Fireworks Embeddings API
Generate dense vector embeddings for retrieval, RAG, and semantic search using nomic, Qwen3, BGE, and other open embedding models.
OpenAPI Specification
openapi: 3.1.0
info:
title: Gateway REST API
version: 4.259.0
tags:
- name: gateway.openapi_Gateway
x-displayName: Gateway
- name: gateway-extra.openapi_Gateway
x-displayName: Gateway
- name: responses.openapi_other
x-displayName: other
- name: text-completion.openapi_other
x-displayName: other
- name: anthropic-messages.openapi_other
x-displayName: other
paths:
/v1/accounts:
servers:
- url: https://api.fireworks.ai
get:
summary: List Accounts
operationId: Gateway_ListAccounts
responses:
'200':
description: A successful response.
content:
application/json:
schema:
$ref: '#/components/schemas/gatewayListAccountsResponse'
parameters:
- name: pageSize
description: >-
The maximum number of accounts to return. The maximum page_size is
200,
values above 200 will be coerced to 200.
If unspecified, the default is 50.
in: query
required: false
schema:
type: integer
format: int32
- name: pageToken
description: >-
A page token, received from a previous ListAccounts call. Provide
this
to retrieve the subsequent page. When paginating, all other
parameters
provided to ListAccounts must match the call that provided the page
token.
in: query
required: false
schema:
type: string
- name: filter
description: |-
Only accounts satisfying the provided filter (if specified) will be
returned. See https://google.aip.dev/160 for the filter grammar.
in: query
required: false
schema:
type: string
- name: orderBy
description: |-
Not supported.
Accounts will be returned ordered by `name`.
in: query
required: false
schema:
type: string
- name: readMask
description: >-
The fields to be returned in the response. If empty or "*", all
fields will be returned.
in: query
required: false
schema:
type: string
tags:
- gateway.openapi_Gateway
security:
- BearerAuth: []
/v1/auth/refresh:
servers:
- url: https://api.fireworks.ai
post:
summary: Refresh a session JWT before expiry with a fresh TTL.
operationId: Gateway_RefreshSessionToken
responses:
'200':
description: A successful response.
content:
application/json:
schema:
$ref: '#/components/schemas/gatewayRefreshSessionTokenResponse'
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/gatewayRefreshSessionTokenRequest'
description: Request to refresh an existing session JWT before it expires.
required: true
tags:
- gateway.openapi_Gateway
security:
- BearerAuth: []
/v1/creditCodes:redeem:
servers:
- url: https://api.fireworks.ai
post:
summary: |-
APIs for credit codes.
Redeem Credit Code
operationId: Gateway_RedeemCreditCode
responses:
'200':
description: A successful response.
content:
application/json:
schema:
$ref: '#/components/schemas/gatewayRedeemCreditCodeResponse'
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/gatewayRedeemCreditCodeRequest'
description: >-
RedeemCreditCodeRequest is the request to redeem a credit code for an
account.
required: true
tags:
- gateway.openapi_Gateway
security:
- BearerAuth: []
/v1/validateModelConfig:
servers:
- url: https://api.fireworks.ai
post:
summary: Validate Model Config
operationId: Gateway_ValidateModelConfig
responses:
'200':
description: A successful response.
content:
application/json:
schema:
type: object
properties: {}
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/gatewayValidateModelConfigRequest'
required: true
tags:
- gateway.openapi_Gateway
security:
- BearerAuth: []
/v1/accounts/{account_id}:
servers:
- url: https://api.fireworks.ai
get:
summary: Get Account
operationId: Gateway_GetAccount
responses:
'200':
description: A successful response.
content:
application/json:
schema:
$ref: '#/components/schemas/gatewayAccount'
parameters:
- name: readMask
description: >-
The fields to be returned in the response. If empty or "*", all
fields will be returned.
in: query
required: false
schema:
type: string
- name: account_id
in: path
required: true
description: The Account Id
schema:
type: string
tags:
- gateway.openapi_Gateway
security:
- BearerAuth: []
/v1/accounts/{account_id}/accountUsageFilterOptions:
servers:
- url: https://api.fireworks.ai
get:
summary: >-
Distinct filter values for an account/time range (serverless +
dedicated; for FE, separate -yet mirrors GetAccountUsage).
operationId: Gateway_GetAccountUsageFilterOptions
responses:
'200':
description: A successful response.
content:
application/json:
schema:
$ref: >-
#/components/schemas/gatewayGetAccountUsageFilterOptionsResponse
parameters:
- name: startTime
in: query
required: true
schema:
type: string
format: date-time
- name: endTime
in: query
required: true
schema:
type: string
format: date-time
- name: usageType
description: |-
If not specified, loads filter options for both usage streams.
- SERVERLESS: Serverless filter dimensions only (model_name, api_key_id, annotations.*).
- DEDICATED_DEPLOYMENT: Dedicated deployment filter dimensions (deployment_name, annotations.team, .project, .environment).
in: query
required: false
schema:
type: string
enum:
- USAGE_TYPE_UNSPECIFIED
- SERVERLESS
- DEDICATED_DEPLOYMENT
default: USAGE_TYPE_UNSPECIFIED
- name: account_id
in: path
required: true
description: The Account Id
schema:
type: string
tags:
- gateway.openapi_Gateway
security:
- BearerAuth: []
/v1/accounts/{account_id}/auditLogs:
servers:
- url: https://api.fireworks.ai
get:
summary: List User Audit Logs
operationId: Gateway_ListAuditLogs
responses:
'200':
description: A successful response.
content:
application/json:
schema:
$ref: '#/components/schemas/gatewayListAuditLogsResponse'
parameters:
- name: startTime
description: |-
Start time of the audit logs to retrieve.
If unspecified, the default is 30 days before now.
in: query
required: false
schema:
type: string
format: date-time
- name: endTime
description: |-
End time of the audit logs to retrieve.
If unspecified, the default is the current time.
in: query
required: false
schema:
type: string
format: date-time
- name: email
description: |-
Optional.
Filter audit logs for user email associated with the account.
in: query
required: false
schema:
type: string
- name: pageSize
description: >-
The maximum number of audit logs to return. The maximum page_size is
200,
values above 200 will be coerced to 200.
If unspecified, the default is 10.
in: query
required: false
schema:
type: integer
format: int32
- name: pageToken
description: >-
A page token, received from a previous ListAuditLogs call. Provide
this
to retrieve the subsequent page. When paginating, all other
parameters
provided to ListAuditLogs must match the call that provided the page
token.
in: query
required: false
schema:
type: string
- name: filter
description: Unused but required to use existing ListRequest functionality.
in: query
required: false
schema:
type: string
- name: orderBy
description: Unused but required to use existing ListRequest functionality.
in: query
required: false
schema:
type: string
- name: readMask
description: >-
The fields to be returned in the response. If empty or "*", all
fields will be returned.
in: query
required: false
schema:
type: string
- name: account_id
in: path
required: true
description: The Account Id
schema:
type: string
tags:
- gateway.openapi_Gateway
security:
- BearerAuth: []
/v1/accounts/{account_id}/batchInferenceJobs:
servers:
- url: https://api.fireworks.ai
get:
summary: List Batch Inference Jobs
operationId: Gateway_ListBatchInferenceJobs
responses:
'200':
description: A successful response.
content:
application/json:
schema:
$ref: '#/components/schemas/gatewayListBatchInferenceJobsResponse'
parameters:
- name: pageSize
description: >-
The maximum number of batch inference jobs to return. The maximum
page_size is 200,
values above 200 will be coerced to 200.
If unspecified, the default is 50.
in: query
required: false
schema:
type: integer
format: int32
- name: pageToken
description: >-
A page token, received from a previous ListBatchInferenceJobs call.
Provide this
to retrieve the subsequent page. When paginating, all other
parameters
provided to ListBatchInferenceJobs must match the call that provided
the page
token.
in: query
required: false
schema:
type: string
- name: filter
description: |-
Only jobs satisfying the provided filter (if specified) will be
returned. See https://google.aip.dev/160 for the filter grammar.
in: query
required: false
schema:
type: string
- name: orderBy
description: >-
A comma-separated list of fields to order by. e.g. "foo,bar"
The default sort order is ascending. To specify a descending order
for a
field, append a " desc" suffix. e.g. "foo desc,bar"
Subfields are specified with a "." character. e.g. "foo.bar"
If not specified, the default order is by "created_time".
in: query
required: false
schema:
type: string
- name: readMask
description: >-
The fields to be returned in the response. If empty or "*", all
fields will be returned.
in: query
required: false
schema:
type: string
- name: account_id
in: path
required: true
description: The Account Id
schema:
type: string
tags:
- gateway.openapi_Gateway
security:
- BearerAuth: []
post:
summary: Create Batch Inference Job
operationId: Gateway_CreateBatchInferenceJob
responses:
'200':
description: A successful response.
content:
application/json:
schema:
$ref: '#/components/schemas/gatewayBatchInferenceJob'
parameters:
- name: batchInferenceJobId
description: ID of the batch inference job.
in: query
required: false
schema:
type: string
- name: account_id
in: path
required: true
description: The Account Id
schema:
type: string
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/gatewayBatchInferenceJob'
required: true
tags:
- gateway.openapi_Gateway
security:
- BearerAuth: []
/v1/accounts/{account_id}/batchInferenceJobs/{batch_inference_job_id}:
servers:
- url: https://api.fireworks.ai
get:
summary: Get Batch Inference Job
operationId: Gateway_GetBatchInferenceJob
responses:
'200':
description: A successful response.
content:
application/json:
schema:
$ref: '#/components/schemas/gatewayBatchInferenceJob'
parameters:
- name: readMask
description: >-
The fields to be returned in the response. If empty or "*", all
fields will be returned.
in: query
required: false
schema:
type: string
- name: account_id
in: path
required: true
description: The Account Id
schema:
type: string
- name: batch_inference_job_id
in: path
required: true
description: The Batch Inference Job Id
schema:
type: string
tags:
- gateway.openapi_Gateway
security:
- BearerAuth: []
delete:
summary: Delete Batch Inference Job
operationId: Gateway_DeleteBatchInferenceJob
responses:
'200':
description: A successful response.
content:
application/json:
schema:
type: object
properties: {}
parameters:
- name: account_id
in: path
required: true
description: The Account Id
schema:
type: string
- name: batch_inference_job_id
in: path
required: true
description: The Batch Inference Job Id
schema:
type: string
tags:
- gateway.openapi_Gateway
security:
- BearerAuth: []
/v1/accounts/{account_id}/billing/summary:
servers:
- url: https://api.fireworks.ai
get:
summary: Get billing summary information for an account
operationId: Gateway_GetBillingSummary
responses:
'200':
description: A successful response.
content:
application/json:
schema:
$ref: '#/components/schemas/gatewayGetBillingSummaryResponse'
parameters:
- name: startTime
description: >-
Start time for the billing period.
Note: Costs are aggregated daily. Only the date portion (YYYY-MM-DD)
is used;
the time portion is ignored. For example, 2025-10-05T07:18:29Z and
2025-10-05T23:59:59Z are treated the same as 2025-10-05T00:00:00Z.
in: query
required: true
schema:
type: string
format: date-time
- name: endTime
description: >-
End time for the billing period (exclusive).
Note: Costs are aggregated daily. Only the date portion (YYYY-MM-DD)
is used;
the time portion is ignored. Costs for the end date are NOT
included.
For example, to get costs for Oct 5 and Oct 6, use:
start_time: 2025-10-05T00:00:00Z
end_time: 2025-10-07T00:00:00Z (Oct 7 is excluded)
in: query
required: true
schema:
type: string
format: date-time
- name: account_id
in: path
required: true
description: The Account Id
schema:
type: string
tags:
- gateway.openapi_Gateway
security:
- BearerAuth: []
/v1/accounts/{account_id}/billingUsage:
servers:
- url: https://api.fireworks.ai
get:
summary: >-
Get account usage (serverless and dedicated deployments).
Optionally filter by usage type via the usage_type field. If not
specified, returns all usage types.
TODO: rename this to /accountUsage
operationId: Gateway_GetAccountUsage
responses:
'200':
description: A successful response.
content:
application/json:
schema:
$ref: '#/components/schemas/gatewayAccountUsage'
parameters:
- name: startTime
description: |-
Costs returned are inclusive of `start_time`.
start_time must be before end_time.
in: query
required: true
schema:
type: string
format: date-time
- name: endTime
description: |-
Costs returned are exclusive of `end_time`.
end_time must not be more than 31 days after start_time.
in: query
required: true
schema:
type: string
format: date-time
- name: usageType
description: >-
Usage type to query usage for
If not specified, returns all usage types (both serverless and
dedicated deployments).
- USAGE_TYPE_UNSPECIFIED: Default value. When specified (or when usage_type field is not set),
returns usage data for all deployment types: both serverless
requests and dedicated deployments.
- SERVERLESS: Returns only serverless usage data.
Filters the response to include only usage from serverless API
requests.
- DEDICATED_DEPLOYMENT: Returns only dedicated deployment usage data.
Filters the response to include only usage from dedicated
deployments.
in: query
required: false
schema:
type: string
enum:
- USAGE_TYPE_UNSPECIFIED
- SERVERLESS
- DEDICATED_DEPLOYMENT
default: USAGE_TYPE_UNSPECIFIED
- name: timezone
description: >-
IANA timezone identifier for daily aggregation (e.g.,
"America/Los_Angeles", "Europe/London").
When specified, the returned data will be aggregated into daily
buckets based on this timezone.
If not specified or empty, defaults to "UTC".
See: https://en.wikipedia.org/wiki/List_of_tz_database_time_zones
in: query
required: false
schema:
type: string
- name: groupBy
description: >-
Dimension to group usage by (at most one value; repeated for wire
compatibility).
Serverless: "model_name", "api_key_id", "annotations.team",
"annotations.project", "annotations.environment".
Dedicated: "deployment_name", "accelerator_type", and the same
annotation keys.
When usage_type is unspecified, dimensions that apply only to the
other stream are ignored there
(e.g. "deployment_name" and "accelerator_type" are ignored for
serverless; "model_name" and "api_key_id" for dedicated).
Example: ["annotations.team"] or ["model_name"].
If empty: serverless aggregates by model name; dedicated defaults to
deployment and accelerator type.
in: query
required: false
explode: true
schema:
type: array
items:
type: string
- name: filter
description: >-
This is a request variable of the map type. The query format is
"map_name[key]=value", e.g. If the map name is Age, the key type is
string, and the value type is integer, the query parameter is
expressed as Age["bob"]=18
in: query
required: false
schema:
type: string
- name: account_id
in: path
required: true
description: The Account Id
schema:
type: string
tags:
- gateway.openapi_Gateway
security:
- BearerAuth: []
/v1/accounts/{account_id}/checkpoints/{checkpoint_id}:promote:
servers:
- url: https://api.fireworks.ai
post:
summary: >-
Promote a checkpoint to a model.
The checkpoint is identified by account + snapshot ID; the trainer job
ID
is passed in the request body to resolve the GCS bucket.
operationId: Gateway_PromoteCheckpoint
responses:
'200':
description: A successful response.
content:
application/json:
schema:
$ref: '#/components/schemas/gatewayPromoteCheckpointResponse'
parameters:
- name: account_id
in: path
required: true
description: The Account Id
schema:
type: string
- name: checkpoint_id
in: path
required: true
description: The Checkpoint Id
schema:
type: string
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/GatewayPromoteCheckpointBody'
required: true
tags:
- gateway.openapi_Gateway
security:
- BearerAuth: []
/v1/accounts/{account_id}/clusters:
servers:
- url: https://api.fireworks.ai
get:
summary: List Clusters
operationId: Gateway_ListClusters
responses:
'200':
description: A successful response.
content:
application/json:
schema:
$ref: '#/components/schemas/gatewayListClustersResponse'
parameters:
- name: pageSize
description: >-
The maximum number of clusters to return. The maximum page_size is
200,
values above 200 will be coerced to 200.
If unspecified, the default is 50.
in: query
required: false
schema:
type: integer
format: int32
- name: pageToken
description: >-
A page token, received from a previous ListClusters call. Provide
this
to retrieve the subsequent page. When paginating, all other
parameters
provided to ListClusters must match the call that provided the page
token.
in: query
required: false
schema:
type: string
- name: filter
description: |-
Only clusters satisfying the provided filter (if specified) will be
returned. See https://google.aip.dev/160 for the filter grammar.
in: query
required: false
schema:
type: string
- name: orderBy
description: >-
A comma-separated list of fields to order by. e.g. "foo,bar"
The default sort order is ascending. To specify a descending order
for a
field, append a " desc" suffix. e.g. "foo desc,bar"
Subfields are specified with a "." character. e.g. "foo.bar"
If not specified, the default order is by "name".
in: query
required: false
schema:
type: string
- name: readMask
description: >-
The fields to be returned in the response. If empty or "*", all
fields will be returned.
in: query
required: false
schema:
type: string
- name: account_id
in: path
required: true
description: The Account Id
schema:
type: string
tags:
- gateway.openapi_Gateway
security:
- BearerAuth: []
post:
summary: Create Cluster
operationId: Gateway_CreateCluster
responses:
'200':
description: A successful response.
content:
application/json:
schema:
$ref: '#/components/schemas/gatewayCluster'
parameters:
- name: account_id
in: path
required: true
description: The Account Id
schema:
type: string
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/GatewayCreateClusterBody'
required: true
tags:
- gateway.openapi_Gateway
security:
- BearerAuth: []
/v1/accounts/{account_id}/clusters/{cluster_id}:
servers:
- url: https://api.fireworks.ai
get:
summary: Get Cluster
operationId: Gateway_GetCluster
responses:
'200':
description: A successful response.
content:
application/json:
schema:
$ref: '#/components/schemas/gatewayCluster'
parameters:
- name: readMask
description: >-
The fields to be returned in the response. If empty or "*", all
fields will be returned.
in: query
required: false
schema:
type: string
- name: account_id
in: path
required: true
description: The Account Id
schema:
type: string
- name: cluster_id
in: path
required: true
description: The Cluster Id
schema:
type: string
tags:
- gateway.openapi_Gateway
security:
- BearerAuth: []
patch:
summary: Update Cluster
operationId: Gateway_UpdateCluster
responses:
'200':
description: A successful response.
content:
application/json:
schema:
$ref: '#/components/schemas/gatewayCluster'
parameters:
- name: account_id
in: path
required: true
description: The Account Id
schema:
type: string
- name: cluster_id
in: path
required: true
description: The Cluster Id
schema:
type: string
requestBody:
content:
application/json:
schema:
type: object
properties:
displayName:
type: string
description: >-
Human-readable display name of the cluster. e.g. "My
Cluster"
Must be fewer than 64 characters long.
createTime:
type: string
format: date-time
description: The creation time of the cluster.
readOnly: true
eksCluster:
$ref: '#/components/schemas/gatewayEksCluster'
fakeCluster:
$ref: '#/components/schemas/gatewayFakeCluster'
state:
$ref: '#/components/schemas/gatewayClusterState'
description: The current state of the cluster.
readOnly: true
status:
$ref: '#/components/schemas/gatewayStatus'
description: >-
Detailed information about the current status of the
cluster.
readOnly: true
updateTime:
type: string
format: date-time
description: The update time for the cluster.
readOnly: true
title: |-
The properties of the cluster being updated. `cluster.name` must
be populated with the updated resource's name.
description: |-
The properties of the cluster being updated. `cluster.name` must
be populated with the updated resource's name.
required: true
tags:
- gateway.openapi_Gateway
security:
- BearerAuth: []
delete:
summary: Delete Cluster
operationId: Gateway_DeleteCluster
responses:
'200':
description: A successful response.
content:
application/json:
schema:
type: object
properties: {}
parameters:
- name: account_id
in: path
required: true
description: The Account Id
schema:
type: string
- name: cluster_id
in: path
required: true
description: The Cluster Id
schema:
type: string
tags:
- gateway.openapi_Gateway
security:
- BearerAuth: []
/v1/accounts/{account_id}/clusters/{cluster_id}:getConnectionInfo:
servers:
- url: https://api.fireworks.ai
get:
summary: Get Cluster Connection Info
description: Retrieve connection settings for the cluster to be put in kubeconfig
operationId: Gateway_GetClusterConnectionInfo
responses:
'200':
description: A successful response.
content:
application/json:
schema:
$ref: '#/components/schemas/gatewayClusterConnectionInfo'
parameters:
- name: readMask
description: >-
The fields to be returned in the response. If empty or "*", all
fields will be returned.
in: query
required: false
schema:
type: string
- name: account_id
in: path
required: true
description: The Account Id
schema:
type: string
- name: cluster_id
in: path
required: true
description: The Cluster Id
schema:
type: string
tags:
- gateway.openapi_Gateway
security:
- BearerAuth: []
/v1/accounts/{account_id}/creditRedemptions:
servers:
- url: https://api.fireworks.ai
get:
summary: List Credit Redemptions
operationId: Gateway_ListCreditRedemptions
responses:
'200':
description: A successful response.
content:
application/json:
schema:
$ref: '#/components/schemas/gatewayListCreditRedemptionsResponse'
parameters:
- name: pageSize
description: The maximum number of redemptions to return
in: query
required: false
schema:
type: integer
format: int32
- name: pageToken
description: A page token, received from a previous ListCreditRedemptions call
in: query
required: false
schema:
type: string
- name: filter
description: Filter string to filter redemptions
in: query
required: false
schema:
type: string
- name: orderBy
description: >-
A comma-separated list of fields to order by. e
# --- truncated at 32 KB (755 KB total) ---
# Full source: https://raw.githubusercontent.com/api-evangelist/fireworks-ai/refs/heads/main/openapi/fireworks-ai-merged-openapi.yml