Reliquary
API verifiedreliqua.ai
Decentralized post-training platform for batch generation, model evaluations and planned RL training on distributed GPUs
- Subnet
- SN81
- Category
- Training
- API
- Verified
- Interface
- OpenAI-compatible
- Endpoints
- 8
- Access
- API Key
Researched from the provider's public pages on 2026-11-18. Values may change; the provider's own terms apply. EnterTAO is not affiliated with the provider.
Access manifest
Use this service
How to call it is documented. Your agent needs your own access first (an API key, gamma deposit or x402 wallet), set up at the provider.
This page cannot know what you have set up. Your access (an account, key, deposit or wallet) is set up at the provider; the steps are listed below.
Access methods
API Key (Bearer)
Fully documented- Documented in
- Provider's OpenAPI spec
- Setup
- 2 one-time steps on your machine
- Local variable
- BM_KEY_RELIQUARY
- This provider
- Not tested
- Method tested
- Request handling tested against a mock provider
One-time setup on your machine
- 1
bearerCreate an API key at Reliquary. Paid plans are paid there, not here.
https://app.reliqua.ai/console/run (opens the provider's site in a new tab)
- 2
bearerKeep the key in your own environment, e.g. as BM_KEY_RELIQUARY. Never send it to EnterTAO.
export BM_KEY_RELIQUARY=<YOUR_API_KEY>
Call it
Code examples
curl -s -X POST "https://app.reliqua.ai/api/openai/v1/files" -H "Authorization: Bearer <API_KEY>" -H "content-type: application/json" -d '<JSON body, see docs>'curl -s -X POST "https://app.reliqua.ai/api/openai/v1/batches" -H "Authorization: Bearer <API_KEY>" -H "content-type: application/json" -d '<JSON body, see docs>'curl -s -X GET "https://app.reliqua.ai/api/openai/v1/batches" -H "Authorization: Bearer <API_KEY>"from openai import OpenAI
client = OpenAI(base_url="https://api.reliqua.ai/api", api_key="<API_KEY>")Auth: Authorization: Bearer <API_KEY> · request bodies are in the provider's docs.
For agents
Operations
What an agent can call, with operation_id, parameters and body schema (the access manifest contains the same). Fully documented read/compute operations can be called directly; sensitive or partly documented ones should only run with your human's approval.
POST
/chat/completionsopenai_chat_completionscomputefully documentedChat completion (OpenAI standard)
No path, query or header parameters.
Body (application/json, required): required model, messages
Gaps: model ids are provider-specific: list them with openai_list_models
Source: OpenAI standard
GET
/modelsopenai_list_modelsreadfully documentedList models (OpenAI standard)
No path, query or header parameters.
Source: OpenAI standard
GET
/api/openai/v1/batchesopenaiListBatchesreadfully documentedList batches
Parameters of openaiListBatches Parameter In Type Required limit query integer no after query string no Source: provider's OpenAPI spec
GET
/api/openai/v1/batches/{batch_id}openaiGetBatchreadfully documentedRead a batch
Parameters of openaiGetBatch Parameter In Type Required batch_id path string yes Source: provider's OpenAPI spec
GET
/api/openai/v1/filesopenaiListFilesreadfully documentedList input files
No path, query or header parameters.
Source: provider's OpenAPI spec
GET
/api/openai/v1/files/{file_id}openaiGetFilereadfully documentedRead a file
Parameters of openaiGetFile Parameter In Type Required file_id path string yes Source: provider's OpenAPI spec
GET
/api/openai/v1/files/{file_id}/contentopenaiFileContentreadfully documentedDownload a file
Parameters of openaiFileContent Parameter In Type Required file_id path string yes Source: provider's OpenAPI spec
POST
/api/openai/v1/batchesopenaiCreateBatchcomputepartly documentedCreate a batch
Parameters of openaiCreateBatch Parameter In Type Required Idempotency-Key header string no Body (application/json, required): required input_file_id, endpoint, completion_window
Gaps: request body schema is missing or incomplete (unsupported keywords: propertyNames)
Source: provider's OpenAPI spec
POST
/api/openai/v1/batches/{batch_id}/cancelopenaiCancelBatchcomputepartly documentedCancel a batch
Parameters of openaiCancelBatch Parameter In Type Required batch_id path string yes Gaps: request body is not documented
Source: provider's OpenAPI spec
POST
/api/openai/v1/filesopenaiUploadFilesensitiveneeds your approvalUpload a batch file
No path, query or header parameters.
Body (multipart/form-data, required): required purpose, file
Source: provider's OpenAPI spec
API surface
Endpoints
- openai compatible
https://api.reliqua.ai/apiEndpoint reachable - openai compatible
https://app.reliqua.ai/api/openai/v1Documented - api
https://app.reliqua.aiDocumented - api
https://api.reliqua.aiDocumented
From the provider's OpenAPI description. Summaries are the provider's text.
| Method | Path | Summary (from spec) | Service |
|---|---|---|---|
| GET | /api/openai/v1/batches | List batches | Reliquary SN81 · verified |
| POST | /api/openai/v1/batches | Create a batch | Reliquary SN81 · verified |
| GET | /api/openai/v1/batches/{batch_id} | Read a batch | Reliquary SN81 · verified |
| POST | /api/openai/v1/batches/{batch_id}/cancel | Cancel a batch | Reliquary SN81 · verified |
| GET | /api/openai/v1/files | List input files | Reliquary SN81 · verified |
| POST | /api/openai/v1/files | Upload a batch file | Reliquary SN81 · verified |
| GET | /api/openai/v1/files/{file_id} | Read a file | Reliquary SN81 · verified |
| GET | /api/openai/v1/files/{file_id}/content | Download a file | Reliquary SN81 · verified |
- OpenAPI
- spec (opens the provider's site in a new tab) valid 3.1.1 · 6 paths
- MCP
- — not published
- Last check
- 19 Nov 2026, 14:51 UTC · HTTP 404
Payment
Costs and payment
- Methods
- Not stated by the provider
- Price (as the provider states it)
- No fixed rates published; quotes per request, paid with USD service credits
- No machine-readable per-request price is published; x402 providers state it in their 402 answer.
Who handles your money
Evidence
Tests for this service
No execution or payment test has been run against this provider. Checks above are EnterTAO's unpaid reachability and spec checks. What is tested per access method
Provenance
Sources
- https://www.reliqua.ai/ (opens the provider's site in a new tab)
- https://app.reliqua.ai/docs (opens the provider's site in a new tab)
- https://app.reliqua.ai/docs/api-reference/overview (opens the provider's site in a new tab)
- https://app.reliqua.ai/docs/agents/mcp (opens the provider's site in a new tab)
- https://app.reliqua.ai/docs/openai-batch.openapi.json (opens the provider's site in a new tab)
- https://app.reliqua.ai/docs/getting-started/account-access (opens the provider's site in a new tab)