List batch-supported models

GET/v1/batches/models

Returns active LLM model templates that can be used in batch jobs for your account. Each item's id is the Token360 model name to put in JSONL body.model (same as synchronous POST /v1/chat/completions).

A model is listed when it has at least one active route through an OpenAI- or Gemini-compatible batch provider. Templates with model_metadata.supports_batch=false are excluded.

See also Batch Jobs for the full workflow.

Authentication

Authorization Bearer

API key as bearer token in Authorization header.

Response

objectstring

Always list.

dataarray

Supported models.

data[].idstring

Model name for JSONL body.model.

data[].objectstring

Always model.

data[].supports_batchboolean

Always true for listed items.

data[].display_namestring

Human-readable name.

data[].model_template_idinteger

Internal template ID.

data[].model_typestring

Typically LLM.

Request

Shell
1curl https://api.token360.ai/v1/batches/models \
2  -H "Authorization: Bearer sk-your-api-key"

Response

JSON
1{
2  "object": "list",
3  "data": [
4    {
5      "id": "gpt-4o-mini",
6      "object": "model",
7      "supports_batch": true,
8      "display_name": "GPT-4o mini",
9      "model_template_id": 1234567890123456789,
10      "model_type": "LLM"
11    }
12  ]
13}
Was this page helpful?