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
import { after } from "next/server";
import { getUnifiedModelsResponse } from "./catalog";
import { getFilteredCatalogResponse } from "./catalogDiscovery";
import { hasCatalogDiscoveryParams } from "./catalogFilters";
/**
* Handle CORS preflight
*/
export async function OPTIONS() {
return new Response(null, {
headers: {
"Access-Control-Allow-Methods": "GET, HEAD, OPTIONS",
"Access-Control-Allow-Headers": "*",
},
});
}
/**
* HEAD /v1/models - availability probe (RFC 9110 §9.3.2: HEAD returns headers only)
*
* Explicit handler prevents Next.js auto-derived HEAD from streaming the full
* GET body (200+ providers enumerated on-demand), which caused ~6s hang for
* clients like the OpenAI SDK that use HEAD as a health/preflight probe.
* See: https://github.com/diegosouzapw/OmniRoute/issues/6400
*/
export async function HEAD() {
return new Response(null, {
status: 200,
headers: { "content-type": "application/json" },
});
}
/**
* GET /v1/models - OpenAI compatible models list
*
* Optional discovery filters: `capability` (repeatable / comma-separated),
* `min_context`, `kind`, `q`. Without any of them the response is untouched.
*/
export async function GET(request: Request) {
if (hasCatalogDiscoveryParams(new URL(request.url).searchParams)) {
return getFilteredCatalogResponse(request, (catalogRequest) =>
getUnifiedModelsResponse(
catalogRequest,
{},
{ scheduleBackgroundRefresh: (task) => after(task) }
)
);
}
return getUnifiedModelsResponse(
request,
{},
{
scheduleBackgroundRefresh: (task) => after(task),
}
);
}