Skip to content

7.4 billion tokens per month. 34 free LLM providers. 635 free model endpoints. All behind one /v1 endpoint, plus any custom OpenAI-compatible endpoint. Smart routing, automatic failover, encrypted keys. Personal experimentation only.

TypeScript

feat(providers): add UnoRouter (unorouter.com) as an OpenAI-compatible provider (#875)

tashdroid68ddca44c086
diff --git a/client/src/components/keys/shared.tsx b/client/src/components/keys/shared.tsx
index 648c56d8..102de220 100644
--- a/client/src/components/keys/shared.tsx
+++ b/client/src/components/keys/shared.tsx
@@ -56,6 +56,7 @@ export const PLATFORMS: { value: Platform; label: string; url: string; keyless?:
{ value: 'nara', label: 'NaraRouter (free key)', url: 'https://router.bynara.id' },
{ value: 'sealion', label: 'SEA-LION (free key)', url: 'https://sea-lion.ai' },
{ value: 'orcarouter', label: 'OrcaRouter (free key)', url: 'https://www.orcarouter.ai' },
+ { value: 'unorouter', label: 'UnoRouter (free key)', url: 'https://unorouter.com' },
// AnyAPI advertises 100K tokens/day free, but live testing on 2026-08-10
// could not get a single free-tier request served (see
// CATALOG-ANYAPI-SMOKE-2026-08-10 in the ops repo). No quota claim until
diff --git a/client/src/lib/routing.ts b/client/src/lib/routing.ts
index 24574812..0c6201be 100644
--- a/client/src/lib/routing.ts
+++ b/client/src/lib/routing.ts
@@ -306,6 +306,7 @@ export const platformColors: Record<string, string> = {
nara: '#2563eb',
sealion: '#0ea5e9',
orcarouter: '#f97316',
+ unorouter: '#ec4899',
anyapi: '#0891b2',
modelscope: '#624aff',
aihorde: '#dc2626',
diff --git a/server/src/__tests__/lib/key-parser.test.ts b/server/src/__tests__/lib/key-parser.test.ts
index cd69f3af..2cf58fbc 100644
--- a/server/src/__tests__/lib/key-parser.test.ts
+++ b/server/src/__tests__/lib/key-parser.test.ts
@@ -57,6 +57,8 @@ describe('key parser', () => {
expect(detectPlatform('SEALION_')).toBe('sealion');
expect(detectPlatform('ORCAROUTER_')).toBe('orcarouter');
expect(detectPlatform('ORCA_')).toBe('orcarouter');
+ expect(detectPlatform('UNOROUTER_')).toBe('unorouter');
+ expect(detectPlatform('UNO_ROUTER_')).toBe('unorouter');
expect(detectPlatform('MODELSCOPE_')).toBe('modelscope');
expect(detectPlatform('ANYAPI_')).toBe('anyapi');
expect(detectPlatform('ANY_API_')).toBe('anyapi');
@@ -73,6 +75,7 @@ describe('key parser', () => {
expect(AUTH_JSON_PROVIDER_MAP['api-navy']).toBe('navy');
expect(AUTH_JSON_PROVIDER_MAP['sea-lion']).toBe('sealion');
expect(AUTH_JSON_PROVIDER_MAP['orca-router']).toBe('orcarouter');
+ expect(AUTH_JSON_PROVIDER_MAP['uno-router']).toBe('unorouter');
expect(AUTH_JSON_PROVIDER_MAP['model-scope']).toBe('modelscope');
expect(AUTH_JSON_PROVIDER_MAP['any-api']).toBe('anyapi');
expect(AUTH_JSON_PROVIDER_MAP['b-ai']).toBe('bai');
diff --git a/server/src/__tests__/providers/openai-compat.test.ts b/server/src/__tests__/providers/openai-compat.test.ts
index 255de183..7abd044e 100644
--- a/server/src/__tests__/providers/openai-compat.test.ts
+++ b/server/src/__tests__/providers/openai-compat.test.ts
@@ -516,6 +516,9 @@ describe('OpenAICompatProvider - platform instances', () => {
{ platform: 'nara', name: 'NaraRouter', baseUrl: 'https://router.bynara.id/v1' },
{ platform: 'sealion', name: 'SEA-LION', baseUrl: 'https://api.sea-lion.ai/v1' },
{ platform: 'orcarouter', name: 'OrcaRouter', baseUrl: 'https://api.orcarouter.ai/v1' },
+ // unorouter's /v1/models requires auth (401 without a key), so default
+ // key validation works — no validateUrl override, unlike xkiro.
+ { platform: 'unorouter', name: 'UnoRouter', baseUrl: 'https://api.unorouter.com/v1' },
// modelscope registers a ModelScopeProvider subclass (custom validateKey,
// see providers/modelscope.test.ts) but chat routing is stock openai-compat.
{ platform: 'modelscope', name: 'ModelScope', baseUrl: 'https://api-inference.modelscope.cn/v1' },
diff --git a/server/src/lib/key-parser.ts b/server/src/lib/key-parser.ts
index 1edde2e7..d7761ecb 100644
--- a/server/src/lib/key-parser.ts
+++ b/server/src/lib/key-parser.ts
@@ -77,6 +77,8 @@ export const PREFIX_MAP: Record<string, string> = {
ORCAROUTER_: 'orcarouter',
ORCA_ROUTER_: 'orcarouter',
ORCA_: 'orcarouter',
+ UNOROUTER_: 'unorouter',
+ UNO_ROUTER_: 'unorouter',
MODELSCOPE_: 'modelscope',
MODEL_SCOPE_: 'modelscope',
ANYAPI_: 'anyapi',
@@ -122,6 +124,8 @@ export const AUTH_JSON_PROVIDER_MAP: Record<string, string> = {
orcarouter: 'orcarouter',
'orca-router': 'orcarouter',
orca: 'orcarouter',
+ unorouter: 'unorouter',
+ 'uno-router': 'unorouter',
modelscope: 'modelscope',
'model-scope': 'modelscope',
anyapi: 'anyapi',
diff --git a/server/src/providers/index.ts b/server/src/providers/index.ts
index f39848fa..f12aebd6 100644
--- a/server/src/providers/index.ts
+++ b/server/src/providers/index.ts
@@ -376,6 +376,25 @@ register(new OpenAICompatProvider({
baseUrl: 'https://api.orcarouter.ai/v1',
}));
+// UnoRouter (unorouter.com) — OpenAI-compatible aggregator. The web app is a
+// Next.js site at unorouter.com (which redirects /v1/* to the marketing app,
+// NOT the API); the real API is api.unorouter.com/v1. Free key from
+// unorouter.com (no card); free models carry a `:free` suffix and a per-minute
+// rate limit (429 on cap — "1 request(s) every 1 min per account on <model>").
+// Live-probed 2026-08-23: GET /v1/models is public (200 with no key) but
+// answers 401 "Invalid token" to a wrong key, and chat/completions is 401
+// without a key — so the default /v1/models key validation (which sends the
+// key) is a real check; no validateUrl override needed. A burst of parallel
+// requests trips an account-wide 429 on every :free model for several
+// minutes, which is why provider-quota pools the platform as one allowance.
+// Catalog rows live in the hosted catalog (premium now, free after the 30-day
+// model-age gate).
+register(new OpenAICompatProvider({
+ platform: 'unorouter',
+ name: 'UnoRouter',
+ baseUrl: 'https://api.unorouter.com/v1',
+}));
+
// ModelScope (魔搭社区, Alibaba) — OpenAI-compatible inference API
// (api-inference.modelscope.cn/v1, Bearer auth). Free tier: 2000 requests/day
// account-wide. Token from modelscope.cn/my/myaccesstoken, BUT calls only work
diff --git a/server/src/routes/keys.ts b/server/src/routes/keys.ts
index 6c2232ec..f7c2e8ed 100644
--- a/server/src/routes/keys.ts
+++ b/server/src/routes/keys.ts
@@ -32,7 +32,7 @@ const PLATFORMS = [
'google', 'groq', 'cerebras', 'bai', 'nvidia', 'mistral',
'openrouter', 'github', 'cohere', 'cloudflare', 'zhipu', 'ollama',
'kilo', 'pollinations', 'llm7', 'huggingface', 'opencode', 'ovh', 'agnes', 'reka', 'siliconflow',
- 'routeway', 'bazaarlink', 'ainative', 'aion', 'anyapi', 'requesty', 'navy', 'nara', 'sealion', 'orcarouter', 'modelscope',
+ 'routeway', 'bazaarlink', 'ainative', 'aion', 'anyapi', 'requesty', 'navy', 'nara', 'sealion', 'orcarouter', 'unorouter', 'modelscope',
'qianfan', 'volcengine', 'longcat', 'xfyun', 'aihorde', 'custom',
] as const;
diff --git a/server/src/services/provider-quota.ts b/server/src/services/provider-quota.ts
index 54285d74..80670457 100644
--- a/server/src/services/provider-quota.ts
+++ b/server/src/services/provider-quota.ts
@@ -145,6 +145,11 @@ function inferPoolForPlatform(platform: Platform, modelId?: string | null): stri
// OrcaRouter: one rate-limited free allowance across all `*-free` aliases
// and the `orcarouter/free` auto route (limits unpublished; 429 on cap).
if (platform === 'orcarouter') return 'orcarouter::free';
+ // UnoRouter: the docs say 1 req/min per free model, but live-probed
+ // 2026-08-23 a burst across many `:free` models put the whole account into
+ // 429 on every model for several minutes — so one pool, and a 429 on any
+ // model backs off the platform as a whole.
+ if (platform === 'unorouter') return 'unorouter::free';
// AnyAPI: the free tier is one 100K-tokens/day budget for the whole account,
// shared across every free/basic model — so one pool, not one per model.
if (platform === 'anyapi') return 'anyapi::free';
@@ -154,7 +159,7 @@ function inferPoolForPlatform(platform: Platform, modelId?: string | null): stri
}
function isSharedPool(platform: Platform): boolean {
- return ['openrouter', 'google', 'groq', 'cerebras', 'bai', 'sambanova', 'nvidia', 'mistral', 'github', 'cohere', 'cloudflare', 'zhipu', 'ollama', 'kilo', 'pollinations', 'llm7', 'huggingface', 'opencode', 'routeway', 'bazaarlink', 'ainative', 'aion', 'requesty', 'navy', 'nara', 'sealion', 'orcarouter', 'anyapi', 'modelscope', 'aihorde'].includes(platform);
+ return ['openrouter', 'google', 'groq', 'cerebras', 'bai', 'sambanova', 'nvidia', 'mistral', 'github', 'cohere', 'cloudflare', 'zhipu', 'ollama', 'kilo', 'pollinations', 'llm7', 'huggingface', 'opencode', 'routeway', 'bazaarlink', 'ainative', 'aion', 'requesty', 'navy', 'nara', 'sealion', 'orcarouter', 'unorouter', 'anyapi', 'modelscope', 'aihorde'].includes(platform);
}
type HeaderSpec = { metric: QuotaMetric; limit: string; remaining?: string; reset?: string; strategy?: QuotaResetStrategy };
diff --git a/shared/types.ts b/shared/types.ts
index 83a561da..0020d403 100644
--- a/shared/types.ts
+++ b/shared/types.ts
@@ -132,6 +132,15 @@ export type Platform =
// (never fall back to paid). Catalog rows live in the Oracle catalog
// (premium now, free after the 30-day model-age gate).
| 'orcarouter'
+ // UnoRouter (unorouter.com) — OpenAI-compatible aggregator. The web app is a
+ // Next.js site at unorouter.com; the API lives at api.unorouter.com/v1. Free
+ // key from unorouter.com (no card); free models carry a `:free` suffix and a
+ // per-minute rate limit (429 on cap, e.g. "1 request(s) every 1 min").
+ // Live-probed 2026-08-23: /v1/models is public without a key but 401s on a
+ // wrong key, and /v1/chat/completions 401s without a key, so default key
+ // validation works. Catalog rows live in the hosted catalog (premium now,
+ // free after the 30-day model-age gate).
+ | 'unorouter'
// ModelScope (魔搭社区, Alibaba) — OpenAI-compatible inference API
// (api-inference.modelscope.cn/v1). Free tier is 2000 requests/day
// account-wide, but calls only work after the ModelScope account is bound to