Unified Batch Inference

Run large‑scale inference jobs through one consistent endpoint

Enterprise Feature
Batch inference is available on Enterprise hybrid and self-hosted plans only. Contact the Portkey team to enable it for your Organization.

Portkey’s AI Gateway lets you send a single request that fan‑outs to hundreds—or millions—of completions. Choose the mode that best fits cost, latency, and provider support.

Choose Your Batching Mode

Mode	When to pick it	Works with
Provider Batch API	Cheapest for overnight or offline jobs. Uses the provider’s native batch endpoint & limits.	OpenAI, Azure OpenAI, Bedrock, Vertex
Portkey Batch API	Fastest and provider‑agnostic. Batches at the Gateway layer; ideal when a provider has no native batch support or you need cross‑provider jobs.	Any provider supported by Portkey Gateway

Quick rule of thumb →
Need low latency or multi‑provider batching? Portkey Batch API. Otherwise, stick with the provider’s native batch for cost savings.

---

Before You Start

Have the following ready to start making batch requests:

1. Portkey account & API key.
2. Data Service to be enabled — required for Portkey Managed Batching or when cost-attribution is needed.
3. Provider credentials for each downstream model (OpenAI key, Bedrock IAM role, etc.).
4. A Portkey File (input_file_id) - required only when using the Portkey Batch API (Mode #2). See Files to upload one.
5. Optional: Familiarity with the Create Batch OpenAPI spec.

---

Provider Batch API Mode

Used to run batch jobs with the provider’s native batch endpoint. Providers usually offer a cheaper rate for batch jobs, but you’ll be limited by the provider’s quota and limits. Most completion windows are about 24 hours.

Polling for batch status: Portkey’s gateway is stateless and does not poll for completion status of batches on the provider side. You must poll the batch status manually using the unified API with the same signature for all supported providers. See Retrieve Batch for details.

Quickstart (OpenAI example)

curl

curl -X POST https://api.portkey.ai/v1/batches \
  -H "Authorization: Bearer $PORTKEY_API_KEY" \
  -H "Content-Type: application/json" \
  -H "x-portkey-provider: $@YOUR_PROVIDER_SLUG" \
  -d '{
    "input_file_id": "file_abc123",
    "completion_window": "24h",
    "endpoint": "/v1/chat/completions",
}'

import Portkey from 'portkey-ai';

const client = new Portkey({
  apiKey: 'PORTKEY_API_KEY',
  provider: '@YOUR_PROVIDER_SLUG'
});

async function main() {
  const batch = await client.batches.create({
    input_file_id: "file-abc123",
    endpoint: "/v1/chat/completions",
    completion_window: "24h"
  });

  console.log(batch);
}

main();

from portkey_ai import Portkey

client = Portkey(
  api_key = "PORTKEY_API_KEY",
  provider = "@YOUR_PROVIDER_SLUG"
)

client.batches.create(
  input_file_id="file-abc123",
  endpoint="/v1/chat/completions",
  completion_window="24h"
)

🔗 Full schema: see the OpenAPI reference.

Supported Providers & Endpoints

Provider	Endpoints
OpenAI	completions, chat completions, embeddings
Azure OpenAI	completions, chat completions, embeddings
Bedrock	chat completions
Vertex AI	chat completions, embeddings

Defaults & Limits

Property	Default	Notes
completion_window	24h	Set by provider (cannot be shorter).
Provider quota	Per provider	e.g., OpenAI ≤ 50k jobs/day.
Retries	Provider‑defined	Portkey surfaces job status; no Gateway retry.

---

Portkey Managed Batching

Portkey Managed Batching is a feature that allows you to manage batches across multiple providers with minimal effort and a unified API.

Read more about portkey file here.

How It Works

1. Submit a batch request to Portkey with portkey file and provider information.
   • Batch requests respect metadata, budgets, and other batch request parameters.
2. Portkey will automatically upload and start the batch with provider.
3. Portkey will periodically check the batch status and update the batch status in Portkey.
4. Once batch is completed, portkey will read the batch output for the following details which will be added to your portkey analytics.
   • Token count
   • Cost
   • Success Request count
   • Failed Request count
   • Total Request count

Note: The automatic status polling and analytics described above apply only to Portkey Managed Batching. For Provider Batch API Mode (Unified Batch Inference), you must poll the batch status manually.

Portkey Custom Batching ⭐️

Portkey custom batching is a feature that allows you to batch requests to the provider which doesn’t have a native batch endpoint.

Portkey custom batching is not a discounted rate.

How It Works

Set completion_window to immediate and Portkey aggregates your requests in memory, then fires them to the target provider in fixed buckets.

Gateway default	Value
Batch size	25 requests
Batch interval	5 s between flushes
Retries	3 per request (configurable via x-portkey-config)

Coming soon: configurable batch_size, batch_interval, and max_retries.

Quickstart (provider‑agnostic)

curl -X POST https://api.portkey.ai/v1/batches \
  -H "Authorization: Bearer <PORTKEY_KEY>" \
  -H "Content-Type: application/json" \
  -d '{
    "input_file_id": "pk_file_...",
    "completion_window": "immediate",
    "endpoint": "/v1/chat/completions",
    "portkey_options": {
      "x-portkey-config": "pc-example-config",
      "x-portkey-metadata": "{\"_user\": \"user_123\"}"
    }
}'

Because Portkey orchestrates the batching, this works even for providers without a native batch endpoint.

Response & Monitoring

Identical to Provider mode; the difference is that provider_job_id is absent and cost is computed from individual calls.

About Portkey Files

Portkey Files are files uploaded to Portkey that are then automatically uploaded to the provider. They’re useful when you want to make multiple batch completions using the same file. Portkey will:

• Automatically upload the file to the provider on your behalf
• Reuse the content in your batch requests
• Check batch progress and provide post-batch analysis including token and cost calculations
• Make batch outputs available via the GET /batches/<batch_id>/output endpoint

---

Error Handling & Retries

Layer	What Portkey does	How to override
Gateway (Portkey Batch)	Retries 3× on network/429/5xx	x-portkey-config: {"retry": {"max_attempts": 5}}
Provider (native batch)	Provider rules	Not configurable via Portkey

---

Security & IAM

• Files are encrypted at rest (AES‑256) and custom encryption key is supported, if required.
• Portkey uploads on your behalf using least‑privilege scoped credentials; no long‑lived secrets are stored.
• Access to batch status & outputs is gated by your workspace role (completions.write).

---

Glossary

Term	Meaning
Batch Job	A collection of completion requests executed asynchronously.
Portkey File (input_file_id)	Files uploaded to Portkey that are automatically uploaded to the provider for batch processing. Useful for reusing the same file across multiple batch completions.
Provider Slug	A unique identifier for your AI provider (e.g., @openai-prod). Set up in Model Catalog.
Completion Window	Time frame in which the job must finish. immediate → handled by Portkey; 24h → delegated to provider.

---

Roadmap

• Custom batch_size, batch_interval, max_retries (Q3 2025)
• Real‑time progress webhooks
• UI for canceling or pausing jobs