feat(providers): add Typhoon (Thailand) and Inception Mercury diffusion LLM (#8170)

* feat(providers): add Typhoon and Inception Mercury API-key providers Two OpenAI-compatible API-key providers, each verified against a live endpoint smoke test with a negative control before registration: an unknown route answers 404 while /v1/chat/completions answers 401, which rules out gateways that reply identically to every path. - typhoon (SCB 10X, Thailand): first Thai-first provider in the catalog. /v1/models answers 200 unauthenticated and serves exactly one chat model, typhoon-v2.5-30b-a3b-instruct (128K ctx). The docs also list typhoon-v2.1-12b-instruct, but the live endpoint no longer serves it, so it is deliberately not registered. The typhoon-ocr* and typhoon-asr* entries are OCR and speech models, not chat, and are omitted. - inception (Inception Labs): first diffusion LLM (dLLM) in the catalog. mercury-2 has a 128K context, 50K max output, and supports tools, json_mode and structured outputs. The mercury-coder models advertised on the vendor blog are no longer served by the live endpoint and are therefore not registered. Both expose a working /v1/models catalog, so they are added to NAMED_OPENAI_STYLE_PROVIDERS for discovery and key validation. Free-tier metadata is claimed only where it is documented and durable: Typhoon issues a free API key rate-limited to 5 req/s and 200 req/m, and Inception grants 10M tokens on signup with no card, so both are registered with hasFree: true. Provider count moves from 280 to 282; README/AGENTS/CLAUDE counters were stale at 278 and are resynced against docs/reference/PROVIDER_REFERENCE.md. * fix(8170): union frontier-labs Inception+Writer, regen ref+golden * fix(8170): close inception object + regen ref/golden --------- Co-authored-by: Álvaro Ángel Molina <alvaretto@users.noreply.github.com> Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
2026-07-26 09:52:11 +03:00 · 2026-07-23 06:18:16 -05:00
parent 7ca821aeee
commit 81ade9e122
12 changed files with 130 additions and 2 deletions
--- a/docs/reference/PROVIDER_REFERENCE.md
+++ b/docs/reference/PROVIDER_REFERENCE.md
@@ -10,7 +10,7 @@ lastUpdated: 2026-07-23
 > Regenerate with: `npm run gen:provider-reference`
 > **Last generated:** 2026-07-23

-Total providers: **288**. See category breakdown below.
+Total providers: **290**. See category breakdown below.

 ## Categories

@@ -98,7 +98,7 @@ Use the dashboard at `/dashboard/providers` to enable, configure, and test each
 | `zai-web` | `zw` | Z.ai Web (Free) | Web cookie | [link](https://chat.z.ai) | Paste the full Cookie header from chat.z.ai (must include the token=<JWT> cookie) | — |
 | `zenmux-free` | `zmf` | ZenMux Free (Web) | Web cookie | [link](https://zenmux.ai) | Login at zenmux.ai, then export all cookies using EditThisCookie or Cookie-Editor and paste the full Cookie header string here. Refresh every ~30 days. | — |

-## API Key Providers (paid / paid-with-free-credits) (193)
+## API Key Providers (paid / paid-with-free-credits) (195)

 | ID | Alias | Name | Tags | Website | Notes |
 |----|-------|------|------|---------|-------|
@@ -188,6 +188,7 @@ Use the dashboard at `/dashboard/providers` to enable, configure, and test each
 | `hyperbolic` | `hyp` | Hyperbolic | API key | [link](https://hyperbolic.xyz) | $1-5 trial credits on signup for serverless inference |
 | `ideogram` | `ideo` | Ideogram | API key | [link](https://ideogram.ai) | Get API key at ideogram.ai/docs/api |
 | `iflytek` | `iflytek` | iFlytek Spark | API key | [link](https://xinghuo.xfyun.cn) | Get API key at console.xfyun.cn |
+| `inception` | `inception` | Inception | API key | [link](https://docs.inceptionlabs.ai) | 10M free tokens on signup, no credit card required. |
 | `inference-net` | `inet` | Inference.net | API key | [link](https://inference.net) | $25 free credits on signup plus research grants available |
 | `internlm` | `internlm` | InternLM (Intern-S1) | API key | [link](https://internlm.intern-ai.org.cn/) | Free monthly quota ~1M input / 3M output tokens (~10 RPM) |
 | `jina-ai` | `jina` | Jina AI | API key, embed/rerank | [link](https://jina.ai) | Bearer API key for the Jina AI rerank API. |
@@ -275,6 +276,7 @@ Use the dashboard at `/dashboard/providers` to enable, configure, and test each
 | `together` | `together` | Together AI | API key, video | [link](https://www.together.ai) | — |
 | `tokenrouter` | `trk` | TokenRouter | API key | [link](https://tokenrouter.com) | Use your TokenRouter API key in Authorization: Bearer <key>. Fully OpenAI-compatible. API base URL: https://api.tokenrouter.com/v1. |
 | `topaz` | `topaz` | Topaz | API key, image | [link](https://topazlabs.com) | — |
+| `typhoon` | `typhoon` | Typhoon | API key | [link](https://docs.opentyphoon.ai) | Free API key with a 5 req/s and 200 req/m rate limit. |
 | `udio` | `udio` | Udio | API key | [link](https://udio.com) | Paste session cookie from udio.com (Supabase auth) |
 | `uncloseai` | `unc` | UncloseAI | API key | [link](https://uncloseai.com) | No auth required. API accepts any non-empty string as key for identification. |
 | `upstage` | `upstage` | Upstage | API key | [link](https://www.upstage.ai) | — |
--- a/open-sse/config/providers/index.ts
+++ b/open-sse/config/providers/index.ts
@@ -172,6 +172,8 @@ import { chenzkProvider } from "./registry/chenzk/index.ts";
 import { factoryProvider } from "./registry/factory/index.ts";
 import { databricksProvider } from "./registry/databricks/index.ts";
 import { rekaProvider } from "./registry/reka/index.ts";
+import { typhoonProvider } from "./registry/typhoon/index.ts";
+import { inceptionProvider } from "./registry/inception/index.ts";
 import { sarvamProvider } from "./registry/sarvam/index.ts";
 import { writerProvider } from "./registry/writer/index.ts";
 import { plamoProvider } from "./registry/plamo/index.ts";
@@ -389,6 +391,8 @@ export const REGISTRY: Record<string, RegistryEntry> = {
  factory: factoryProvider,
  databricks: databricksProvider,
  reka: rekaProvider,
+  typhoon: typhoonProvider,
+  inception: inceptionProvider,
  sarvam: sarvamProvider,
  writer: writerProvider,
  plamo: plamoProvider,
--- a/open-sse/config/providers/registry/inception/index.ts
+++ b/open-sse/config/providers/registry/inception/index.ts
@@ -0,0 +1,19 @@
+import type { RegistryEntry } from "../../shared.ts";
+
+export const inceptionProvider: RegistryEntry = {
+  id: "inception",
+  alias: "inception",
+  format: "openai",
+  executor: "default",
+  baseUrl: "https://api.inceptionlabs.ai/v1/chat/completions",
+  authType: "apikey",
+  authHeader: "bearer",
+  models: [
+    {
+      id: "mercury-2",
+      name: "Mercury 2",
+      contextLength: 128000,
+      maxOutputTokens: 50000,
+    },
+  ],
+};
--- a/open-sse/config/providers/registry/typhoon/index.ts
+++ b/open-sse/config/providers/registry/typhoon/index.ts
@@ -0,0 +1,18 @@
+import type { RegistryEntry } from "../../shared.ts";
+
+export const typhoonProvider: RegistryEntry = {
+  id: "typhoon",
+  alias: "typhoon",
+  format: "openai",
+  executor: "default",
+  baseUrl: "https://api.opentyphoon.ai/v1/chat/completions",
+  authType: "apikey",
+  authHeader: "bearer",
+  models: [
+    {
+      id: "typhoon-v2.5-30b-a3b-instruct",
+      name: "Typhoon v2.5 30B A3B Instruct",
+      contextLength: 131072,
+    },
+  ],
+};
--- a/src/app/api/providers/[id]/models/discovery/providerSets.ts
+++ b/src/app/api/providers/[id]/models/discovery/providerSets.ts
@@ -70,6 +70,11 @@ export const NAMED_OPENAI_STYLE_PROVIDERS = new Set([
  // discovered live from https://api.openvecta.com/v1/models; the registry seed
  // (registry/openvecta) covers the most-used LLMs as the offline fallback.
  "openvecta",
+  // Typhoon (SCB 10X, Thailand) and Inception Labs (Mercury diffusion models) are
+  // OpenAI-compatible providers whose /v1/models endpoint exists and is used for
+  // catalog discovery/key validation (verified 2026-07-22).
+  "typhoon",
+  "inception",
  // Sarvam AI (India), Writer Palmyra, and PLaMo (Preferred Networks, Japan) are
  // OpenAI-compatible providers whose /v1/models endpoint exists and is used for
  // catalog discovery/key validation (verified 2026-07-22).
--- a/src/i18n/messages/en.json
+++ b/src/i18n/messages/en.json
@@ -5789,6 +5789,7 @@
      "watsonx": "The watsonx model gateway exposes OpenAI-compatible /chat/completions and /models under /ml/gateway/v1.",
      "ideogram": "Get API key at ideogram.ai/docs/api",
      "iflytek": "Get API key at console.xfyun.cn",
+      "inception": "Inception Labs is OpenAI-compatible at https://api.inceptionlabs.ai/v1. mercury-2 is the first diffusion LLM (dLLM) in the catalog — 5-10x faster generation than comparable autoregressive models, with tool calling, json_mode, and structured outputs.",
      "inference-net": "$25 free credits on signup plus research grants available",
      "internlm": "Free monthly quota ~1M input / 3M output tokens (~10 RPM)",
      "jina-ai": "Bearer API key for the Jina AI rerank API.",
@@ -5866,6 +5867,7 @@
      "together": "Connect Together AI with an API key.",
      "tokenrouter": "TokenRouter exposes an OpenAI-compatible chat completions endpoint at https://api.tokenrouter.com/v1/chat/completions, plus a working /v1/models catalog. OmniRoute uses the OpenAI protocol.",
      "topaz": "Connect Topaz with an API key.",
+      "typhoon": "Typhoon is OpenAI-compatible on /v1. Built by SCB 10X (Thailand); typhoon-v2.5-30b-a3b-instruct is a thai-first, multilingual model.",
      "udio": "Paste session cookie from udio.com (Supabase auth)",
      "uncloseai": "No auth required. API accepts any non-empty string as key for identification.",
      "upstage": "Connect Upstage with an API key.",
--- a/src/i18n/messages/pt-BR.json
+++ b/src/i18n/messages/pt-BR.json
@@ -5788,6 +5788,7 @@
      "watsonx": "O gateway de modelos do watsonx expõe /chat/completions e /models compatíveis com OpenAI sob /ml/gateway/v1.",
      "ideogram": "Obtenha a chave de API em ideogram.ai/docs/api",
      "iflytek": "Obtenha a chave de API em console.xfyun.cn",
+      "inception": "A Inception Labs é compatível com OpenAI em https://api.inceptionlabs.ai/v1. O mercury-2 é o primeiro LLM de difusão (dLLM) do catálogo — geração 5-10x mais rápida que modelos autoregressivos comparáveis, com chamadas de ferramentas, json_mode e saídas estruturadas.",
      "inference-net": "$25 em créditos grátis no cadastro, além de bolsas de pesquisa disponíveis",
      "internlm": "Cota mensal gratuita de ~1M tokens de entrada / 3M de saída (~10 RPM)",
      "jina-ai": "Chave de API Bearer para a API de rerank da Jina AI.",
@@ -5865,6 +5866,7 @@
      "together": "Conecte o Together AI com uma chave de API.",
      "tokenrouter": "O TokenRouter expõe um endpoint de chat completions compatível com OpenAI em https://api.tokenrouter.com/v1/chat/completions, além de um catálogo /v1/models funcional. O OmniRoute usa o protocolo OpenAI.",
      "topaz": "Conecte o Topaz com uma chave de API.",
+      "typhoon": "O Typhoon é compatível com OpenAI em /v1. Desenvolvido pela SCB 10X (Tailândia); o typhoon-v2.5-30b-a3b-instruct é um modelo multilíngue com foco no idioma tailandês.",
      "udio": "Cole o cookie de sessão do udio.com (autenticação Supabase)",
      "uncloseai": "Nenhuma autenticação necessária. A API aceita qualquer string não vazia como chave para identificação.",
      "upstage": "Conecte o Upstage com uma chave de API.",
--- a/src/i18n/messages/vi.json
+++ b/src/i18n/messages/vi.json
@@ -5788,6 +5788,7 @@
      "watsonx": "Cổng mô hình watsonx cung cấp /chat/completions và /models tương thích OpenAI trong /ml/gateway/v1.",
      "ideogram": "Lấy khóa API tại ideogram.ai/docs/api",
      "iflytek": "Lấy khóa API tại console.xfyun.cn",
+      "inception": "Inception Labs tương thích OpenAI tại https://api.inceptionlabs.ai/v1. mercury-2 là LLM khuếch tán (dLLM) đầu tiên trong danh mục — tạo sinh nhanh hơn 5-10 lần so với các mô hình tự hồi quy tương đương, hỗ trợ gọi công cụ, json_mode và đầu ra có cấu trúc.",
      "inference-net": "25 USD tín dụng miễn phí khi đăng ký và có các khoản tài trợ nghiên cứu",
      "internlm": "Hạn mức miễn phí hàng tháng ~1M token đầu vào / 3M token đầu ra (~10 RPM)",
      "jina-ai": "Khóa API Bearer cho API xếp hạng lại của Jina AI.",
@@ -5865,6 +5866,7 @@
      "together": "Kết nối Together AI bằng khóa API.",
      "tokenrouter": "TokenRouter cung cấp endpoint chat completions tương thích OpenAI tại https://api.tokenrouter.com/v1/chat/completions cùng danh mục /v1/models hoạt động. OmniRoute dùng giao thức OpenAI.",
      "topaz": "Kết nối Topaz bằng khóa API.",
+      "typhoon": "Typhoon tương thích OpenAI trên /v1. Được SCB 10X (Thái Lan) phát triển; typhoon-v2.5-30b-a3b-instruct là mô hình đa ngôn ngữ ưu tiên tiếng Thái.",
      "udio": "Dán cookie phiên từ udio.com (xác thực Supabase)",
      "uncloseai": "Không yêu cầu xác thực. API chấp nhận mọi chuỗi không rỗng làm khóa để nhận dạng.",
      "upstage": "Kết nối Upstage bằng khóa API.",
--- a/src/shared/constants/providers/apikey/frontier-labs.ts
+++ b/src/shared/constants/providers/apikey/frontier-labs.ts
@@ -250,6 +250,19 @@ export const APIKEY_PROVIDERS_FRONTIER = {
    passthroughModels: true,
    authHint: "Get API key at liquid.ai",
  },
+  inception: {
+    id: "inception",
+    alias: "inception",
+    name: "Inception",
+    icon: "auto_awesome",
+    color: "#F97316",
+    textIcon: "IN",
+    website: "https://docs.inceptionlabs.ai",
+    apiHint:
+      "Inception Labs is OpenAI-compatible at https://api.inceptionlabs.ai/v1. mercury-2 is the first diffusion LLM (dLLM) in the catalog — 5-10x faster generation than comparable autoregressive models, with tool calling, json_mode, and structured outputs.",
+    hasFree: true,
+    freeNote: "10M free tokens on signup, no credit card required.",
+  },
  writer: {
    id: "writer",
    alias: "writer",
--- a/src/shared/constants/providers/apikey/regional.ts
+++ b/src/shared/constants/providers/apikey/regional.ts
@@ -478,4 +478,17 @@ export const APIKEY_PROVIDERS_REGIONAL = {
      "PLaMo is OpenAI-compatible at https://api.platform.preferredai.jp/v1. Built by Preferred Networks and optimized for Japanese. Docs are primarily in Japanese.",
    hasFree: false,
  },
+  typhoon: {
+    id: "typhoon",
+    alias: "typhoon",
+    name: "Typhoon",
+    icon: "public",
+    color: "#7C3AED",
+    textIcon: "TY",
+    website: "https://docs.opentyphoon.ai",
+    apiHint:
+      "Typhoon is OpenAI-compatible on /v1. Built by SCB 10X (Thailand); typhoon-v2.5-30b-a3b-instruct is a thai-first, multilingual model.",
+    hasFree: true,
+    freeNote: "Free API key with a 5 req/s and 200 req/m rate limit.",
+  },
 };
--- a/tests/snapshots/provider/translate-path.json
+++ b/tests/snapshots/provider/translate-path.json
@@ -2647,6 +2647,29 @@
      "stream": "https://spark-api-open.xf-yun.com/v1/chat/completions"
    }
  },
+  "inception": {
+    "format": "openai",
+    "headers": {
+      "apiKey": {
+        "Accept": "text/event-stream",
+        "Authorization": "Bearer <TOK>",
+        "Content-Type": "application/json"
+      },
+      "nonStream": {
+        "Authorization": "Bearer <TOK>",
+        "Content-Type": "application/json"
+      },
+      "oauth": {
+        "Accept": "text/event-stream",
+        "Authorization": "Bearer <TOK>",
+        "Content-Type": "application/json"
+      }
+    },
+    "url": {
+      "nonStream": "https://api.inceptionlabs.ai/v1/chat/completions",
+      "stream": "https://api.inceptionlabs.ai/v1/chat/completions"
+    }
+  },
  "inference-net": {
    "format": "openai",
    "headers": {
@@ -4740,6 +4763,29 @@
      "stream": "https://core-normal.trae.ai/api/remote/v1"
    }
  },
+  "typhoon": {
+    "format": "openai",
+    "headers": {
+      "apiKey": {
+        "Accept": "text/event-stream",
+        "Authorization": "Bearer <TOK>",
+        "Content-Type": "application/json"
+      },
+      "nonStream": {
+        "Authorization": "Bearer <TOK>",
+        "Content-Type": "application/json"
+      },
+      "oauth": {
+        "Accept": "text/event-stream",
+        "Authorization": "Bearer <TOK>",
+        "Content-Type": "application/json"
+      }
+    },
+    "url": {
+      "nonStream": "https://api.opentyphoon.ai/v1/chat/completions",
+      "stream": "https://api.opentyphoon.ai/v1/chat/completions"
+    }
+  },
  "udio": {
    "format": "openai",
    "headers": {
--- a/tests/unit/chat-openai-compat-providers.test.ts
+++ b/tests/unit/chat-openai-compat-providers.test.ts
@@ -42,6 +42,8 @@ const CHAT_OPENAI_COMPAT_PROVIDER_IDS = [
  "reka",
  "byteplus",
  "orcarouter",
+  "typhoon",
+  "inception",
  "sarvam",
  "writer",
  "plamo",