Batches

​

Example

const batch = await client.createBatch({
  model: "openai/gpt-5-mini",
  prompts: [
    "Summarize this record.",
    "Classify this support ticket.",
  ],
  system: "Be concise.",
  max_tokens: 256,
  completion_window: "24h",
  webhook_endpoint_id: "we_123",
});
const status = await client.getBatch(batch.id);
const cancelling = await client.cancelBatch(batch.id);
const websocketUrl = client.batches.websocketUrl(batch.id, { intervalMs: 1500 });

​

Key parameters

• model: Model id used to infer the upstream provider. Most callers should not pass provider.
• prompts: Simple shorthand for one or more prompt strings. Phaseo compiles these into provider-native batch rows.
• items: Structured prompt shorthand with id / custom_id, prompt, messages, input, per-row settings, or an advanced body.
• requests: Advanced inline provider-native batch rows.
• input_file_id: Existing file id uploaded via /batches/files?model=... for large prebuilt JSONL inputs.
• endpoint: Optional target endpoint for advanced rows. Phaseo chooses a model/provider default when omitted.
• completion_window: e.g., 24h.
• session_id: Optional Phaseo grouping id for logs, sessions, and investigate tooling.
• webhook: Optional webhook configuration for async lifecycle notifications.
• metadata: Optional object stored with the batch.
• provider: Advanced routing constraint. Most requests should omit this and rely on model.

​

Returns

{
  "id": "batch_123",
  "object": "batch",
  "endpoint": "responses",
  "status": "completed",
  "request_id": "G-01BATCH123",
  "provider": "openai",
  "session_id": "agent-run-42",
  "created_at": 1677610602,
  "completed_at": 1677610602,
  "input_file_id": "file_123",
  "output_file_id": "file_456",
  "error_file_id": null,
  "pricing_lines": [],
  "billing": {
    "billed": true,
    "charged": false,
    "reason": "zero_cost"
  }
}