POST/api/v1/gateway

Send chat request through the gateway

Routes a chat completion through the LLM gateway with automatic provider selection, caching, rate limiting, and circuit breaking. Supports fallback models.

Authentication

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

Request body required

Example

{
  "messages": [
    {
      "role": "system",
      "content": "string"
    }
  ],
  "model": "gpt-4o",
  "tenantId": "00000000-0000-0000-0000-000000000000",
  "options": {
    "temperature": 0.7,
    "maxTokens": 1024,
    "fallbackModels": [
      "string"
    ]
  }
}
Schema
{
  "application/json": {
    "schema": {
      "type": "object",
      "required": [
        "messages",
        "model"
      ],
      "properties": {
        "messages": {
          "type": "array",
          "items": {
            "type": "object",
            "required": [
              "role",
              "content"
            ],
            "properties": {
              "role": {
                "type": "string",
                "enum": [
                  "system",
                  "user",
                  "assistant"
                ]
              },
              "content": {
                "type": "string"
              }
            }
          }
        },
        "model": {
          "type": "string",
          "example": "gpt-4o"
        },
        "tenantId": {
          "type": "string",
          "format": "uuid"
        },
        "options": {
          "type": "object",
          "properties": {
            "temperature": {
              "type": "number",
              "default": 0.7
            },
            "maxTokens": {
              "type": "integer",
              "default": 1024
            },
            "fallbackModels": {
              "type": "array",
              "items": {
                "type": "string"
              }
            }
          }
        }
      }
    }
  }
}

Response

All status codes

200Chat completion response with usage, latency, and cost
502All models failed

Code samples

cURL

curl -X POST \
  https://evalguard.ai/api/v1/gateway \
  -H "Authorization: Bearer $EVALGUARD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "messages": [ { "role": "system", "content": "string" } ], "model": "gpt-4o", "tenantId": "00000000-0000-0000-0000-000000000000", "options": { "temperature": 0.7, "maxTokens": 1024, "fallbackModels": [ "string" ] } }'

TypeScript

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

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

const response = await client.request({
  method: "POST",
  path: "/api/v1/gateway",
  body: {
    "messages": [
      {
        "role": "system",
        "content": "string"
      }
    ],
    "model": "gpt-4o",
    "tenantId": "00000000-0000-0000-0000-000000000000",
    "options": {
      "temperature": 0.7,
      "maxTokens": 1024,
      "fallbackModels": [
        "string"
      ]
    }
  },
});
console.log(response);

Python

from evalguard import EvalGuard
import os

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

response = client.request(
    method="POST",
    path="/api/v1/gateway",
    body={
    "messages": [
        {
            "role": "system",
            "content": "string"
        }
    ],
    "model": "gpt-4o",
    "tenantId": "00000000-0000-0000-0000-000000000000",
    "options": {
        "temperature": 0.7,
        "maxTokens": 1024,
        "fallbackModels": [
            "string"
        ]
    }
},
)
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(), "POST", "/api/v1/gateway", map[string]any{"messages": []any{map[string]any{"role": "system", "content": "string"}}, "model": "gpt-4o", "tenantId": "00000000-0000-0000-0000-000000000000", "options": map[string]any{"temperature": 0.7, "maxTokens": 1024, "fallbackModels": []any{"string"}}})
	if err != nil { panic(err) }
	fmt.Println(resp)
}

Errors

502

Other Gateway endpoints