Skip to content
POST/api/v1/gateway

Send a chat request through the gateway

Routes a chat completion through the LLM gateway (provider selection, caching, fallback). temperature/maxTokens accepted at the top level OR inside options. Returns 422 NO_API_KEY when no provider key is configured for the model.

Authentication

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

Request body required

Example

{
  "messages": [
    {
      "role": "string",
      "content": "string"
    }
  ],
  "model": "gpt-4o",
  "tenantId": "00000000-0000-0000-0000-000000000000",
  "temperature": 0,
  "maxTokens": 1,
  "options": {
    "temperature": 0,
    "maxTokens": 1,
    "fallbackModels": [
      "string"
    ]
  }
}
Schema
{
  "application/json": {
    "schema": {
      "type": "object",
      "properties": {
        "messages": {
          "minItems": 1,
          "maxItems": 500,
          "type": "array",
          "items": {
            "type": "object",
            "properties": {
              "role": {
                "type": "string",
                "maxLength": 60
              },
              "content": {
                "type": "string",
                "maxLength": 1000000
              }
            },
            "required": [
              "role",
              "content"
            ],
            "additionalProperties": false
          }
        },
        "model": {
          "type": "string",
          "minLength": 1,
          "maxLength": 200,
          "example": "gpt-4o"
        },
        "tenantId": {
          "type": "string",
          "format": "uuid",
          "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
        },
        "temperature": {
          "type": "number",
          "minimum": 0,
          "maximum": 2
        },
        "maxTokens": {
          "type": "integer",
          "minimum": 1,
          "maximum": 1000000
        },
        "options": {
          "type": "object",
          "properties": {
            "temperature": {
              "type": "number",
              "minimum": 0,
              "maximum": 2
            },
            "maxTokens": {
              "type": "integer",
              "minimum": 1,
              "maximum": 1000000
            },
            "fallbackModels": {
              "maxItems": 20,
              "type": "array",
              "items": {
                "type": "string",
                "maxLength": 200
              }
            }
          },
          "additionalProperties": false
        }
      },
      "required": [
        "messages",
        "model"
      ],
      "additionalProperties": false
    }
  }
}

Response

All status codes

200Chat completion with usage, latency, and cost.
400(no description)
401(no description)
422No API key configured for this model (NO_API_KEY).
429(no description)

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": "string", "content": "string" } ], "model": "gpt-4o", "tenantId": "00000000-0000-0000-0000-000000000000", "temperature": 0, "maxTokens": 1, "options": { "temperature": 0, "maxTokens": 1, "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": "string",
        "content": "string"
      }
    ],
    "model": "gpt-4o",
    "tenantId": "00000000-0000-0000-0000-000000000000",
    "temperature": 0,
    "maxTokens": 1,
    "options": {
      "temperature": 0,
      "maxTokens": 1,
      "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": "string",
            "content": "string"
        }
    ],
    "model": "gpt-4o",
    "tenantId": "00000000-0000-0000-0000-000000000000",
    "temperature": 0,
    "maxTokens": 1,
    "options": {
        "temperature": 0,
        "maxTokens": 1,
        "fallbackModels": [
            "string"
        ]
    }
},
)
print(response)

Go

package main

import (
	"context"
	"fmt"
	"net/http"
	"os"
	"strings"
)

func main() {
	body := strings.NewReader(`{"messages":[{"role":"string","content":"string"}],"model":"gpt-4o","tenantId":"00000000-0000-0000-0000-000000000000","temperature":0,"maxTokens":1,"options":{"temperature":0,"maxTokens":1,"fallbackModels":["string"]}}`)
	req, _ := http.NewRequestWithContext(context.Background(), "POST", "https://evalguard.ai/api/v1/gateway", body)
	req.Header.Set("Authorization", "Bearer "+os.Getenv("EVALGUARD_API_KEY"))
	req.Header.Set("Content-Type", "application/json")
	resp, err := http.DefaultClient.Do(req)
	if err != nil { panic(err) }
	defer resp.Body.Close()
	fmt.Println(resp.Status)
}

Errors

400401422429

Other Gateway endpoints