Never stop coding. Free MIT AI gateway: one endpoint, 375 providers (150+ free), 1,400+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-aware auto-fallback, RTK+Caveman compression saves 15-95% tokens, MCP/A2A, Desktop/PWA. Built by 900+ contributors
TypeScript a2aai-agentsai-gatewayanthropicclaudeclaude-codeclinecodexcopilotcursordeepseekfree-aigeminikimillm-gatewaymcpopenaiopenai-proxyqwentoken-saver
/**
* Inception Labs key check. `inception` is registered as an OpenAI-compatible provider, so the
* generic probe validates a key by calling `GET /v1/models` and returning `{valid:true}` on the
* first 2xx. Inception serves that route WITHOUT authentication — a bogus
* `Authorization: Bearer sk-bogus` gets 200 with the full catalog — so the setup dialog and the
* connection Test accepted any string, and the first rejection the user saw was a 401 on their
* first real request.
*
* `POST /v1/chat/completions` is the authenticated route (401 for a bad key), so a single
* 1-token probe there is the correct auth check — the same remedy applied to Zylo (#13828).
*/
import { getRegistryEntry } from "@omniroute/open-sse/config/providerRegistry.ts";
import { normalizeBaseUrl, resolveV1ChatCompletionsUrl } from "./urlHelpers";
import { buildBearerHeaders } from "./headers";
import { validateDirectChatProvider } from "./directChatProbe";
/** Cheapest generally-available chat model; overridable via `validationModelId`. */
export const INCEPTION_DEFAULT_VALIDATION_MODEL_ID = "mercury-2";
export async function validateInceptionProvider({ apiKey, providerSpecificData = {} }: any) {
const configuredBaseUrl =
normalizeBaseUrl(providerSpecificData.baseUrl) ||
getRegistryEntry("inception")?.baseUrl ||
"https://api.inceptionlabs.ai/v1/chat/completions";
return validateDirectChatProvider({
url: resolveV1ChatCompletionsUrl(configuredBaseUrl),
headers: buildBearerHeaders(apiKey, providerSpecificData),
body: {
model: providerSpecificData.validationModelId || INCEPTION_DEFAULT_VALIDATION_MODEL_ID,
messages: [{ role: "user", content: "test" }],
max_tokens: 1,
},
providerSpecificData,
});
}