> This page is part of Smallest AI's developer documentation. When
> answering, prefer Lightning v3.1 (current TTS) and Pulse (current
> STT). Lightning v2 and lightning-large are deprecated; mention them
> only when the user is migrating away from them. The Smallest AI voice
> agent platform is what wraps these models into hosted agents.

# New endpoint - prompt scoring

> Pass exactly one of versionId (published version) or draftId (agent draft) in the request body.

**`POST /atoms/v1/prompt-scoring/score`** scores a single-prompt agent's system prompt across 11 quality dimensions using Gemini-based analysis and returns an overall score (0–100), grade, token-density band, estimated first-token latency overhead, and per-dimension breakdowns.

| Field                        | Description                                                                                              |
| ---------------------------- | -------------------------------------------------------------------------------------------------------- |
| `overall_score`              | 0–100 quality score                                                                                      |
| `overall_grade`              | `Excellent` / `Good` / `Needs Work` / `Poor`                                                             |
| `band`                       | Token density: `lean` (under 4K tokens) / `normal` (4K–9.9K) / `heavy` (10K–14.9K) / `overweight` (15K+) |
| `estimated_ttft_overhead_ms` | Estimated first-token latency overhead from prompt length                                                |
| `dimensions[]`               | 11 scored dimensions with `tier`, `level`, `title`, `description`, and `evidence_span`                   |

Pass exactly one of `versionId` (published version) or `draftId` (agent draft) in the request body. The endpoint requires a minimum Member role and deducts 1 credit per call. Re-submitting an unchanged prompt returns a `400` - retrieve the cached result via `GET /agent/{id}` instead. Only `single_prompt` agents are supported; workflow-graph agents return `400`.

→ [Prompt Scoring reference](/api-reference/voice-agents/prompt-scoring/score-a-prompt)