---
title: "Prepare Model for different precisions"
method: POST
path: "/v1/accounts/{account_id}/models/{model_id}:prepare"
tags: ["Gateway"]
---

# Prepare Model for different precisions

`POST /v1/accounts/{account_id}/models/{model_id}:prepare`

## Path parameters

- `account_id` string, required
- `model_id` string, required

## Request body

- GatewayGatewayPrepareModelBody
  - `precision` 'PRECISION_UNSPECIFIED' | 'FP16' | 'FP8' | 'FP8_MM' | 'FP8_AR' | 'FP8_MM_KV_ATTN' | 'FP8_KV' | 'FP8_MM_V2' | 'FP8_V2' | 'FP8_MM_KV_ATTN_V2' | 'NF4' | 'FP4' | 'BF16' | 'FP4_BLOCKSCALED_MM' | 'FP4_MX_MOE'
  - `readMask` string
  - `acceleratorCount` integer — Number of accelerators (GPUs) to use for quantization. Defaults to 8 if unset.
  - `abort` boolean — If true, abort an active prepare job and clear prepare tracking state. No new prepare job is launched in this request.

## Response `200`

A successful response.

- object

---

[API](https://skmtc.net/fireworks/apis/fireworks-ai-anthropic-compatible-messages-api.md) · [All operations](https://skmtc.net/fireworks/apis/fireworks-ai-anthropic-compatible-messages-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/fireworks/fireworks-ai-anthropic-compatible-messages-api/revisions/954d6bc5d922/schema)