From e07106a9248b157471efb2178fdfe7cdf1cd15f2 Mon Sep 17 00:00:00 2001 From: Yaowei Zheng Date: Thu, 6 Aug 2026 20:08:20 +0800 Subject: [PATCH] feat(models): add Inkling and Fireworks DeepSeek V4 Flash 0731, delist gateway GLM-5.1 (#220) Co-authored-by: Claude Fable 5 --- README.md | 1 + README.zh.md | 1 + packages/core/src/state/model-catalog.ts | 76 +++++++++++-------- packages/core/test/model-catalog.test.ts | 18 ++++- .../skills/skills/agenthub-models/SKILL.md | 9 ++- 5 files changed, 67 insertions(+), 38 deletions(-) diff --git a/README.md b/README.md index 47ddfe3..929445e 100644 --- a/README.md +++ b/README.md @@ -98,6 +98,7 @@ Four Skill groups ship in the box ([docs](https://penguin.ooo/docs/skills)); age | GPT 5.6 | OpenRouter | | Gemini 3.6 Flash | Google Gemini, OpenRouter | | Claude 5 | Anthropic, OpenRouter | +| Inkling | OpenRouter, Fireworks AI | Each family's latest generation only — the app's **Models** page lists every built-in preset, and any OpenAI-protocol endpoint works too: pick a preset, or point a custom endpoint at any of the 1000+ online and local models. diff --git a/README.zh.md b/README.zh.md index 97d11f1..bc8262d 100644 --- a/README.zh.md +++ b/README.zh.md @@ -98,6 +98,7 @@ https://github.com/user-attachments/assets/aec49ae9-b743-467b-b247-37bedfeaa36e | GPT 5.6 | OpenRouter | | Gemini 3.6 Flash | Google Gemini, OpenRouter | | Claude 5 | Anthropic, OpenRouter | +| Inkling | OpenRouter, Fireworks AI | 上表每个系列只列最新一代，完整预置清单请在应用的**模型**页查看；只要是 OpenAI 协议的端点都可以接入：选择预置，或用自定义端点连接 1000+ 在线与本地模型。 diff --git a/packages/core/src/state/model-catalog.ts b/packages/core/src/state/model-catalog.ts index 3c05ac9..548778a 100644 --- a/packages/core/src/state/model-catalog.ts +++ b/packages/core/src/state/model-catalog.ts @@ -17,10 +17,12 @@ * * Scope: excludes deepseek-chat / deepseek-reasoner legacy aliases that AgentHub cannot * auto-route (deprecated 2026-07-24), glm-5v-turbo (image input unsupported by AgentHub's GLM - * client), non-chat models (embedding / image generation / TTS), and Bedrock. Direct-vendor - * ids are auto-routed by AgentHub and leave client_type unset; the five gateway groups - * (OpenRouter, Fireworks AI, SiliconFlow, Qwen Token Plan, Qwen Pay-As-You-Go) can't be - * auto-routed, so they set `client_type: "openai"` and inline their preset base URL. + * client), the OpenRouter z-ai/glm-5.1 and SiliconFlow Pro/zai-org/GLM-5.1 gateway listings + * (delisted 2026-08-06; the Z.AI direct glm-5.1 remains), non-chat models (embedding / image + * generation / TTS), and Bedrock. Direct-vendor ids are auto-routed by AgentHub and leave + * client_type unset; the five gateway groups (OpenRouter, Fireworks AI, SiliconFlow, Qwen + * Token Plan, Qwen Pay-As-You-Go) can't be auto-routed, so they set `client_type: "openai"` + * and inline their preset base URL. * * This file imports no Node built-ins (type-only imports only), so it can be bundled directly * for the browser. @@ -222,9 +224,9 @@ export const MODEL_CATALOG: ModelCatalogEntry[] = [ // -- OpenRouter (gateway: OpenAI-compatible protocol, preset base URL). Prices re-read in // one pass on 2026-08-03 from the models API (/api/v1/models): cache_read stores the // published input_cache_read (falling back to the input price for the few rows without - // one — qwen3.6-35b-a3b and the :free rows); cache_write stores input_cache_write only - // when it is a genuine per-token write premium (the Anthropic, GPT and qwen3.8-max rows, - // 1.25x input) — + // one — qwen3.6-35b-a3b, thinkingmachines/inkling and the :free rows); cache_write stores + // input_cache_write only when it is a genuine per-token write premium (the Anthropic, GPT + // and qwen3.8-max rows, 1.25x input) — // Gemini's field is an hourly cache-STORAGE rate, not a per-token price, so those rows // keep the input price — and otherwise also carries the input price. The :free tier and // the openrouter/free Free Models Router store a genuine $0 price (not "unknown"), so @@ -503,6 +505,20 @@ export const MODEL_CATALOG: ModelCatalogEntry[] = [ clientType: "openai", baseUrl: OPENROUTER_BASE_URL, }, + { + // Thinking Machines Lab's Inkling (released 2026-07-14): multimodal (image + audio + // input). Specs and pricing from its OpenRouter page (2026-08-06), which publishes no + // cached-input price, so cache_read repeats the input price (no discount assumed; see + // the block comment above). + modelId: "thinkingmachines/inkling", + displayName: "Inkling", + provider: "openrouter", + contextWindow: 1000000, + pricing: usd(0.95, 0.95, 4.05), + supportsVision: true, + clientType: "openai", + baseUrl: OPENROUTER_BASE_URL, + }, { modelId: "x-ai/grok-4.5", displayName: "Grok 4.5", @@ -533,19 +549,19 @@ export const MODEL_CATALOG: ModelCatalogEntry[] = [ clientType: "openai", baseUrl: OPENROUTER_BASE_URL, }, - { - modelId: "z-ai/glm-5.1", - displayName: "GLM-5.1", - provider: "openrouter", - contextWindow: 204800, - pricing: usd(0.1794, 0.966, 3.036), - supportsVision: false, - clientType: "openai", - baseUrl: OPENROUTER_BASE_URL, - }, // -- Fireworks AI (gateway, standard serverless USD pricing: cached input / uncached // input / output from each model's page; API ids use the accounts/fireworks/models/ // form) -- + { + modelId: "accounts/fireworks/models/deepseek-v4-flash-0731", + displayName: "DeepSeek V4 Flash 0731", + provider: "fireworks", + contextWindow: 1000000, + pricing: usd(0.028, 0.14, 0.28), + supportsVision: false, + clientType: "openai", + baseUrl: FIREWORKS_BASE_URL, + }, { modelId: "accounts/fireworks/models/deepseek-v4-flash", displayName: "DeepSeek V4 Flash", @@ -576,6 +592,18 @@ export const MODEL_CATALOG: ModelCatalogEntry[] = [ clientType: "openai", baseUrl: FIREWORKS_BASE_URL, }, + { + // Thinking Machines Lab's Inkling (released 2026-07-14): multimodal (image + audio + // input); specs and serverless pricing from its Fireworks model page (2026-08-06). + modelId: "accounts/fireworks/models/inkling", + displayName: "Inkling", + provider: "fireworks", + contextWindow: 1000000, + pricing: usd(0.17, 1, 4.05), + supportsVision: true, + clientType: "openai", + baseUrl: FIREWORKS_BASE_URL, + }, { modelId: "accounts/fireworks/models/kimi-k3", displayName: "Kimi K3", @@ -649,9 +677,7 @@ export const MODEL_CATALOG: ModelCatalogEntry[] = [ }, // The Pro/ and Qwen/ entries below were unpriced until 2026-08-03 (SiliconFlow's price // list sits behind an authenticated console); prices below are its official CNY list - // prices. GLM-5.1 bills in two input-length tiers ([0, 32k) and [32k, +inf) for hit/input/ - // output alike); the catalog stores one number per bucket, so these rows keep the LOWER - // tier — treat its cost as a floor for long-context use. + // prices. { modelId: "Pro/moonshotai/Kimi-K2.6", displayName: "Kimi K2.6", @@ -662,16 +688,6 @@ export const MODEL_CATALOG: ModelCatalogEntry[] = [ clientType: "openai", baseUrl: SILICONFLOW_BASE_URL, }, - { - modelId: "Pro/zai-org/GLM-5.1", - displayName: "GLM-5.1", - provider: "siliconflow", - contextWindow: 200000, - pricing: cny(1.3, 6, 24), - supportsVision: false, - clientType: "openai", - baseUrl: SILICONFLOW_BASE_URL, - }, { // No cache-hit price on the list, so cache_read carries the input price. modelId: "Qwen/Qwen3.6-35B-A3B", diff --git a/packages/core/test/model-catalog.test.ts b/packages/core/test/model-catalog.test.ts index 4c3e682..cdbadae 100644 --- a/packages/core/test/model-catalog.test.ts +++ b/packages/core/test/model-catalog.test.ts @@ -41,6 +41,11 @@ describe("model-catalog", () => { expect(providerInfo("siliconflow")!.label).toBe("SiliconFlow"); // The catalog no longer includes GLM-5-Turbo. expect(ids).not.toContain("glm-5-turbo"); + // The OpenRouter and SiliconFlow gateway listings of GLM-5.1 were delisted 2026-08-06; + // the Z.AI direct glm-5.1 remains in the catalog. + expect(ids).not.toContain("z-ai/glm-5.1"); + expect(ids).not.toContain("Pro/zai-org/GLM-5.1"); + expect(ids).toContain("glm-5.1"); }); it("every provider is in MODEL_PROVIDERS (custom only groups user-defined models; the catalog never uses it)", () => { @@ -175,10 +180,10 @@ describe("model-catalog", () => { "qwen/qwen3.6-35b-a3b", "stepfun/step-3.7-flash", "tencent/hy3", + "thinkingmachines/inkling", "x-ai/grok-4.5", "xiaomi/mimo-v2.5", "z-ai/glm-5.2", - "z-ai/glm-5.1", ]); for (const m of or) { expect(m.clientType).toBe("openai"); @@ -186,9 +191,11 @@ describe("model-catalog", () => { } const fw = MODEL_CATALOG.filter((m) => m.provider === "fireworks"); expect(fw.map((m) => [m.modelId, m.supportsVision])).toEqual([ + ["accounts/fireworks/models/deepseek-v4-flash-0731", false], ["accounts/fireworks/models/deepseek-v4-flash", false], ["accounts/fireworks/models/deepseek-v4-pro", false], ["accounts/fireworks/models/glm-5p2", false], + ["accounts/fireworks/models/inkling", true], ["accounts/fireworks/models/kimi-k3", true], ["accounts/fireworks/models/kimi-k2p7-code", true], ["accounts/fireworks/models/minimax-m3", true], @@ -206,7 +213,6 @@ describe("model-catalog", () => { "meituan-longcat/LongCat-2.0", "moonshotai/Kimi-K2.7-Code", "Pro/moonshotai/Kimi-K2.6", - "Pro/zai-org/GLM-5.1", "Qwen/Qwen3.6-35B-A3B", "zai-org/GLM-5.2", ]); @@ -370,14 +376,18 @@ describe("model-catalog", () => { ["moonshot", "kimi-k3", "openrouter", "moonshotai/kimi-k3"], ["moonshot", "kimi-k2.6", "openrouter", "moonshotai/kimi-k2.6"], ["moonshot", "kimi-k2.6", "siliconflow", "Pro/moonshotai/Kimi-K2.6"], - ["zhipu", "glm-5.1", "openrouter", "z-ai/glm-5.1"], - ["zhipu", "glm-5.1", "siliconflow", "Pro/zai-org/GLM-5.1"], ] as const) { expect( catalogEntryFor(gatewayProvider, gatewayId)!.displayName, `${gatewayProvider}/${gatewayId}`, ).toBe(catalogEntryFor(directProvider, directId)!.displayName); } + // Inkling has no direct-vendor group (Thinking Machines Lab is gateway-only); its two + // gateway listings still share one display name, with the vendor prefix stripped. + expect(catalogEntryFor("openrouter", "thinkingmachines/inkling")!.displayName).toBe("Inkling"); + expect(catalogEntryFor("fireworks", "accounts/fireworks/models/inkling")!.displayName).toBe( + "Inkling", + ); }); it("DeepSeek and Kimi are initialized from official CNY prices (stored in USD; x7 recovers the official price)", () => { diff --git a/packages/skills/skills/agenthub-models/SKILL.md b/packages/skills/skills/agenthub-models/SKILL.md index 505e774..39aec02 100644 --- a/packages/skills/skills/agenthub-models/SKILL.md +++ b/packages/skills/skills/agenthub-models/SKILL.md @@ -3,8 +3,8 @@ name: agenthub-models description: Call model APIs through @prismshadow/agenthub — streaming text generation, image generation, speech synthesis, embeddings and the supported-model registry with one client. short_description: Call model APIs with one AgentHub client. short_description_zh: 用一个 AgentHub 客户端调用模型 API。 -version: 10 -updated: 2026-08-04T09:33:09Z +version: 11 +updated: 2026-08-06T11:51:12Z --- # AgentHub Model APIs @@ -60,11 +60,12 @@ Use exact model ids. If an id is not in the table below and the user has not giv | OpenAI embedding | `text-embedding-3-small`, `text-embedding-3-large` | — | | Kimi K3 | `kimi-k3` | OpenRouter `moonshotai/kimi-k3` | | Kimi K2.6 | `kimi-k2.6` | OpenRouter `moonshotai/kimi-k2.6`; SiliconFlow `Pro/moonshotai/Kimi-K2.6` | -| DeepSeek V4 | `deepseek-v4-pro`, `deepseek-v4-flash` | OpenRouter `deepseek/deepseek-v4-pro`, `deepseek/deepseek-v4-flash`, `deepseek/deepseek-v4-flash-0731`; SiliconFlow `deepseek-ai/DeepSeek-V4-Pro`, `deepseek-ai/DeepSeek-V4-Flash` | +| DeepSeek V4 | `deepseek-v4-pro`, `deepseek-v4-flash` | OpenRouter `deepseek/deepseek-v4-pro`, `deepseek/deepseek-v4-flash`, `deepseek/deepseek-v4-flash-0731`; Fireworks AI `accounts/fireworks/models/deepseek-v4-flash-0731`; SiliconFlow `deepseek-ai/DeepSeek-V4-Pro`, `deepseek-ai/DeepSeek-V4-Flash` | | GLM 5.2 | `glm-5.2` | OpenRouter `z-ai/glm-5.2`; SiliconFlow `zai-org/GLM-5.2` | -| GLM 5.1 | `glm-5.1` | OpenRouter `z-ai/glm-5.1`; SiliconFlow `Pro/zai-org/GLM-5.1` | +| GLM 5.1 | `glm-5.1` | — | | Qwen 3.8 Max | — | OpenRouter `qwen/qwen3.8-max` | | Qwen 3.6 | — | OpenRouter `qwen/qwen3.6-35b-a3b`; SiliconFlow `Qwen/Qwen3.6-35B-A3B` | +| Inkling | — | OpenRouter `thinkingmachines/inkling`; Fireworks AI `accounts/fireworks/models/inkling` | The image endpoint dropped its preview suffix: `gemini-3.1-flash-image-preview` is deprecated, use `gemini-3.1-flash-image`.