Skip to content
POST/api/v1/batches

Create an async batch

Submits a batch of chat requests for asynchronous processing. Returns 201 with a batch id; poll GET /api/v1/batches/{id} for status and results.

Authentication

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

Request body required

Example

{
  "projectId": "00000000-0000-0000-0000-000000000000",
  "endpoint": "/v1/chat/completions",
  "model": "<Default model when a request omits one>",
  "completion_window": "24h",
  "requests": [
    {
      "custom_id": "string",
      "model": "string",
      "messages": [
        {
          "role": "string",
          "content": "string"
        }
      ]
    }
  ],
  "metadata": {},
  "discount_pct": 0
}
Schema
{
  "application/json": {
    "schema": {
      "type": "object",
      "properties": {
        "projectId": {
          "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)$"
        },
        "endpoint": {
          "default": "/v1/chat/completions",
          "type": "string",
          "maxLength": 256
        },
        "model": {
          "type": "string",
          "maxLength": 128,
          "description": "Default model when a request omits one"
        },
        "completion_window": {
          "default": "24h",
          "type": "string",
          "maxLength": 16
        },
        "requests": {
          "minItems": 1,
          "maxItems": 1000,
          "type": "array",
          "items": {
            "type": "object",
            "properties": {
              "custom_id": {
                "type": "string",
                "maxLength": 256
              },
              "model": {
                "type": "string",
                "maxLength": 128
              },
              "messages": {
                "minItems": 1,
                "type": "array",
                "items": {
                  "type": "object",
                  "properties": {
                    "role": {
                      "type": "string",
                      "maxLength": 32
                    },
                    "content": {
                      "type": "string"
                    }
                  },
                  "required": [
                    "role",
                    "content"
                  ],
                  "additionalProperties": false
                }
              }
            },
            "required": [
              "messages"
            ],
            "additionalProperties": false
          }
        },
        "metadata": {
          "type": "object",
          "additionalProperties": {}
        },
        "discount_pct": {
          "type": "number",
          "minimum": 0,
          "maximum": 100
        }
      },
      "required": [
        "projectId",
        "endpoint",
        "completion_window",
        "requests"
      ],
      "additionalProperties": false
    }
  }
}

Response

201 example

{
  "success": true
}

All status codes

201Batch created
400(no description)
401(no description)
404(no description)
503Batch could not be queued for processing

Code samples

cURL

curl -X POST \
  https://evalguard.ai/api/v1/batches \
  -H "Authorization: Bearer $EVALGUARD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "projectId": "00000000-0000-0000-0000-000000000000", "endpoint": "/v1/chat/completions", "model": "<Default model when a request omits one>", "completion_window": "24h", "requests": [ { "custom_id": "string", "model": "string", "messages": [ { "role": "string", "content": "string" } ] } ], "metadata": {}, "discount_pct": 0 }'

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/batches",
  body: {
    "projectId": "00000000-0000-0000-0000-000000000000",
    "endpoint": "/v1/chat/completions",
    "model": "<Default model when a request omits one>",
    "completion_window": "24h",
    "requests": [
      {
        "custom_id": "string",
        "model": "string",
        "messages": [
          {
            "role": "string",
            "content": "string"
          }
        ]
      }
    ],
    "metadata": {},
    "discount_pct": 0
  },
});
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/batches",
    body={
    "projectId": "00000000-0000-0000-0000-000000000000",
    "endpoint": "/v1/chat/completions",
    "model": "<Default model when a request omits one>",
    "completion_window": "24h",
    "requests": [
        {
            "custom_id": "string",
            "model": "string",
            "messages": [
                {
                    "role": "string",
                    "content": "string"
                }
            ]
        }
    ],
    "metadata": {},
    "discount_pct": 0
},
)
print(response)

Go

package main

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

func main() {
	body := strings.NewReader(`{"projectId":"00000000-0000-0000-0000-000000000000","endpoint":"/v1/chat/completions","model":"<Default model when a request omits one>","completion_window":"24h","requests":[{"custom_id":"string","model":"string","messages":[{"role":"string","content":"string"}]}],"metadata":{},"discount_pct":0}`)
	req, _ := http.NewRequestWithContext(context.Background(), "POST", "https://evalguard.ai/api/v1/batches", 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

400401404503

Other Batches endpoints