Lium Public APIs For Providers API
⚙️ **Public Provider APIs** - Open endpoints for providers and validators in the network. No authentication required.
⚙️ **Public Provider APIs** - Open endpoints for providers and validators in the network. No authentication required.
Every API here is available over the APIs.io API and to AI agents over MCP.
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
find_apisBrowse and filter every API in the catalog.get_api_artifactsOne API's artifacts, grouped by type.get_openapiThe primary OpenAPI for this API.find_similar_apisAPIs that look like this one.apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.resolveTurn a domain, URL or GitHub org into the provider it belongs to.find_cohortsEvery scored population of providers in the catalog.curl "https://apis.io/api/v1/apis/lium-io:lium-io-public-apis-for-providers-api"
curl "https://apis.io/api/v1/apis?limit=25"
Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.
Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. By signing up you are subscribing to the APIs.io and API Evangelist newsletters — you can unsubscribe from any issue. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.
openapi: 3.2.0
info:
title: Lium Backend Public APIs For Providers API
description: '## 🚀 Lium Backend API
A comprehensive compute platform that enables users to rent GPU resources from a network of providers/nodes.
*Built with FastAPI, PostgreSQL and Redis.*'
contact:
name: Lium
url: https://lium.io/
email: support@lium.io
license:
name: MIT
url: https://opensource.org/licenses/MIT
version: 1.0.0
servers:
- url: /api
description: Production API
tags:
- name: Public APIs For Providers
description: ⚙️ **Public Provider APIs** - Open endpoints for providers and validators in the network. No authentication required.
paths:
/billing/billing-history/{miner_coldkey}:
get:
tags:
- Public APIs For Providers
summary: Get the billing history for a provider
operationId: billing_history_for_miner_billing_billing_history__miner_coldkey__get
parameters:
- name: miner_coldkey
in: path
required: true
schema:
type: string
title: Miner Coldkey
responses:
'200':
description: Get the billing history for a provider
content:
application/json:
schema:
type: array
items:
$ref: '#/components/schemas/BillingHistoryForMinerResponse'
title: Response Billing History For Miner Billing Billing History Miner Coldkey Get
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
/v1/shared-config:
get:
tags:
- Public APIs For Providers
summary: Get Shared Config
operationId: get_shared_config_v1_shared_config_get
responses:
'200':
description: Successful Response
content:
application/json:
schema:
$ref: '#/components/schemas/SharedConfig'
'304':
description: Unchanged since the ETag sent in If-None-Match
/v1/nvml-driver/report-unknown:
post:
tags:
- Public APIs For Providers
summary: Report Unknown Driver
description: 'Queue an unknown NVIDIA driver for official verification (DAH-2451).
The response carries no verdict: the driver is enqueued (once) and resolved
asynchronously against NVIDIA''s official installer, then published via shared config.'
operationId: report_unknown_driver_v1_nvml_driver_report_unknown_post
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/ReportUnknownDriverRequest'
required: true
responses:
'202':
description: Successful Response
content:
application/json:
schema:
additionalProperties:
type: string
type: object
title: Response Report Unknown Driver V1 Nvml Driver Report Unknown Post
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
security:
- JwtAccessBearer: []
- APIKeyHeader: []
/v1/referral-weights:
get:
tags:
- Public APIs For Providers
summary: Get Referral Weights
description: 'Epoch-stable public feed of each referrer''s referral EMA keyed by SN51 hotkey.
A subnet validator polls this endpoint and pays the EMA through mining emission. The EMA
values only change when the accrue task folds a new epoch (advancing
ReferralFoldState.last_processed_epoch), so the fully-serialized response is cached in Redis
under a key that includes that watermark. Two reads within the same fold-epoch return
byte-identical bodies, and the watermark and weights can never straddle a fold commit
(see :func:`_build_referral_weights_body`).'
operationId: get_referral_weights_v1_referral_weights_get
responses:
'200':
description: Successful Response
content:
application/json:
schema: {}
components:
schemas:
BillingHistoryForMinerResponse:
properties:
billing_day:
type: string
title: Billing Day
amount:
type: number
title: Amount
miner_amount:
type: number
title: Miner Amount
validator_hotkey:
type: string
title: Validator Hotkey
is_declined_for_miner_payment:
type: boolean
title: Is Declined For Miner Payment
declined_reason:
anyOf:
- type: string
- type: 'null'
title: Declined Reason
executor_id_in_subnet:
anyOf:
- type: string
format: uuid
- type: 'null'
title: Executor Id In Subnet
executor_price_per_gpu:
anyOf:
- type: number
- type: 'null'
title: Executor Price Per Gpu
executor_gpu_count:
anyOf:
- type: integer
- type: 'null'
title: Executor Gpu Count
executor_specs:
anyOf:
- $ref: '#/components/schemas/BillingExecutorSpecs'
- type: 'null'
type: object
required:
- billing_day
- amount
- miner_amount
- validator_hotkey
title: BillingHistoryForMinerResponse
HTTPValidationError:
properties:
detail:
items:
$ref: '#/components/schemas/ValidationError'
type: array
title: Detail
type: object
title: HTTPValidationError
BillingExecutorSpecs:
properties:
gpu:
anyOf:
- $ref: '#/components/schemas/BillingGpu'
- type: 'null'
type: object
title: BillingExecutorSpecs
BillingGpu:
properties:
count:
anyOf:
- type: integer
- type: 'null'
title: Count
details:
items:
$ref: '#/components/schemas/BillingGpuDetail'
type: array
title: Details
default: []
type: object
title: BillingGpu
BillingGpuDetail:
properties:
name:
anyOf:
- type: string
- type: 'null'
title: Name
type: object
title: BillingGpuDetail
SharedConfig:
properties:
machine_prices:
additionalProperties:
type: number
type: object
title: Machine Prices
machine_prices_p90:
additionalProperties:
type: number
type: object
title: Machine Prices P90
required_deposit_amount:
additionalProperties:
type: number
type: object
title: Required Deposit Amount
gpu_architectures:
additionalProperties:
additionalProperties: true
type: object
type: object
title: Gpu Architectures
driver_cuda_map:
additionalProperties:
type: number
type: object
title: Driver Cuda Map
nvml_ml_digests:
additionalProperties:
type: string
type: object
title: Nvml Ml Digests
nvml_invalid_drivers:
items:
type: string
type: array
title: Nvml Invalid Drivers
machine_max_price_rate:
type: number
title: Machine Max Price Rate
machine_min_price_rate:
type: number
title: Machine Min Price Rate
soft_limit_price_rate:
type: number
title: Soft Limit Price Rate
default: 1.1
rental_fees_rate:
type: number
title: Rental Fees Rate
collateral_days:
type: integer
title: Collateral Days
collateral_contract_address:
type: string
title: Collateral Contract Address
bittensor_netuid:
type: integer
title: Bittensor Netuid
volume_gb_hour_price_usd:
type: number
title: Volume Gb Hour Price Usd
max_initial_port_count:
type: integer
title: Max Initial Port Count
total_burn_emission:
type: number
title: Total Burn Emission
require_storage_limit_supported:
type: boolean
title: Require Storage Limit Supported
default: false
multinode_clusters_enabled:
type: boolean
title: Multinode Clusters Enabled
default: false
payout_delay_days:
type: integer
title: Payout Delay Days
default: 2
payout_processing_hour_utc:
type: integer
title: Payout Processing Hour Utc
default: 17
default_docker_images:
items:
additionalProperties: true
type: object
type: array
title: Default Docker Images
default:
- image: daturaai/pytorch
tag: 2.12.0-py3.12-cuda12.8-devel-ubuntu24.04-dind
pytorch: 2.12
python: 3.12
cuda: 12.8
ubuntu: 24.04
size: 12022823632
- image: daturaai/pytorch
tag: 2.12.0-py3.12-cuda13.0.2-devel-ubuntu24.04-dind
pytorch: 2.12
python: 3.12
cuda: 13.0
ubuntu: 24.04
size: 12022823632
type: object
required:
- machine_prices
- required_deposit_amount
- gpu_architectures
- driver_cuda_map
- machine_max_price_rate
- machine_min_price_rate
- rental_fees_rate
- collateral_days
- collateral_contract_address
- bittensor_netuid
- volume_gb_hour_price_usd
- max_initial_port_count
- total_burn_emission
title: SharedConfig
ReportUnknownDriverRequest:
properties:
driver_version:
type: string
maxLength: 32
pattern: ^[0-9]+(\.[0-9]+){1,2}$
title: Driver Version
description: NVIDIA driver version the validator could not recognize, e.g. 595.84
type: object
required:
- driver_version
title: ReportUnknownDriverRequest
ValidationError:
properties:
loc:
items:
anyOf:
- type: string
- type: integer
type: array
title: Location
msg:
type: string
title: Message
type:
type: string
title: Error Type
type: object
required:
- loc
- msg
- type
title: ValidationError
securitySchemes:
JwtAccessBearer:
type: http
scheme: bearer
APIKeyHeader:
type: apiKey
in: header
name: X-API-Key