API Reference
Inference
Fine-tuning
Multimedia
Admin
Build SDK (Deprecated)
curl --request GET \
--url https://api.fireworks.ai/v1/accounts/{account_id}/deploymentShapes/{deployment_shape_id}/versions/{version_id} \
--header 'Authorization: Bearer <token>'{
"name": "<string>",
"createTime": "2023-11-07T05:31:56Z",
"snapshot": {
"baseModel": "<string>",
"name": "<string>",
"displayName": "<string>",
"description": "<string>",
"createTime": "2023-11-07T05:31:56Z",
"updateTime": "2023-11-07T05:31:56Z",
"modelType": "<string>",
"parameterCount": "<string>",
"acceleratorCount": 123,
"acceleratorType": "ACCELERATOR_TYPE_UNSPECIFIED",
"precision": "PRECISION_UNSPECIFIED",
"disableDeploymentSizeValidation": true,
"enableAddons": true,
"draftTokenCount": 123,
"draftModel": "<string>",
"ngramSpeculationLength": 123,
"enableSessionAffinity": true,
"numLoraDeviceCached": 123,
"presetType": "PRESET_TYPE_UNSPECIFIED"
},
"validated": true,
"public": true,
"latestValidated": true
}Get Deployment Shape Version
curl --request GET \
--url https://api.fireworks.ai/v1/accounts/{account_id}/deploymentShapes/{deployment_shape_id}/versions/{version_id} \
--header 'Authorization: Bearer <token>'{
"name": "<string>",
"createTime": "2023-11-07T05:31:56Z",
"snapshot": {
"baseModel": "<string>",
"name": "<string>",
"displayName": "<string>",
"description": "<string>",
"createTime": "2023-11-07T05:31:56Z",
"updateTime": "2023-11-07T05:31:56Z",
"modelType": "<string>",
"parameterCount": "<string>",
"acceleratorCount": 123,
"acceleratorType": "ACCELERATOR_TYPE_UNSPECIFIED",
"precision": "PRECISION_UNSPECIFIED",
"disableDeploymentSizeValidation": true,
"enableAddons": true,
"draftTokenCount": 123,
"draftModel": "<string>",
"ngramSpeculationLength": 123,
"enableSessionAffinity": true,
"numLoraDeviceCached": 123,
"presetType": "PRESET_TYPE_UNSPECIFIED"
},
"validated": true,
"public": true,
"latestValidated": true
}Authorizations
Bearer authentication using your Fireworks API key. Format: Bearer <API_KEY>
Path Parameters
The Account Id
The Deployment Shape Id
The Version Id
Query Parameters
The fields to be returned in the response. If empty or "*", all fields will be returned.
Response
A successful response.
The creation time of the deployment shape version. Lists will be ordered by this field.
Full snapshot of the Deployment Shape at this version.
Show child attributes
Show child attributes
Human-readable display name of the deployment shape. e.g. "My Deployment Shape" Must be fewer than 64 characters long.
The description of the deployment shape. Must be fewer than 1000 characters long.
The creation time of the deployment shape.
The update time for the deployment shape.
The model type of the base model.
The parameter count of the base model .
The number of accelerators used per replica. If not specified, the default is the estimated minimum required by the base model.
The type of accelerator to use. If not specified, the default is NVIDIA_A100_80GB.
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 The precision with which the model should be served.
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 If true, the deployment size validation is disabled.
If true, LORA addons are enabled for deployments created from this shape.
The number of candidate tokens to generate per step for speculative decoding. Default is the base model's draft_token_count.
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.
The length of previous input sequence to be considered for N-gram speculation.
Whether to apply sticky routing based on user field.
Type of deployment shape for different deployment configurations.
PRESET_TYPE_UNSPECIFIED, MINIMAL, FAST, THROUGHPUT, FULL_PRECISION If true, this version has been validated.
If true, this version will be publicly readable.
If true, this version is the latest validated version. Only one version of the shape can be the latest validated version.
Was this page helpful?