List All Batches
curl --request POST \
--url https://api.mixpeek.com/v1/batches/list \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"offset": 0,
"limit": 100
}
'import requests
url = "https://api.mixpeek.com/v1/batches/list"
payload = {
"offset": 0,
"limit": 100
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({offset: 0, limit: 100})
};
fetch('https://api.mixpeek.com/v1/batches/list', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));<?php
$curl = curl_init();
curl_setopt_array($curl, [
CURLOPT_URL => "https://api.mixpeek.com/v1/batches/list",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => json_encode([
'offset' => 0,
'limit' => 100
]),
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>",
"Content-Type: application/json"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"strings"
"net/http"
"io"
)
func main() {
url := "https://api.mixpeek.com/v1/batches/list"
payload := strings.NewReader("{\n \"offset\": 0,\n \"limit\": 100\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Authorization", "Bearer <token>")
req.Header.Add("Content-Type", "application/json")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.post("https://api.mixpeek.com/v1/batches/list")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"offset\": 0,\n \"limit\": 100\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.mixpeek.com/v1/batches/list")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"offset\": 0,\n \"limit\": 100\n}"
response = http.request(request)
puts response.read_body{
"results": [
{
"bucket_id": "<string>",
"batch_id": "<string>",
"namespace_id": "<string>",
"status": "DRAFT",
"queue_context": {},
"object_ids": [
"<string>"
],
"dedup_strategy": "skip",
"submitted_by_key_id": "<string>",
"submitted_by_key_prefix": "<string>",
"submitted_by_is_internal": true,
"dedup_audit": {},
"collection_ids": [
"col_chunks"
],
"error": "Failed to process batch: Object not found",
"failure_reason": "Ray job failed: ImportError: No module named 'google.genai'",
"error_summary": null,
"failure_category": null,
"failed_objects": [
{
"object_id": "<string>",
"error": "<string>",
"timestamp": "<string>"
}
],
"failed_object_count": 0,
"type": "BUCKET",
"manifest_key": "ns_abc/org_123/manifests/tier_0.parquet",
"task_id": "task_tier0_abc123",
"loaded_object_ids": [
"obj_video_001",
"obj_video_002"
],
"internal_metadata": {
"include_history": true,
"last_health_check": {
"enriched_documents": 98,
"health_status": "HEALTHY",
"missing_features": [
"text_embedding"
],
"processed_documents": 100,
"recommendations": [],
"stall_duration_seconds": 0,
"timestamp": "2025-11-06T10:05:00Z",
"total_documents": 100,
"vector_populated_count": 98
}
},
"metadata": {
"campaign_id": "Q4_2025",
"source": "s3://raw-uploads/2026-05/",
"tags": [
"video",
"high-priority"
],
"notes": "Re-run after Whisper quota fix"
},
"tier_tasks": [
{
"tier_num": 1,
"source_type": "<string>",
"task_id": "task_tier0_abc123",
"status": "PENDING",
"collection_ids": [
"<string>"
],
"extractor_jobs": [
{
"extractor_type": "<string>",
"collection_ids": [
"<string>"
],
"extractor_id": "universal_extractor_v1",
"ray_job_id": "raysubmit_abc123",
"celery_task_id": "celery_task_abc123",
"callback_job_id": "celery_fast_path_btch_abc123_0_universal_extractor_v1",
"execution_mode": "celery_fast_path_universal",
"status": "PENDING",
"started_at": "2023-11-07T05:31:56Z",
"completed_at": "2023-11-07T05:31:56Z",
"duration_ms": 123,
"documents_written": 123,
"pages_dropped": 10,
"pages_dropped_reasons": {
"max_document_pages_cap": 10
},
"documents_skipped": 0,
"errors": [
{
"message": "<string>",
"component": "VertexMultimodalService",
"stage": "gemini_extraction",
"traceback": "<string>",
"timestamp": "2023-11-07T05:31:56Z",
"affected_document_ids": [
"<string>"
],
"affected_count": 1,
"recovery_suggestion": "Install google-genai package: pip install google-genai",
"metadata": {}
}
],
"error": "Ray job FAILED",
"last_activity_at": "2023-11-07T05:31:56Z",
"ray_job_status": "RUNNING",
"submission_params": {
"entrypoint": "<string>",
"deployment_mode": "<string>",
"requires_gpu": true,
"num_cpus": 123,
"num_gpus": 123,
"memory_bytes": 123,
"priority": 123,
"plugin_archives": [
"<string>"
],
"plugin_dependencies": [
"<string>"
],
"image_uri": "<string>",
"extractor_name": "<string>",
"extractor_version": "<string>",
"env_vars_keys": [
"<string>"
],
"manifest_key": "<string>",
"submitted_at": "2023-11-07T05:31:56Z"
}
}
],
"source_collection_ids": [
"col_chunks"
],
"parent_task_id": "task_tier0_abc123",
"started_at": "2025-11-03T10:00:00Z",
"completed_at": "2025-11-03T10:05:00Z",
"duration_ms": 300000,
"errors": [
{
"message": "<string>",
"component": "VertexMultimodalService",
"stage": "gemini_extraction",
"traceback": "<string>",
"timestamp": "2023-11-07T05:31:56Z",
"affected_document_ids": [
"<string>"
],
"affected_count": 1,
"recovery_suggestion": "Install google-genai package: pip install google-genai",
"metadata": {}
}
],
"error_summary": null,
"performance": {
"avg_latency_ms": 234.56,
"bottlenecks": [
{
"avg_time_ms": 113.58,
"execution_count": 50,
"max_time_ms": 234.56,
"stage_name": "gcs_batch_upload_all_segments",
"total_time_ms": 5678.9
},
{
"avg_time_ms": 69.14,
"execution_count": 50,
"max_time_ms": 123.45,
"stage_name": "pipeline_run",
"total_time_ms": 3456.78
}
],
"stage_count": 5,
"timestamp": "2025-11-06T10:05:00Z",
"total_time_ms": 12345.67
},
"ray_job_id": "raysubmit_9pDAyZbd5MN281TB",
"requires_gpu": null,
"worker_groups": null,
"celery_task_id": "a1b2c3d4-e5f6-7890-abcd-ef1234567890",
"source_documents_fetched": 100,
"documents_after_source_filter": 95,
"documents_missing_input_fields": 0,
"documents_submitted_to_engine": 95,
"documents_written": 95,
"documents_before_processing": 0,
"last_activity_at": "2023-11-07T05:31:56Z",
"ray_job_status": "RUNNING",
"ray_job_logs": "<string>",
"ray_job_logs_captured_at": "2023-11-07T05:31:56Z",
"submission_params": {
"entrypoint": "<string>",
"deployment_mode": "<string>",
"requires_gpu": true,
"num_cpus": 123,
"num_gpus": 123,
"memory_bytes": 123,
"priority": 123,
"plugin_archives": [
"<string>"
],
"plugin_dependencies": [
"<string>"
],
"image_uri": "<string>",
"extractor_name": "<string>",
"extractor_version": "<string>",
"env_vars_keys": [
"<string>"
],
"manifest_key": "<string>",
"submitted_at": "2023-11-07T05:31:56Z"
},
"infrastructure_events": [
{
"detected_at": "2023-11-07T05:31:56Z",
"raw_signal": "<string>",
"node_id": "<string>",
"pod_name": "<string>"
}
],
"audit": {},
"audit_override_reason": "<string>"
}
],
"current_tier": 0,
"total_tiers": 1,
"dag_tiers": [
[
"col_chunks"
]
],
"created_at": "2023-11-07T05:31:56Z",
"progress": null,
"documents_written": null,
"pages_dropped": null,
"pages_dropped_reasons": null,
"status_diagnostics": {},
"health": "healthy",
"cost": {
"credits_consumed": 0,
"cost_usd": 0,
"credit_rate_usd": 0.001
},
"last_activity_at": "2023-11-07T05:31:56Z",
"retry_count": 0,
"max_retries": 3,
"last_retry_at": null,
"retry_reason": null,
"webhook_url": "https://example.com/webhooks/batch-complete",
"updated_at": "2023-11-07T05:31:56Z",
"status_message": "<string>",
"estimated_completion": "2023-11-07T05:31:56Z"
}
],
"total_count": 123,
"pagination": {}
}{
"status": 123,
"error": {
"message": "<string>",
"type": "<string>",
"code": "<string>",
"details": {}
},
"success": false
}{
"status": 123,
"error": {
"message": "<string>",
"type": "<string>",
"code": "<string>",
"details": {}
},
"success": false
}{
"status": 123,
"error": {
"message": "<string>",
"type": "<string>",
"code": "<string>",
"details": {}
},
"success": false
}{
"status": 123,
"error": {
"message": "<string>",
"type": "<string>",
"code": "<string>",
"details": {}
},
"success": false
}{
"detail": [
{
"loc": [
"<string>"
],
"msg": "<string>",
"type": "<string>",
"input": "<unknown>",
"ctx": {}
}
]
}{
"status": 123,
"error": {
"message": "<string>",
"type": "<string>",
"code": "<string>",
"details": {}
},
"success": false
}Batch Queue
List All Batches
List batches across all buckets. Supports status and namespace filters.
POST
/
v1
/
batches
/
list
List All Batches
curl --request POST \
--url https://api.mixpeek.com/v1/batches/list \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"offset": 0,
"limit": 100
}
'import requests
url = "https://api.mixpeek.com/v1/batches/list"
payload = {
"offset": 0,
"limit": 100
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({offset: 0, limit: 100})
};
fetch('https://api.mixpeek.com/v1/batches/list', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));<?php
$curl = curl_init();
curl_setopt_array($curl, [
CURLOPT_URL => "https://api.mixpeek.com/v1/batches/list",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => json_encode([
'offset' => 0,
'limit' => 100
]),
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>",
"Content-Type: application/json"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"strings"
"net/http"
"io"
)
func main() {
url := "https://api.mixpeek.com/v1/batches/list"
payload := strings.NewReader("{\n \"offset\": 0,\n \"limit\": 100\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Authorization", "Bearer <token>")
req.Header.Add("Content-Type", "application/json")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.post("https://api.mixpeek.com/v1/batches/list")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"offset\": 0,\n \"limit\": 100\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.mixpeek.com/v1/batches/list")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"offset\": 0,\n \"limit\": 100\n}"
response = http.request(request)
puts response.read_body{
"results": [
{
"bucket_id": "<string>",
"batch_id": "<string>",
"namespace_id": "<string>",
"status": "DRAFT",
"queue_context": {},
"object_ids": [
"<string>"
],
"dedup_strategy": "skip",
"submitted_by_key_id": "<string>",
"submitted_by_key_prefix": "<string>",
"submitted_by_is_internal": true,
"dedup_audit": {},
"collection_ids": [
"col_chunks"
],
"error": "Failed to process batch: Object not found",
"failure_reason": "Ray job failed: ImportError: No module named 'google.genai'",
"error_summary": null,
"failure_category": null,
"failed_objects": [
{
"object_id": "<string>",
"error": "<string>",
"timestamp": "<string>"
}
],
"failed_object_count": 0,
"type": "BUCKET",
"manifest_key": "ns_abc/org_123/manifests/tier_0.parquet",
"task_id": "task_tier0_abc123",
"loaded_object_ids": [
"obj_video_001",
"obj_video_002"
],
"internal_metadata": {
"include_history": true,
"last_health_check": {
"enriched_documents": 98,
"health_status": "HEALTHY",
"missing_features": [
"text_embedding"
],
"processed_documents": 100,
"recommendations": [],
"stall_duration_seconds": 0,
"timestamp": "2025-11-06T10:05:00Z",
"total_documents": 100,
"vector_populated_count": 98
}
},
"metadata": {
"campaign_id": "Q4_2025",
"source": "s3://raw-uploads/2026-05/",
"tags": [
"video",
"high-priority"
],
"notes": "Re-run after Whisper quota fix"
},
"tier_tasks": [
{
"tier_num": 1,
"source_type": "<string>",
"task_id": "task_tier0_abc123",
"status": "PENDING",
"collection_ids": [
"<string>"
],
"extractor_jobs": [
{
"extractor_type": "<string>",
"collection_ids": [
"<string>"
],
"extractor_id": "universal_extractor_v1",
"ray_job_id": "raysubmit_abc123",
"celery_task_id": "celery_task_abc123",
"callback_job_id": "celery_fast_path_btch_abc123_0_universal_extractor_v1",
"execution_mode": "celery_fast_path_universal",
"status": "PENDING",
"started_at": "2023-11-07T05:31:56Z",
"completed_at": "2023-11-07T05:31:56Z",
"duration_ms": 123,
"documents_written": 123,
"pages_dropped": 10,
"pages_dropped_reasons": {
"max_document_pages_cap": 10
},
"documents_skipped": 0,
"errors": [
{
"message": "<string>",
"component": "VertexMultimodalService",
"stage": "gemini_extraction",
"traceback": "<string>",
"timestamp": "2023-11-07T05:31:56Z",
"affected_document_ids": [
"<string>"
],
"affected_count": 1,
"recovery_suggestion": "Install google-genai package: pip install google-genai",
"metadata": {}
}
],
"error": "Ray job FAILED",
"last_activity_at": "2023-11-07T05:31:56Z",
"ray_job_status": "RUNNING",
"submission_params": {
"entrypoint": "<string>",
"deployment_mode": "<string>",
"requires_gpu": true,
"num_cpus": 123,
"num_gpus": 123,
"memory_bytes": 123,
"priority": 123,
"plugin_archives": [
"<string>"
],
"plugin_dependencies": [
"<string>"
],
"image_uri": "<string>",
"extractor_name": "<string>",
"extractor_version": "<string>",
"env_vars_keys": [
"<string>"
],
"manifest_key": "<string>",
"submitted_at": "2023-11-07T05:31:56Z"
}
}
],
"source_collection_ids": [
"col_chunks"
],
"parent_task_id": "task_tier0_abc123",
"started_at": "2025-11-03T10:00:00Z",
"completed_at": "2025-11-03T10:05:00Z",
"duration_ms": 300000,
"errors": [
{
"message": "<string>",
"component": "VertexMultimodalService",
"stage": "gemini_extraction",
"traceback": "<string>",
"timestamp": "2023-11-07T05:31:56Z",
"affected_document_ids": [
"<string>"
],
"affected_count": 1,
"recovery_suggestion": "Install google-genai package: pip install google-genai",
"metadata": {}
}
],
"error_summary": null,
"performance": {
"avg_latency_ms": 234.56,
"bottlenecks": [
{
"avg_time_ms": 113.58,
"execution_count": 50,
"max_time_ms": 234.56,
"stage_name": "gcs_batch_upload_all_segments",
"total_time_ms": 5678.9
},
{
"avg_time_ms": 69.14,
"execution_count": 50,
"max_time_ms": 123.45,
"stage_name": "pipeline_run",
"total_time_ms": 3456.78
}
],
"stage_count": 5,
"timestamp": "2025-11-06T10:05:00Z",
"total_time_ms": 12345.67
},
"ray_job_id": "raysubmit_9pDAyZbd5MN281TB",
"requires_gpu": null,
"worker_groups": null,
"celery_task_id": "a1b2c3d4-e5f6-7890-abcd-ef1234567890",
"source_documents_fetched": 100,
"documents_after_source_filter": 95,
"documents_missing_input_fields": 0,
"documents_submitted_to_engine": 95,
"documents_written": 95,
"documents_before_processing": 0,
"last_activity_at": "2023-11-07T05:31:56Z",
"ray_job_status": "RUNNING",
"ray_job_logs": "<string>",
"ray_job_logs_captured_at": "2023-11-07T05:31:56Z",
"submission_params": {
"entrypoint": "<string>",
"deployment_mode": "<string>",
"requires_gpu": true,
"num_cpus": 123,
"num_gpus": 123,
"memory_bytes": 123,
"priority": 123,
"plugin_archives": [
"<string>"
],
"plugin_dependencies": [
"<string>"
],
"image_uri": "<string>",
"extractor_name": "<string>",
"extractor_version": "<string>",
"env_vars_keys": [
"<string>"
],
"manifest_key": "<string>",
"submitted_at": "2023-11-07T05:31:56Z"
},
"infrastructure_events": [
{
"detected_at": "2023-11-07T05:31:56Z",
"raw_signal": "<string>",
"node_id": "<string>",
"pod_name": "<string>"
}
],
"audit": {},
"audit_override_reason": "<string>"
}
],
"current_tier": 0,
"total_tiers": 1,
"dag_tiers": [
[
"col_chunks"
]
],
"created_at": "2023-11-07T05:31:56Z",
"progress": null,
"documents_written": null,
"pages_dropped": null,
"pages_dropped_reasons": null,
"status_diagnostics": {},
"health": "healthy",
"cost": {
"credits_consumed": 0,
"cost_usd": 0,
"credit_rate_usd": 0.001
},
"last_activity_at": "2023-11-07T05:31:56Z",
"retry_count": 0,
"max_retries": 3,
"last_retry_at": null,
"retry_reason": null,
"webhook_url": "https://example.com/webhooks/batch-complete",
"updated_at": "2023-11-07T05:31:56Z",
"status_message": "<string>",
"estimated_completion": "2023-11-07T05:31:56Z"
}
],
"total_count": 123,
"pagination": {}
}{
"status": 123,
"error": {
"message": "<string>",
"type": "<string>",
"code": "<string>",
"details": {}
},
"success": false
}{
"status": 123,
"error": {
"message": "<string>",
"type": "<string>",
"code": "<string>",
"details": {}
},
"success": false
}{
"status": 123,
"error": {
"message": "<string>",
"type": "<string>",
"code": "<string>",
"details": {}
},
"success": false
}{
"status": 123,
"error": {
"message": "<string>",
"type": "<string>",
"code": "<string>",
"details": {}
},
"success": false
}{
"detail": [
{
"loc": [
"<string>"
],
"msg": "<string>",
"type": "<string>",
"input": "<unknown>",
"ctx": {}
}
]
}{
"status": 123,
"error": {
"message": "<string>",
"type": "<string>",
"code": "<string>",
"details": {}
},
"success": false
}Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Body
application/json
The request model for listing batches.
Filter batches by status.
Available options:
PENDING, QUEUED, IN_PROGRESS, PROCESSING, COMPLETED, COMPLETED_WITH_ERRORS, FAILED, CANCELED, INTERRUPTED, UNKNOWN, SKIPPED, DRAFT, ACTIVE, ARCHIVED, SUSPENDED Filter batches to only those associated with a specific collection ID. Useful for tracking the processing state of all batches for a given collection.
Filter batches to only those belonging to a specific bucket. Useful with the org-level POST /v1/batches/list endpoint to scope results.
The number of batches to skip.
Required range:
x >= 0The maximum number of batches to return.
Required range:
1 <= x <= 1000Cursor for deep pagination. Use next_cursor from a previous response to fetch the next page. More efficient than offset for large result sets.
Response
Successful Response
The response model for listing batches.
Each batch in results includes bucket_id, enabling callers to build batch-to-bucket mappings without additional queries.
Was this page helpful?
⌘I