Granite Switch 4.1 vs OpenAI Decisions API

Granite Switch 4.1

One self-hosted Apache 2.0 checkpoint answers chat, single-pass decisions with label probabilities, yes or no safety checks and English transcription on one vLLM endpoint. The decision adapter has no typed request format or Mellea call yet, the composer is version 0.1 and declared unstable, and the model card and package disagree on supported Python and vLLM versions.

OpenAI Decisions API

Typed predicate, choice and score answers with probabilities, up to 200 questions a call, at $0.10 per million input tokens with no output charge. It is a public beta released on 6 October 2026, with one model alias, no dated snapshot, no Batch route and no SLA found.

Granite Switch 4.1

1. Pass chat_template_kwargs: {"adapter_name": "decision"} or "guardian-core". Without it the request is ordinary chat on the base model
2. For a decision, send the state and the ### DECISION question as two user turns, request logprob_token_ids for the option labels, and set max_completion_tokens to 1
3. Use single-token option labels. Split more than 128 labels into chunks with the identical prompt and apply one softmax over all returned logprobs
4. Parse guardian-core answers as JSON, {"score": "yes"} or {"score": "no"}, where yes means the criterion is met
5. Add authentication before exposing the vLLM server. Neither vLLM nor the checkpoint requires a key by default

OpenAI Decisions API

1. Put independent questions about one input in a single questions array. Send a separate request when a question depends on an earlier answer
2. Check each answer's type before reading it. A question can come back as refusal while the others in the same request are answered
3. Send images as base64 data URLs, which the guide and the reference both accept. Hosted HTTP(S) URLs are accepted per the reference only, and file_id is rejected
4. Give a choice question a fallback value such as other, and set thresholds from your own labelled examples
5. Use Python SDK 3.26.0 or JavaScript 7.30.0 or later, and follow Retry-After on 429 and 503