---
title: "CRUD APIs for deployment shape. Create Deployment Shape"
method: POST
path: "/v1/accounts/{account_id}/deploymentShapes"
tags: ["gateway.openapi_Gateway"]
---

# CRUD APIs for deployment shape. Create Deployment Shape

`POST /v1/accounts/{account_id}/deploymentShapes`

## Path parameters

- `account_id` string, required

## Query parameters

- `deploymentShapeId` string

## Request body

- GatewayDeploymentShape
  - `name` string
  - `displayName` string — Human-readable display name of the deployment shape. e.g. "My Deployment Shape" Must be fewer than 64 characters long.
  - `description` string — The description of the deployment shape. Must be fewer than 1000 characters long.
  - `createTime` string, date-time — The creation time of the deployment shape.
  - `updateTime` string, date-time — The update time for the deployment shape.
  - `baseModel` string, required
  - `modelType` string — The model type of the base model.
  - `parameterCount` string, int64 — The parameter count of the base model .
  - `acceleratorCount` integer — The number of accelerators used per replica. If not specified, the default is the estimated minimum required by the base model.
  - `acceleratorType` 'ACCELERATOR_TYPE_UNSPECIFIED' | 'NVIDIA_A100_80GB' | 'NVIDIA_H100_80GB' | 'AMD_MI300X_192GB' | 'NVIDIA_A10G_24GB' | 'NVIDIA_A100_40GB' | 'NVIDIA_L4_24GB' | 'NVIDIA_H200_141GB' | 'NVIDIA_B200_180GB' | 'AMD_MI325X_256GB' | 'AMD_MI350X_288GB'
  - `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'
  - `disableDeploymentSizeValidation` boolean — If true, the deployment size validation is disabled.
  - `enableAddons` boolean — If true, LORA addons are enabled for deployments created from this shape.
  - `draftTokenCount` integer — The number of candidate tokens to generate per step for speculative decoding. Default is the base model's draft_token_count.
  - `draftModel` string — The draft model name for speculative decoding. e.g. accounts/fireworks/models/my-draft-model If empty, speculative decoding using a draft model is disabled. Default is the base model's default_draft_model. this behavior.
  - `ngramSpeculationLength` integer — The length of previous input sequence to be considered for N-gram speculation.
  - `enableSessionAffinity` boolean — Whether to apply sticky routing based on `user` field.
  - `numLoraDeviceCached` integer
  - `maxContextLength` integer — The maximum context length supported by the model (context window). If set to 0 or not specified, the model's default maximum context length will be used.
  - `presetType` 'PRESET_TYPE_UNSPECIFIED' | 'MINIMAL' | 'FAST' | 'THROUGHPUT' | 'FULL_PRECISION' | 'AGENTIC_CODING' | 'CHAT' | 'SUMMARIZATION'

## Response `200`

A successful response.

- GatewayDeploymentShape
  - `name` string
  - `displayName` string — Human-readable display name of the deployment shape. e.g. "My Deployment Shape" Must be fewer than 64 characters long.
  - `description` string — The description of the deployment shape. Must be fewer than 1000 characters long.
  - `createTime` string, date-time — The creation time of the deployment shape.
  - `updateTime` string, date-time — The update time for the deployment shape.
  - `baseModel` string, required
  - `modelType` string — The model type of the base model.
  - `parameterCount` string, int64 — The parameter count of the base model .
  - `acceleratorCount` integer — The number of accelerators used per replica. If not specified, the default is the estimated minimum required by the base model.
  - `acceleratorType` 'ACCELERATOR_TYPE_UNSPECIFIED' | 'NVIDIA_A100_80GB' | 'NVIDIA_H100_80GB' | 'AMD_MI300X_192GB' | 'NVIDIA_A10G_24GB' | 'NVIDIA_A100_40GB' | 'NVIDIA_L4_24GB' | 'NVIDIA_H200_141GB' | 'NVIDIA_B200_180GB' | 'AMD_MI325X_256GB' | 'AMD_MI350X_288GB'
  - `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'
  - `disableDeploymentSizeValidation` boolean — If true, the deployment size validation is disabled.
  - `enableAddons` boolean — If true, LORA addons are enabled for deployments created from this shape.
  - `draftTokenCount` integer — The number of candidate tokens to generate per step for speculative decoding. Default is the base model's draft_token_count.
  - `draftModel` string — The draft model name for speculative decoding. e.g. accounts/fireworks/models/my-draft-model If empty, speculative decoding using a draft model is disabled. Default is the base model's default_draft_model. this behavior.
  - `ngramSpeculationLength` integer — The length of previous input sequence to be considered for N-gram speculation.
  - `enableSessionAffinity` boolean — Whether to apply sticky routing based on `user` field.
  - `numLoraDeviceCached` integer
  - `maxContextLength` integer — The maximum context length supported by the model (context window). If set to 0 or not specified, the model's default maximum context length will be used.
  - `presetType` 'PRESET_TYPE_UNSPECIFIED' | 'MINIMAL' | 'FAST' | 'THROUGHPUT' | 'FULL_PRECISION' | 'AGENTIC_CODING' | 'CHAT' | 'SUMMARIZATION'

## Changes

- **2026-02-11** `3c3ed322dd52` — 3 warning, 3 info
  - added the new `AGENTIC_CODING` enum value to the `presetType` response property for the response status `200`
  - added the new `CHAT` enum value to the `presetType` response property for the response status `200`
  - added the new `SUMMARIZATION` enum value to the `presetType` response property for the response status `200`
  - added the new `AGENTIC_CODING` enum value to the request property `presetType`
  - …2 more
- **2026-01-30** `920bcfb416a7` — 2 info
  - added the new optional request property `maxContextLength`
  - added the optional property `maxContextLength` to the response with the `200` status
- **2025-12-18** `4e1bdf0cae56` — 1 warning, 1 info
  - added the new `AMD_MI350X_288GB` enum value to the `acceleratorType` response property for the response status `200`
  - added the new `AMD_MI350X_288GB` enum value to the request property `acceleratorType`
- **2025-12-01** `4506ec9d12ff` — 1 breaking, 2 warning, 6 info
  - removed the enum value `REINFORCEMENT_FINE_TUNING` of the request property `presetType`
  - deleted the `query` request parameter `disableSizeValidation`
  - added the new `FULL_PRECISION` enum value to the `presetType` response property for the response status `200`
  - added the new optional request property `disableDeploymentSizeValidation`
  - …5 more
- …earlier changes not shown

[Full history](https://skmtc.dev/fw-ai-external/apis/gateway-rest-api/changes/v1/accounts/:account_id/deploymentShapes/post.md)

---

[API](https://skmtc.dev/fw-ai-external/apis/gateway-rest-api.md) · [All operations](https://skmtc.dev/fw-ai-external/apis/gateway-rest-api/llms.txt) · [OpenAPI document](https://skmtc.dev/fw-ai-external/apis/gateway-rest-api/revisions/29a1e4db152c?raw)