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
Add Agnes AI provider (OpenAI-compatible) (#323)
Tashfeen7f861316a2f2
diff --git a/client/src/pages/KeysPage.tsx b/client/src/pages/KeysPage.tsxindex 5fc337f1..64dc2a7e 100644--- a/client/src/pages/KeysPage.tsx+++ b/client/src/pages/KeysPage.tsx@@ -54,6 +54,7 @@ const PLATFORMS: { value: Platform; label: string; url: string; keyless?: boolea{ value: 'llm7', label: 'LLM7 (anon ok)', url: 'https://llm7.io' },{ value: 'huggingface', label: 'HuggingFace Router', url: 'https://huggingface.co/settings/tokens' },{ value: 'opencode', label: 'OpenCode Zen (free key)', url: 'https://opencode.ai/auth' },+ { value: 'agnes', label: 'Agnes AI (free key)', url: 'https://platform.agnes-ai.com' },]// 'custom' is configured through its own form (base URL + model), not thediff --git a/server/src/providers/index.ts b/server/src/providers/index.tsindex ddbddfc7..54800ef8 100644--- a/server/src/providers/index.ts+++ b/server/src/providers/index.ts@@ -184,6 +184,22 @@ register(new OpenAICompatProvider({keyless: true,}));+// Agnes AI (Sapiens AI) — OpenAI-compatible, backed by LiteLLM + vLLM. Its+// proprietary Agnes models are currently served at $0/token: live-probed+// 2026-06-15, the LiteLLM cost headers (x-litellm-response-cost-original) come+// back 0.0 with no credit drain, so usage is genuinely free rather than a+// one-time signup-credit grant. The $0 is promotional ("previously $X" /+// "during this period"), and there is a paid Token/Unlimited subscription+// underneath, so watch for reversion to paid. ~30 concurrent requests succeed+// before 429s (no documented RPM/RPD). Free key from platform.agnes-ai.com,+// no card. Catalog rows live in the catalog (premium → age into free); not+// shipped as freeapi model migrations.+register(new OpenAICompatProvider({+ platform: 'agnes',+ name: 'Agnes AI',+ baseUrl: 'https://apihub.agnes-ai.com/v1',+}));+// Chutes was evaluated for V11 and dropped: probe with a free-tier key// returned 402 on every model — "Quota exceeded and account balance is// $0.0, please pay with fiat or send tao". The "free" tier requires adiff --git a/server/src/routes/keys.ts b/server/src/routes/keys.tsindex 00b8ec45..a1fdc2ec 100644--- a/server/src/routes/keys.ts+++ b/server/src/routes/keys.ts@@ -14,7 +14,7 @@ export const keysRouter = Router();const PLATFORMS = ['google', 'groq', 'cerebras', 'nvidia', 'mistral','openrouter', 'github', 'cohere', 'cloudflare', 'zhipu', 'ollama',- 'kilo', 'pollinations', 'llm7', 'huggingface', 'opencode', 'ovh', 'custom',+ 'kilo', 'pollinations', 'llm7', 'huggingface', 'opencode', 'ovh', 'agnes', 'custom',] as const;// `key` is optional so keyless providers (Kilo's anonymous gateway) can be addeddiff --git a/shared/types.ts b/shared/types.tsindex 9b3941ba..d320d0b3 100644--- a/shared/types.ts+++ b/shared/types.ts@@ -29,6 +29,10 @@ export type Platform =// OVHcloud AI Endpoints — OpenAI-compatible, keyless anonymous tier// (2 req/min per IP per model); see migrateModelsV26.| 'ovh'+ // Agnes AI (Sapiens AI) — OpenAI-compatible (LiteLLM + vLLM backend). Serves+ // its own proprietary Agnes models; the free key comes from+ // platform.agnes-ai.com (no card).+ | 'agnes'// User-configured OpenAI-compatible endpoint (llama.cpp, LM Studio, vLLM,// Ollama, any base_url). The endpoint URL lives on the api_keys row; see #117.| 'custom';