> ## Documentation Index > Fetch the complete documentation index at: https://docs.cloud.gomry.com/llms.txt > Use this file to discover all available pages before exploring further. # One model call, priced per token, at three grades — with the routing, compression and caching that make the cheap grade cheap. > One model call, priced per token, at three grades — with the routing, compression and caching that make the cheap grade cheap. Requires the `inference:run` scope, and the project must have Ember enabled. Billed on success. The response reports `usage` — the quantity metered for this call. Rates: https://docs.cloud.gomry.com/pricing. Full reference: https://docs.cloud.gomry.com/services/inference ## OpenAPI ````yaml /openapi.json post /v1/inference openapi: 3.1.0 info: title: Gomry Cloud API summary: >- Developer APIs from Gomry. Metered per request, priced per unit, billed monthly — no plans, no seats, no free tier to outgrow. description: >- Gomry Cloud sells the technical services Gomry built to run its own event platform as metered HTTP APIs. Authentication is an API key sent as a bearer token. Billing is postpaid and metered: you are charged per unit consumed, invoiced monthly, and only for work that produced a result. There is no free tier — an active payment method is required before any API will serve. Rate limits are applied per API key, not per IP. Guides, errors and rates: https://docs.cloud.gomry.com version: 1.0.0 termsOfService: https://gomry.com/terms contact: name: Gomry Cloud support url: https://docs.cloud.gomry.com servers: - url: https://api.cloud.gomry.com description: Production data plane security: - bearerAuth: [] tags: - name: Scrape description: Fetch a page and extract structured data from it against a JSON schema. externalDocs: url: https://docs.cloud.gomry.com/services/scrape - name: ToolsAPI description: >- Find a tool that can do a task and run it — 1,700+ across 55+ vendors, on your Gomry key. externalDocs: url: https://docs.cloud.gomry.com/services/toolsapi - name: Superagent description: >- Give it a research question and a JSON schema. It plans, searches, reads, notices what is missing, searches again — and cites every field. externalDocs: url: https://docs.cloud.gomry.com/services/tasks - name: Ember description: >- One model call, priced per token, at three grades — with the routing, compression and caching that make the cheap grade cheap. externalDocs: url: https://docs.cloud.gomry.com/services/inference externalDocs: description: Gomry Cloud documentation url: https://docs.cloud.gomry.com paths: /v1/inference: post: tags: - Ember summary: >- One model call, priced per token, at three grades — with the routing, compression and caching that make the cheap grade cheap. description: >- One model call, priced per token, at three grades — with the routing, compression and caching that make the cheap grade cheap. Requires the `inference:run` scope, and the project must have Ember enabled. Billed on success. The response reports `usage` — the quantity metered for this call. Rates: https://docs.cloud.gomry.com/pricing. Full reference: https://docs.cloud.gomry.com/services/inference operationId: inference_post_v1_inference parameters: [] requestBody: required: true content: application/json: schema: type: object required: [] properties: capability: description: >- Required. cheap | balanced | strong. Chooses the price/quality grade, never a specific model. system: description: >- Required. 1–20000 characters of instruction. Treat it as yours: nothing is prepended. user: description: >- Required. 1–400000 characters. The content to work on. Long inputs are trimmed to the model's window, head first. jsonSchema: description: >- A JSON Schema object. Sent as a constrained-decoding hint where the vendor supports it; always parse defensively, because some ignore it. maxOutputTokens: description: >- Caps the answer. 1–16384, and never raised above the capability's own ceiling. Remember that thinking tokens count against it, and check `usage.truncated` — a call that hits the ceiling still returns 200. effort: description: >- minimal | low | default. Lowers the thinking budget on a call that does not need to reason. Ignored by vendors that do not support it. timeoutMs: description: >- Milliseconds before the vendor call is abandoned. Can only tighten the capability's own timeout, never extend it. noCache: description: >- Skip the result cache for this call. Default false. A cache hit bills the same as a live call — it is our cost that changed, not your result. example: capability: cheap system: You extract structured data. Answer with one JSON object. user: Event page text here. Return the name and start date. jsonSchema: type: object properties: name: type: string startDate: type: string responses: '200': description: Success. `usage` reports what was metered. headers: x-request-id: schema: type: string description: >- Echoed or generated per request. Capture it — an intermittent failure cannot be traced without it. x-ratelimit-remaining: schema: type: integer description: Requests left in the current window for this key. x-ratelimit-reset: schema: type: integer description: Unix timestamp in milliseconds at which the window resets. content: application/json: schema: type: object '400': description: '`validation_error` — the body failed schema validation.' headers: x-request-id: schema: type: string description: >- Echoed or generated per request. Capture it — an intermittent failure cannot be traced without it. x-ratelimit-remaining: schema: type: integer description: Requests left in the current window for this key. x-ratelimit-reset: schema: type: integer description: Unix timestamp in milliseconds at which the window resets. content: application/json: schema: $ref: '#/components/schemas/Error' '401': description: >- `unauthorized` — key missing, malformed, unknown, revoked or expired. headers: x-request-id: schema: type: string description: >- Echoed or generated per request. Capture it — an intermittent failure cannot be traced without it. x-ratelimit-remaining: schema: type: integer description: Requests left in the current window for this key. x-ratelimit-reset: schema: type: integer description: Unix timestamp in milliseconds at which the window resets. content: application/json: schema: $ref: '#/components/schemas/Error' '402': description: >- `billing_required`, `billing_past_due`, `billing_suspended` or `insufficient_credit` — spending is blocked until a human adds a card, fixes one, or raises the project budget. Do not retry in a loop. headers: x-request-id: schema: type: string description: >- Echoed or generated per request. Capture it — an intermittent failure cannot be traced without it. x-ratelimit-remaining: schema: type: integer description: Requests left in the current window for this key. x-ratelimit-reset: schema: type: integer description: Unix timestamp in milliseconds at which the window resets. content: application/json: schema: $ref: '#/components/schemas/Error' '403': description: >- `forbidden` (the key lacks the scope) or `api_not_enabled` (the project has not enabled this API). headers: x-request-id: schema: type: string description: >- Echoed or generated per request. Capture it — an intermittent failure cannot be traced without it. x-ratelimit-remaining: schema: type: integer description: Requests left in the current window for this key. x-ratelimit-reset: schema: type: integer description: Unix timestamp in milliseconds at which the window resets. content: application/json: schema: $ref: '#/components/schemas/Error' '404': description: >- `not_found` — the addressed resource does not exist, or is not yours to see. headers: x-request-id: schema: type: string description: >- Echoed or generated per request. Capture it — an intermittent failure cannot be traced without it. x-ratelimit-remaining: schema: type: integer description: Requests left in the current window for this key. x-ratelimit-reset: schema: type: integer description: Unix timestamp in milliseconds at which the window resets. content: application/json: schema: $ref: '#/components/schemas/Error' '429': description: '`rate_limited` — back off until `x-ratelimit-reset`, with jitter.' headers: x-request-id: schema: type: string description: >- Echoed or generated per request. Capture it — an intermittent failure cannot be traced without it. x-ratelimit-remaining: schema: type: integer description: Requests left in the current window for this key. x-ratelimit-reset: schema: type: integer description: Unix timestamp in milliseconds at which the window resets. content: application/json: schema: $ref: '#/components/schemas/Error' '500': description: >- `internal_error` — a fault on our side. Retry, and send us the `x-request-id`. headers: x-request-id: schema: type: string description: >- Echoed or generated per request. Capture it — an intermittent failure cannot be traced without it. x-ratelimit-remaining: schema: type: integer description: Requests left in the current window for this key. x-ratelimit-reset: schema: type: integer description: Unix timestamp in milliseconds at which the window resets. content: application/json: schema: $ref: '#/components/schemas/Error' '502': description: >- `upstream_error` — a provider we depend on failed. Retryable, and not billed. headers: x-request-id: schema: type: string description: >- Echoed or generated per request. Capture it — an intermittent failure cannot be traced without it. x-ratelimit-remaining: schema: type: integer description: Requests left in the current window for this key. x-ratelimit-reset: schema: type: integer description: Unix timestamp in milliseconds at which the window resets. content: application/json: schema: $ref: '#/components/schemas/Error' '503': description: >- `provider_unavailable` — the service is not currently configured to serve. Retryable. headers: x-request-id: schema: type: string description: >- Echoed or generated per request. Capture it — an intermittent failure cannot be traced without it. x-ratelimit-remaining: schema: type: integer description: Requests left in the current window for this key. x-ratelimit-reset: schema: type: integer description: Unix timestamp in milliseconds at which the window resets. content: application/json: schema: $ref: '#/components/schemas/Error' components: schemas: Error: type: object required: - error properties: error: type: string description: Stable machine-readable code. Branch on this, never on `message`. message: type: string description: Human-readable detail. Written for a person and may be reworded. securitySchemes: bearerAuth: type: http scheme: bearer description: >- An API key minted in the console, sent as `Authorization: Bearer `. Keys are project-scoped and carry per-operation scopes. A `gck_test_…` key runs the full request path — including the real upstream call — and bills nothing. Every scope is enumerated in `x-scopes` below and in the RFC 9728 protected-resource metadata at https://cloud.gomry.com/.well-known/oauth-protected-resource, which is also what a `401` points at through its `WWW-Authenticate: Bearer resource_metadata="…"` header. x-scopes: scrape:run: 'Grants: POST /v1/scrape.' scrape:fetch: 'Grants: POST /v1/fetch.' toolsapi:run: 'Grants: POST /v1/toolsapi/run.' toolsapi:read: >- Grants: POST /v1/toolsapi/discover, POST /v1/toolsapi/inspect, GET /v1/toolsapi/runs/{runId}. tasks:run: 'Grants: POST /v1/superagent.' tasks:read: 'Grants: GET /v1/superagent/{taskId}, DELETE /v1/superagent/{taskId}.' inference:run: 'Grants: POST /v1/inference.' x-protected-resource-metadata: https://cloud.gomry.com/.well-known/oauth-protected-resource x-credential-issuance-endpoint: https://cloud.gomry.com/sign-in x-agent-instructions: https://cloud.gomry.com/auth.md ````