GET/api/v1/gateway/proxy/{path+}

Forward GET to LLM provider

Transparent reverse-proxy to the configured LLM provider (OpenAI, Anthropic, Google, Bedrock, etc.). Adds: org/project resolution, BYOK credential injection (ADR-0008), audit logging (ADR-0023), idempotency cache (ADR-0024), per-key budget enforcement, semantic cache lookup.

Authentication

Send Authorization: Bearer YOUR_API_KEY on every request. Generate API keys at /dashboard/api-keys.

Response

200 example

{}

All status codes

200Provider response.
400(no description)
401(no description)
402Payment Required — per-key budget exceeded (hard_cap=true).
429(no description)
502Bad Gateway — upstream provider error.

Code samples

cURL

curl -X GET \
  https://evalguard.ai/api/v1/gateway/proxy/{path+} \
  -H "Authorization: Bearer $EVALGUARD_API_KEY" \

TypeScript

import { EvalGuard } from "@evalguard/sdk";

const client = new EvalGuard({ apiKey: process.env.EVALGUARD_API_KEY });

const response = await client.request({
  method: "GET",
  path: "/api/v1/gateway/proxy/{path+}",
});
console.log(response);

Python

from evalguard import EvalGuard
import os

client = EvalGuard(api_key=os.environ["EVALGUARD_API_KEY"])

response = client.request(method="GET", path="/api/v1/gateway/proxy/{path+}")
print(response)

Go

package main

import (
	"context"
	"fmt"
	"os"

	"github.com/evalguard/evalguard-go"
)

func main() {
	client := evalguard.NewClient(os.Getenv("EVALGUARD_API_KEY"))
	resp, err := client.Request(context.Background(), "GET", "/api/v1/gateway/proxy/{path+}", nil)
	if err != nil { panic(err) }
	fmt.Println(resp)
}

Errors

400401402429502

Other Gateway endpoints