To try a Copilot route, use: + +```json +{ + "model": "github-copilot/gpt-5.6-luna" +} +``` + +Your application still talks to the same endpoint. The route changes; the integration stays stable. + +## GPT-5.6 Sol, Terra, and Luna + +The three named variants give teams a useful testing ladder: + +- **GPT-5.6 Sol** — the flagship route for the hardest coding-agent steps. +- **GPT-5.6 Terra** — a middle route for repeated implementation and debugging loops. +- **GPT-5.6 Luna** — a lower-cost route for exploration, triage, and subtask fan-out. + +That matters because agent workloads are uneven. A repository-wide plan, a subtle failing test, and a boilerplate file edit should not automatically use the same cost tier. + +## Pricing and cache accounting + +Token Station exposes GPT-5.6 pricing in the categories agent operators actually need to track: input, output, cached input, cache writes, and long-context tiers above 272K input tokens. + +For coding agents, cache accounting matters because repository context repeats. Agents send file summaries, diffs, test output, task state, and previous plans again and again. Prompt caching can lower repeated-context cost, but only if cache writes and cached reads are handled separately. + +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. + +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. + +## How to compare GPT-5.6 with Claude Fable 5 + +Claude Fable 5 is still a natural comparison point for long-running coding agents. It is configured in Token Station with a 1M context window and a higher $10/$50 price profile. + +GPT-5.6 brings a different operating shape: OpenAI-native routes, Codex and Copilot surfaces, and multiple price tiers in the same family. + +A simple starting point: + +- Use GPT-5.6 Sol when you want the strongest GPT-5.6 route. +- Use GPT-5.6 Terra when you want a cheaper middle route for implementation loops. +- Use GPT-5.6 Luna when you want low-cost exploration or subagent fan-out. +- Use Claude Fable 5 when you specifically want Anthropic's long-running-agent behavior and are willing to pay the higher rate. +- Compare them inside Token Station when workflow fit matters more than model-brand loyalty. + +## Azure and unavailable provider catalogs + +The integration also includes commented Azure OpenAI GPT-5.6 preview templates and support for Azure's `/openai/v1` surface through `azure_api_version = "v1"`. + +Those templates are intentionally not enabled with guessed prices. Azure GPT-5.6 meters were not published at the time of integration, so operators should fill in pricing when their Azure deployment exposes the model. + +GMI Cloud and AWS Bedrock OpenAI catalogs were not added because their public catalogs did not list GPT-5.6 support at the time. Token Station should make model routing easier, not pretend every surface supports every model on day one. + +## Try GPT-5.6 through Token Station + +If you already use Token Station, GPT-5.6 is now another route family you can test in your coding-agent workflow. + +Start with the direct OpenAI route for a simple API check. Try the Codex route for terminal coding tasks. Try the Copilot route if your workflow depends on GitHub Copilot's supported model catalog. + +Token Station gives you one place to compare those routes without rewriting your agent stack for every model launch. + +[Try Token Station](https://models.bytefuture.ai/intro.html) diff --git a/src/content/writings/ja/gpt-5-6-token-station.md b/src/content/writings/ja/gpt-5-6-token-station.md new file mode 100644 index 0000000..62be080 --- /dev/null +++ b/src/content/writings/ja/gpt-5-6-token-station.md @@ -0,0 +1,138 @@ +--- +slug: gpt-5-6-token-station +lang: ja +title: "GPT-5.6 が Token Station に登場：coding agent のルートでそのまま試す" +summary: "Token Station は GPT-5.6 を OpenAI-compatible API、Codex、Copilot などの coding-agent ルートでサポートしました。1 つの endpoint から Sol、Terra、Luna、Claude Fable 5 を実際の workflow で比較できます。" +category: model-launches +date: 2026-07-13 +cta: https://models.bytefuture.ai/intro.html +--- + +GPT-5.6 が Token Station で使えるようになりました。 + +coding-agent チームにとって重要なのは、新しい OpenAI モデルファミリーが増えたことだけではありません。重要なのは、GPT-5.6 を開発者がすでに使っているルートで試せることです。直接の OpenAI-compatible API、OpenAI Codex スタイルの workflow、そして対応 catalog が公開している GitHub Copilot ルートです。 + +つまり GPT-5.6 は単なる発表ではなく、agent stack を作り直さずに route して、比較して、採用を判断できる選択肢になります。 + +## Token Station がサポートするルート + +直接の OpenAI-compatible ルート： + +- `openai/gpt-5.6` +- `openai/gpt-5.6-sol` +- `openai/gpt-5.6-terra` +- `openai/gpt-5.6-luna` + +OpenAI Codex ルート： + +- `openai-codex/gpt-5.6` +- `openai-codex/gpt-5.6-sol` +- `openai-codex/gpt-5.6-terra` +- `openai-codex/gpt-5.6-luna` + +GitHub Copilot catalog で公開されているルート： + +- `github-copilot/gpt-5.6-sol` +- `github-copilot/gpt-5.6-terra` +- `github-copilot/gpt-5.6-luna` + +同じモデルファミリーを、自分の workflow に合う surface から試せます。 + +## AI coding agent にとって重要な理由 + +coding agent は 1 回の API call ではありません。計画、repository search、patch generation、test repair、code review、delegated subtasks などが続きます。すべての step が同じ model tier を必要とするわけではありません。 + +実用的な routing はこうです。 + +- 探索、triage、反復には安い route を使う。 +- 難しい reasoning、高リスク patch、final review では強い route に上げる。 +- endpoint を安定させ、harness、agent、evaluation scripts を毎回書き換えない。 + +Token Station ではモデル選択が route name になります。新しい integration project ではありません。 + +## 1 つの endpoint から GPT-5.6 を試す + +```bash +curl https://models.bytefuture.ai/v1/chat/completions \ + -H "Authorization: Bearer TOKEN_STATION_API_KEY" \ + -H "Content-Type: application/json" \ + -d '{ + "model": "openai/gpt-5.6-sol", + "messages": [ + {"role": "user", "content": "Plan a safe refactor for a pricing module and list the tests to run."} + ] + }' +``` + +Codex ルートを試すには model だけを変えます。 + +```json +{ + "model": "openai-codex/gpt-5.6-terra" +} +``` + +Copilot ルートなら： + +```json +{ + "model": "github-copilot/gpt-5.6-luna" +} +``` + +endpoint は同じです。変えるのは route だけです。 + +## GPT-5.6 Sol、Terra、Luna + +- **GPT-5.6 Sol** — 最も難しい coding-agent step に使う flagship route。 +- **GPT-5.6 Terra** — implementation や debugging loop に使う middle route。 +- **GPT-5.6 Luna** — exploration、triage、subtask fan-out に使う lower-cost route。 + +agent workload は均一ではないので、この tier 差は重要です。 + +## Pricing と cache accounting + +Token Station は GPT-5.6 の input、output、cached input、cache writes、そして 272K input tokens を超える long-context tier を扱います。 + +coding agent は repository context を何度も送ります。file summaries、diff、test output、task state、previous plans などです。Prompt caching はこの繰り返しコストを下げられますが、cache writes と cached reads を分けて扱う必要があります。 + +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。 + +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。 + +## Claude Fable 5 との比較 + +Claude Fable 5 は long-running coding agent の自然な比較対象です。Token Station では 1M context window と $10/$50 の高い price profile で設定されています。 + +GPT-5.6 は別の運用形を持ちます。OpenAI-native route、Codex/Copilot surface、そして同じ family 内の複数 price tier です。 + +まずはこう選べます。 + +- 最強の GPT-5.6 route が必要なら Sol。 +- implementation loop の中間 route なら Terra。 +- exploration や subagent fan-out の low-cost route なら Luna。 +- Anthropic の long-running-agent behavior を重視し、高い価格を許容するなら Claude Fable 5。 +- workflow fit が model brand より重要なら Token Station 内で比較する。 + +## Azure と未対応 catalog + +Azure OpenAI GPT-5.6 preview template と `azure_api_version = "v1"` による `/openai/v1` surface の support も含まれます。 + +ただし Azure pricing は推測で有効化していません。統合時点では Azure GPT-5.6 meter が公開されていなかったため、operator が deployment 側でモデルを公開した時点で価格を埋めるべきです。 + +GMI Cloud と AWS Bedrock OpenAI catalog は、公開 catalog に GPT-5.6 がなかったため追加していません。 + +## Token Station で GPT-5.6 を試す + +Token Station を使っているなら、GPT-5.6 は coding-agent workflow に追加できる新しい route family です。 + +direct OpenAI route で API check を行い、Codex route で terminal coding task を試し、GitHub Copilot catalog に依存する workflow なら Copilot route を試せます。 + +[Token Station を試す](https://models.bytefuture.ai/intro.html) diff --git a/src/content/writings/ko/gpt-5-6-token-station.md b/src/content/writings/ko/gpt-5-6-token-station.md new file mode 100644 index 0000000..82e0916 --- /dev/null +++ b/src/content/writings/ko/gpt-5-6-token-station.md @@ -0,0 +1,138 @@ +--- +slug: gpt-5-6-token-station +lang: ko +title: "GPT-5.6이 Token Station에 추가되었습니다: coding agent route에서 바로 테스트하기" +summary: "Token Station은 GPT-5.6을 OpenAI-compatible API, Codex, Copilot 같은 coding-agent route에서 지원합니다. 하나의 endpoint로 Sol, Terra, Luna, Claude Fable 5를 실제 workflow에서 비교할 수 있습니다." +category: model-launches +date: 2026-07-13 +cta: https://models.bytefuture.ai/intro.html +--- + +GPT-5.6을 이제 Token Station에서 사용할 수 있습니다. + +coding-agent 팀에게 중요한 점은 새로운 OpenAI 모델 패밀리가 하나 더 생겼다는 사실만이 아닙니다. 중요한 점은 GPT-5.6을 개발자가 이미 쓰는 route에서 테스트할 수 있다는 것입니다. 직접 OpenAI-compatible API, OpenAI Codex 스타일 workflow, 그리고 지원 catalog가 공개한 GitHub Copilot route입니다. + +즉 GPT-5.6은 단순한 출시 소식이 아니라, agent stack을 다시 만들지 않고 route하고 비교하고 도입을 판단할 수 있는 선택지가 됩니다. + +## Token Station이 지원하는 route + +직접 OpenAI-compatible route: + +- `openai/gpt-5.6` +- `openai/gpt-5.6-sol` +- `openai/gpt-5.6-terra` +- `openai/gpt-5.6-luna` + +OpenAI Codex route: + +- `openai-codex/gpt-5.6` +- `openai-codex/gpt-5.6-sol` +- `openai-codex/gpt-5.6-terra` +- `openai-codex/gpt-5.6-luna` + +GitHub Copilot catalog가 공개한 route: + +- `github-copilot/gpt-5.6-sol` +- `github-copilot/gpt-5.6-terra` +- `github-copilot/gpt-5.6-luna` + +같은 모델 패밀리를 workflow에 맞는 surface에서 테스트할 수 있습니다. + +## AI coding agent에 중요한 이유 + +coding agent는 API call 한 번이 아닙니다. planning, repository search, patch generation, test repair, code review, delegated subtasks가 이어집니다. 모든 step이 같은 model tier를 필요로 하지는 않습니다. + +실용적인 routing pattern은 이렇습니다. + +- exploration, triage, 반복 작업에는 더 저렴한 route를 사용합니다. +- 어려운 reasoning, 위험한 patch, final review에는 더 강한 route로 올립니다. +- endpoint를 안정적으로 유지해 harness, agent, evaluation script를 매번 바꾸지 않습니다. + +Token Station에서는 모델 선택이 route name이 됩니다. 새 integration project가 아닙니다. + +## 하나의 endpoint로 GPT-5.6 테스트 + +```bash +curl https://models.bytefuture.ai/v1/chat/completions \ + -H "Authorization: Bearer TOKEN_STATION_API_KEY" \ + -H "Content-Type: application/json" \ + -d '{ + "model": "openai/gpt-5.6-sol", + "messages": [ + {"role": "user", "content": "Plan a safe refactor for a pricing module and list the tests to run."} + ] + }' +``` + +Codex route를 시험하려면 model만 바꾸면 됩니다. + +```json +{ + "model": "openai-codex/gpt-5.6-terra" +} +``` + +Copilot route는 다음처럼 사용합니다. + +```json +{ + "model": "github-copilot/gpt-5.6-luna" +} +``` + +endpoint는 그대로입니다. 바뀌는 것은 route입니다. + +## GPT-5.6 Sol, Terra, Luna + +- **GPT-5.6 Sol** — 가장 어려운 coding-agent step에 쓰는 flagship route. +- **GPT-5.6 Terra** — implementation과 debugging loop에 쓰는 middle route. +- **GPT-5.6 Luna** — exploration, triage, subtask fan-out에 쓰는 lower-cost route. + +agent workload는 균일하지 않기 때문에 tier 차이가 중요합니다. + +## Pricing과 cache accounting + +Token Station은 GPT-5.6의 input, output, cached input, cache writes, 그리고 272K input tokens를 넘는 long-context tier를 다룹니다. + +coding agent는 repository context를 반복해서 보냅니다. file summaries, diff, test output, task state, previous plans가 계속 등장합니다. Prompt caching은 반복 context 비용을 낮출 수 있지만, cache writes와 cached reads를 분리해서 처리해야 합니다. + +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. + +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. + +## Claude Fable 5와 비교하기 + +Claude Fable 5는 long-running coding agent의 자연스러운 비교 대상입니다. Token Station에서는 1M context window와 더 높은 $10/$50 price profile로 설정되어 있습니다. + +GPT-5.6은 다른 운영 형태를 제공합니다. OpenAI-native route, Codex/Copilot surface, 그리고 같은 family 안의 여러 price tier입니다. + +시작점은 간단합니다. + +- 가장 강한 GPT-5.6 route가 필요하면 Sol. +- implementation loop의 중간 route가 필요하면 Terra. +- exploration 또는 subagent fan-out의 low-cost route가 필요하면 Luna. +- Anthropic의 long-running-agent behavior가 필요하고 더 높은 가격을 감수한다면 Claude Fable 5. +- workflow fit이 model brand보다 중요하면 Token Station 안에서 비교합니다. + +## Azure와 아직 지원하지 않는 catalog + +Azure OpenAI GPT-5.6 preview template과 `azure_api_version = "v1"` 기반 `/openai/v1` surface support도 포함됩니다. + +하지만 Azure pricing은 추측으로 활성화하지 않았습니다. 통합 시점에는 Azure GPT-5.6 meter가 공개되지 않았기 때문에, operator가 자신의 Azure deployment에서 모델을 노출할 때 pricing을 채워야 합니다. + +GMI Cloud와 AWS Bedrock OpenAI catalog는 당시 공개 catalog에 GPT-5.6이 없었기 때문에 추가하지 않았습니다. + +## Token Station에서 GPT-5.6 테스트하기 + +이미 Token Station을 사용하고 있다면 GPT-5.6은 coding-agent workflow에 추가할 수 있는 새로운 route family입니다. + +direct OpenAI route로 API check를 하고, Codex route로 terminal coding task를 테스트하고, GitHub Copilot catalog에 의존하는 workflow라면 Copilot route를 시험할 수 있습니다. + +[Token Station 사용해 보기](https://models.bytefuture.ai/intro.html) diff --git a/src/content/writings/zh/gpt-5-6-token-station.md b/src/content/writings/zh/gpt-5-6-token-station.md new file mode 100644 index 0000000..b09d096 --- /dev/null +++ b/src/content/writings/zh/gpt-5-6-token-station.md @@ -0,0 +1,144 @@ +--- +slug: gpt-5-6-token-station +lang: zh +title: "GPT-5.6 已接入 Token Station：在你的 coding agent 路由里直接试用" +summary: "Token Station 现在支持 GPT-5.6，覆盖 OpenAI-compatible API、Codex 和 Copilot 等 coding-agent 路由。用一个 endpoint 比较 Sol、Terra、Luna 和 Claude Fable 5 在真实工作流里的表现。" +category: model-launches +date: 2026-07-13 +cta: https://models.bytefuture.ai/intro.html +--- + +GPT-5.6 已经接入 Token Station。 + +对 coding-agent 团队来说，重点不只是 OpenAI 又有了一个新模型家族。重点是 GPT-5.6 可以通过开发者已经在用的 route 来测试：直接的 OpenAI-compatible API、OpenAI Codex 风格工作流，以及 GitHub Copilot 已发布支持的 route。 + +这让 GPT-5.6 不只是一个发布新闻，而是一个可以路由、比较、逐步采用的模型选择，并且不需要重建你的 agent stack。 + +## Token Station 支持什么 + +Token Station 暴露直接 OpenAI-compatible GPT-5.6 route： + +- `openai/gpt-5.6` +- `openai/gpt-5.6-sol` +- `openai/gpt-5.6-terra` +- `openai/gpt-5.6-luna` + +也暴露 OpenAI Codex route： + +- `openai-codex/gpt-5.6` +- `openai-codex/gpt-5.6-sol` +- `openai-codex/gpt-5.6-terra` +- `openai-codex/gpt-5.6-luna` + +以及 GitHub Copilot 已发布支持的 route： + +- `github-copilot/gpt-5.6-sol` +- `github-copilot/gpt-5.6-terra` +- `github-copilot/gpt-5.6-luna` + +结果很简单：你可以从匹配工作流的 surface 测试同一个模型家族，而不是把每个 provider interface 都当成一个单独集成项目。 + +## 为什么这对 AI coding agent 重要 + +Coding agent 不是一次 API 调用。真实 session 可能包括规划、搜索代码库、生成 patch、修测试、代码审查和子任务分发。这些步骤不一定需要同一个模型 tier。 + +一个实用 routing pattern 是： + +- 用更便宜的 route 做探索、triage 和反复迭代。 +- 在困难推理、高风险 patch 和最终审查时切到更强 route。 +- 保持 endpoint 稳定，让 harness、agent 和评测脚本不用每次比较模型都重写。 + +这就是 Token Station 的价值：模型选择变成 route name，而不是新的集成项目。 + +## 用一个 endpoint 试 GPT-5.6 + +Endpoint 是标准 Token Station OpenAI-compatible API： + +```bash +curl https://models.bytefuture.ai/v1/chat/completions \ + -H "Authorization: Bearer TOKEN_STATION_API_KEY" \ + -H "Content-Type: application/json" \ + -d '{ + "model": "openai/gpt-5.6-sol", + "messages": [ + {"role": "user", "content": "Plan a safe refactor for a pricing module and list the tests to run."} + ] + }' +``` + +想试 Codex route，只改 model： + +```json +{ + "model": "openai-codex/gpt-5.6-terra" +} +``` + +想试 Copilot route： + +```json +{ + "model": "github-copilot/gpt-5.6-luna" +} +``` + +应用仍然访问同一个 endpoint。变化的是 route，稳定的是集成层。 + +## GPT-5.6 Sol、Terra 和 Luna + +三个命名变体给团队一个实用测试阶梯： + +- **GPT-5.6 Sol** — 用于最难 coding-agent 步骤的旗舰 route。 +- **GPT-5.6 Terra** — 用于反复实现和 debugging loop 的中间 route。 +- **GPT-5.6 Luna** — 用于探索、triage 和 subtask fan-out 的低成本 route。 + +这很重要，因为 agent 工作负载并不均匀。全仓库计划、微妙的失败测试和样板文件修改，不应该默认使用同一个成本 tier。 + +## 价格和 cache 计费 + +Token Station 暴露 GPT-5.6 的关键价格类别：input、output、cached input、cache writes，以及 272K input tokens 以上的 long-context tier。 + +对 coding agent 来说，cache accounting 很重要，因为 repository context 会重复出现。Agent 会反复发送文件摘要、diff、测试输出、任务状态和之前的计划。Prompt caching 可以降低重复上下文成本，但前提是 cache write 和 cached read 被分开处理。 + +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。 + +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。 + +## 如何比较 GPT-5.6 和 Claude Fable 5 + +Claude Fable 5 仍然是 long-running coding agent 的自然对比对象。它在 Token Station 中配置为 1M context window，并且价格是更高的 $10/$50 profile。 + +GPT-5.6 的操作形态不同：OpenAI-native route、Codex 和 Copilot surface，以及同一模型家族里的多个价格 tier。 + +一个简单起点： + +- 想用最强 GPT-5.6 route，用 GPT-5.6 Sol。 +- 想用更便宜的中间 route 跑 implementation loop，用 GPT-5.6 Terra。 +- 想用低成本方式做探索或 subagent fan-out，用 GPT-5.6 Luna。 +- 明确想要 Anthropic 的 long-running-agent 行为，并愿意支付更高价格，用 Claude Fable 5。 +- 当 workflow fit 比模型品牌更重要时，把它们放在 Token Station 里比较。 + +## Azure 和暂不可用的 provider catalog + +这次集成也包含 Azure OpenAI GPT-5.6 preview 模板注释，并通过 `azure_api_version = "v1"` 支持 Azure 的 `/openai/v1` surface。 + +这些模板没有用猜测价格直接启用。集成时 Azure GPT-5.6 meter 还没有发布，所以 operator 应该在自己的 Azure deployment 暴露模型后再填入价格。 + +GMI Cloud 和 AWS Bedrock OpenAI catalog 没有添加，因为它们当时的公开 catalog 没有列出 GPT-5.6。Token Station 应该让 model routing 更容易，而不是假装每个 surface 第一天都支持每个模型。 + +## 通过 Token Station 试 GPT-5.6 + +如果你已经使用 Token Station，GPT-5.6 现在就是另一个可以放进 coding-agent workflow 测试的 route family。 + +先用直接 OpenAI route 做简单 API 检查；用 Codex route 跑终端 coding task；如果 workflow 依赖 GitHub Copilot 的 supported model catalog，就试 Copilot route。 + +Token Station 让你在一个地方比较这些 route，而不用为每次模型发布重写 agent stack。 + +[试用 Token Station](https://models.bytefuture.ai/intro.html) From 4b60fcb4cfb802309964493cbb13f5ba0924ffc7 Mon Sep 17 00:00:00 2001 From: Hu Xiao Wei Date: Mon, 13 Jul 2026 22:01:02 +0800 Subject: [PATCH 2/6] refactor(blog): generate posts manifests with Astro --- posts-ja.json | 7 ------- posts-ko.json | 7 ------- posts-zh.json | 7 ------- posts.json | 7 ------- scripts/sync-legacy-public.mjs | 4 ---- src/content.config.ts | 1 + src/lib/posts-manifest.ts | 36 ++++++++++++++++++++++++++++++++++ src/pages/posts-ja.json.ts | 5 +++++ src/pages/posts-ko.json.ts | 5 +++++ src/pages/posts-zh.json.ts | 5 +++++ src/pages/posts.json.ts | 5 +++++ 11 files changed, 57 insertions(+), 32 deletions(-) create mode 100644 src/lib/posts-manifest.ts create mode 100644 src/pages/posts-ja.json.ts create mode 100644 src/pages/posts-ko.json.ts create mode 100644 src/pages/posts-zh.json.ts create mode 100644 src/pages/posts.json.ts diff --git a/posts-ja.json b/posts-ja.json index 7b3fed1..9d42e40 100644 --- a/posts-ja.json +++ b/posts-ja.json @@ -1,11 +1,4 @@ [ - { - "slug": "gpt-5-6-token-station", - "title": "GPT-5.6 が Token Station に登場：coding agent のルートでそのまま試す", - "summary": "Token Station は GPT-5.6 を OpenAI-compatible API、Codex、Copilot などの coding-agent ルートでサポートしました。1 つの endpoint から Sol、Terra、Luna、Claude Fable 5 を実際の workflow で比較できます。", - "category": "model-launches", - "date": "2026-07-13" - }, { "slug": "use-any-model-in-claude-code-through-token-station", "title": "Token Station 経由で Claude Code に任意のモデルを使う", diff --git a/posts-ko.json b/posts-ko.json index 4d9343b..8337c62 100644 --- a/posts-ko.json +++ b/posts-ko.json @@ -1,11 +1,4 @@ [ - { - "slug": "gpt-5-6-token-station", - "title": "GPT-5.6이 Token Station에 추가되었습니다: coding agent route에서 바로 테스트하기", - "summary": "Token Station은 GPT-5.6을 OpenAI-compatible API, Codex, Copilot 같은 coding-agent route에서 지원합니다. 하나의 endpoint로 Sol, Terra, Luna, Claude Fable 5를 실제 workflow에서 비교할 수 있습니다.", - "category": "model-launches", - "date": "2026-07-13" - }, { "slug": "use-any-model-in-claude-code-through-token-station", "title": "Token Station을 통해 Claude Code에서 어떤 모델이든 사용하기", diff --git a/posts-zh.json b/posts-zh.json index 401ca44..97a42f1 100644 --- a/posts-zh.json +++ b/posts-zh.json @@ -1,11 +1,4 @@ [ - { - "slug": "gpt-5-6-token-station", - "title": "GPT-5.6 已接入 Token Station：在你的 coding agent 路由里直接试用", - "summary": "Token Station 现在支持 GPT-5.6，覆盖 OpenAI-compatible API、Codex 和 Copilot 等 coding-agent 路由。用一个 endpoint 比较 Sol、Terra、Luna 和 Claude Fable 5 在真实工作流里的表现。", - "category": "model-launches", - "date": "2026-07-13" - }, { "slug": "use-token-station-in-cc-switch-for-claude-desktop", "title": "在 CC Switch 里用 Token Station 配置 Claude Desktop", diff --git a/posts.json b/posts.json index ac885bb..cf183ed 100644 --- a/posts.json +++ b/posts.json @@ -1,11 +1,4 @@ [ - { - "slug": "gpt-5-6-token-station", - "title": "GPT-5.6 is now on Token Station: try it in your coding agent routes", - "summary": "Token Station now supports GPT-5.6 across OpenAI-compatible API and coding-agent routes, including Codex and Copilot surfaces. Use one endpoint to compare Sol, Terra, Luna, and Claude Fable 5 in real workflows.", - "category": "model-launches", - "date": "2026-07-13" - }, { "slug": "use-any-model-in-claude-code-through-token-station", "title": "Use any model in Claude Code through Token Station", diff --git a/scripts/sync-legacy-public.mjs b/scripts/sync-legacy-public.mjs index 626051d..448486b 100644 --- a/scripts/sync-legacy-public.mjs +++ b/scripts/sync-legacy-public.mjs @@ -9,10 +9,6 @@ const copyNames = [ 'index-zh.html', 'index-ja.html', 'index-ko.html', - 'posts.json', - 'posts-zh.json', - 'posts-ja.json', - 'posts-ko.json', 'CNAME', '.nojekyll', 'robots.txt', diff --git a/src/content.config.ts b/src/content.config.ts index 2dfe4de..80b0ab7 100644 --- a/src/content.config.ts +++ b/src/content.config.ts @@ -15,6 +15,7 @@ const writings = defineCollection({ category: z.string().default('tutorial'), date: z.coerce.date(), cta: z.string().url().default('https://models.bytefuture.ai/intro.html'), + cover: z.string().optional(), draft: z.boolean().default(false), }), }); diff --git a/src/lib/posts-manifest.ts b/src/lib/posts-manifest.ts new file mode 100644 index 0000000..37e95bf --- /dev/null +++ b/src/lib/posts-manifest.ts @@ -0,0 +1,36 @@ +import { getCollection } from 'astro:content'; + +export type ManifestLang = 'en' | 'zh' | 'ja' | 'ko'; + +export async function getPostsManifest(lang: ManifestLang) { + const entries = await getCollection('writings'); + return entries + .filter((entry) => !entry.data.draft && entry.data.lang === lang) + .sort((a, b) => b.data.date.getTime() - a.data.date.getTime()) + .map((entry) => { + const post: { + slug: string; + title: string; + summary: string; + category: string; + date: string; + cover?: string; + } = { + slug: entry.data.slug, + title: entry.data.title, + summary: entry.data.summary, + category: entry.data.category, + date: entry.data.date.toISOString().slice(0, 10), + }; + if (entry.data.cover) post.cover = entry.data.cover; + return post; + }); +} + +export function jsonResponse(data: unknown) { + return new Response(JSON.stringify(data, null, 2) + '\n', { + headers: { + 'Content-Type': 'application/json; charset=utf-8', + }, + }); +} diff --git a/src/pages/posts-ja.json.ts b/src/pages/posts-ja.json.ts new file mode 100644 index 0000000..ba836b7 --- /dev/null +++ b/src/pages/posts-ja.json.ts @@ -0,0 +1,5 @@ +import { getPostsManifest, jsonResponse } from '../lib/posts-manifest'; + +export async function GET() { + return jsonResponse(await getPostsManifest('ja')); +} diff --git a/src/pages/posts-ko.json.ts b/src/pages/posts-ko.json.ts new file mode 100644 index 0000000..05ea61f --- /dev/null +++ b/src/pages/posts-ko.json.ts @@ -0,0 +1,5 @@ +import { getPostsManifest, jsonResponse } from '../lib/posts-manifest'; + +export async function GET() { + return jsonResponse(await getPostsManifest('ko')); +} diff --git a/src/pages/posts-zh.json.ts b/src/pages/posts-zh.json.ts new file mode 100644 index 0000000..c5dbee6 --- /dev/null +++ b/src/pages/posts-zh.json.ts @@ -0,0 +1,5 @@ +import { getPostsManifest, jsonResponse } from '../lib/posts-manifest'; + +export async function GET() { + return jsonResponse(await getPostsManifest('zh')); +} diff --git a/src/pages/posts.json.ts b/src/pages/posts.json.ts new file mode 100644 index 0000000..f1473b0 --- /dev/null +++ b/src/pages/posts.json.ts @@ -0,0 +1,5 @@ +import { getPostsManifest, jsonResponse } from '../lib/posts-manifest'; + +export async function GET() { + return jsonResponse(await getPostsManifest('en')); +} From 06039a4fdc1b55f8462d21e597830ba75e8f4819 Mon Sep 17 00:00:00 2001 From: Hu Xiao Wei Date: Mon, 13 Jul 2026 22:15:49 +0800 Subject: [PATCH 3/6] docs(blog): remove Codex route ID list --- src/content/writings/en/gpt-5-6-token-station.md | 7 ------- src/content/writings/ja/gpt-5-6-token-station.md | 7 ------- src/content/writings/ko/gpt-5-6-token-station.md | 7 ------- src/content/writings/zh/gpt-5-6-token-station.md | 7 ------- 4 files changed, 28 deletions(-) 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 49655f7..c2dac89 100644 --- a/src/content/writings/en/gpt-5-6-token-station.md +++ b/src/content/writings/en/gpt-5-6-token-station.md @@ -23,13 +23,6 @@ Token Station exposes the GPT-5.6 family through direct OpenAI-compatible routes - `openai/gpt-5.6-terra` - `openai/gpt-5.6-luna` -It also exposes OpenAI Codex routes: - -- `openai-codex/gpt-5.6` -- `openai-codex/gpt-5.6-sol` -- `openai-codex/gpt-5.6-terra` -- `openai-codex/gpt-5.6-luna` - And GitHub Copilot routes where the supported catalog publishes availability: - `github-copilot/gpt-5.6-sol` 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 62be080..b771e71 100644 --- a/src/content/writings/ja/gpt-5-6-token-station.md +++ b/src/content/writings/ja/gpt-5-6-token-station.md @@ -23,13 +23,6 @@ coding-agent チームにとって重要なのは、新しい OpenAI モデル - `openai/gpt-5.6-terra` - `openai/gpt-5.6-luna` -OpenAI Codex ルート： - -- `openai-codex/gpt-5.6` -- `openai-codex/gpt-5.6-sol` -- `openai-codex/gpt-5.6-terra` -- `openai-codex/gpt-5.6-luna` - GitHub Copilot catalog で公開されているルート： - `github-copilot/gpt-5.6-sol` 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 82e0916..9b8e9a6 100644 --- a/src/content/writings/ko/gpt-5-6-token-station.md +++ b/src/content/writings/ko/gpt-5-6-token-station.md @@ -23,13 +23,6 @@ coding-agent 팀에게 중요한 점은 새로운 OpenAI 모델 패밀리가 하 - `openai/gpt-5.6-terra` - `openai/gpt-5.6-luna` -OpenAI Codex route: - -- `openai-codex/gpt-5.6` -- `openai-codex/gpt-5.6-sol` -- `openai-codex/gpt-5.6-terra` -- `openai-codex/gpt-5.6-luna` - GitHub Copilot catalog가 공개한 route: - `github-copilot/gpt-5.6-sol` 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 b09d096..cc28937 100644 --- a/src/content/writings/zh/gpt-5-6-token-station.md +++ b/src/content/writings/zh/gpt-5-6-token-station.md @@ -23,13 +23,6 @@ Token Station 暴露直接 OpenAI-compatible GPT-5.6 route： - `openai/gpt-5.6-terra` - `openai/gpt-5.6-luna` -也暴露 OpenAI Codex route： - -- `openai-codex/gpt-5.6` -- `openai-codex/gpt-5.6-sol` -- `openai-codex/gpt-5.6-terra` -- `openai-codex/gpt-5.6-luna` - 以及 GitHub Copilot 已发布支持的 route： - `github-copilot/gpt-5.6-sol` From de74a73c35f6426e09526b7326d9f12c8520225c Mon Sep 17 00:00:00 2001 From: alabulei1 Date: Tue, 14 Jul 2026 00:36:30 +0800 Subject: [PATCH 4/6] docs(blog): tighten GPT-5.6 article, fix category + sitemap - Merge the "why this matters" tiering content into the Sol/Terra/Luna section and drop the generic heading; reads in sequence now. - Remove em-dashes from tier bullets (no-em-dash style rule). - Clarify that Codex-style workflows use the same openai/ routes (no separate Codex route); fix the dangling "Codex route" mentions. - Rewrite the opening to drop the "not just X, X is Y" reversal. - Change category model-launches -> product (closed set); the raw value otherwise leaks untranslated in the article header/Topics and is unfilterable in the listing. - Add the four article URLs to sitemap.xml (still hand-maintained). - Update CLAUDE.md for the Astro authoring model: Markdown collection source of truth, generated manifests, centralized chrome in WritingLayout, and the still-manual listing category set + sitemap. Co-Authored-By: Claude Opus 4.8 (1M context) --- CLAUDE.md | 23 ++++++++-- sitemap.xml | 20 ++++++++ .../writings/en/gpt-5-6-token-station.md | 44 +++++++----------- .../writings/ja/gpt-5-6-token-station.md | 46 ++++++++----------- .../writings/ko/gpt-5-6-token-station.md | 46 ++++++++----------- .../writings/zh/gpt-5-6-token-station.md | 44 +++++++----------- 6 files changed, 111 insertions(+), 112 deletions(-) diff --git a/CLAUDE.md b/CLAUDE.md index 5282bcd..366e6a6 100644 --- a/CLAUDE.md +++ b/CLAUDE.md @@ -5,8 +5,10 @@ Static site for **ByteFuture**, served from GitHub Pages (`.nojekyll`, `CNAME` Layout: - `index.html` — ByteFuture home: company intro, the hybrid-inference thesis, the two products, and a "Writings" teaser. -- `blog/` — the **Writings** section (listing + articles). Rules below. -- `posts.json` — content manifest for Writings (repo root; the site fetches it at `/posts.json`). +- `src/content/writings//.md` — the article sources (Astro content collection); the build generates `/blog/[-lang].html`. See **Authoring model — Astro** below. +- `blog/` — the **Writings** section listing pages + article assets/covers (the listing `index*.html` are still hand-maintained static files). +- `posts.json` (+ `posts-{zh,ja,ko}.json`) — the Writings manifest served at `/posts.json`, **generated at build** from the collection by `src/pages/posts*.json.ts` (the root `posts*.json` files are stale legacy, no longer served). +- `sitemap.xml` — hand-maintained (no Astro sitemap integration); new articles need manual `` entries. - `CNAME`, `.nojekyll` — GitHub Pages config. ## HARD RULE — NEVER touch analytics or ads tracking @@ -152,7 +154,20 @@ The `blog/` folder is the **ByteFuture Writings** section. It contains: - `blog/.html` — one file per published article. - cover images and article assets, also under `blog/`. -The post index is driven by `posts.json` (repo root); `blog/index.html` fetches it at `/posts.json` and renders the cards. The **HARD RULE above applies to every page under `blog/`.** +The post index is driven by `posts.json`; `blog/index.html` fetches it at `/posts.json` and renders the cards. The **HARD RULE above applies to every page under `blog/`.** + +### Authoring model — Astro (current, authoritative) + +The site is now built with **Astro** (`astro.config.mjs`, `output: 'static'`, `format: 'file'`). Articles are authored as **Markdown in a content collection**, not as hand-written HTML. This section is authoritative and supersedes the older per-file HTML instructions further down (the `cp blog/post-template.html`, "fill every `▼ EDIT ▼` marker", "copy the redirect script / GA / hreflang / view-counter verbatim into each page" steps): those describe the pre-Astro static pages and are kept only as reference for the legacy files still on disk. + +What changed, and where things live now: + +- **One Markdown file per language per article:** `src/content/writings//.md` where `` ∈ `en | zh | ja | ko`. Frontmatter fields (validated by `src/content.config.ts`): `slug`, `lang`, `title`, `summary`, `category`, `date` (`YYYY-MM-DD`), `cta` (URL, defaults to Token Station intro), `cover` (optional, repo-root-relative), `draft` (optional bool). The article body is Markdown/HTML below the frontmatter. +- **URLs are generated, unchanged:** `src/pages/blog/[...slug].astro` emits `/blog/.html` for `en` and `/blog/-.html` for the others (the `-zh/-ja/-ko` suffix is derived from `lang`, so you never hand-name files). +- **Chrome is centralized — do NOT copy it per article.** `src/layouts/WritingLayout.astro` injects, for every article automatically: the viewport meta, the i18n redirect script + `bf_lang` cookie logic, `canonical` / `og:locale` / all four `hreflang` alternates, the **GA4 tag** (`G-KQ0EX9QGK6`), the nav + language `