Console coming soon

Browse documentation

Developer docs

Start from a live reference page.

Phone layout stays search-first: pick a page here, then read it in a full single-column view.

Getting Started

OverviewPlatform map, live routes, auth model, and API quick links.QuickstartMake the first live request and inspect the response shape.AuthenticationBearer keys, scopes, rotation, and account-bound access.

Models

EvaEsi InstantByte-native chat with live evidence retrieval. The default model.Instant FastInstant with a shorter evidence gather, for latency-bound work.EvaEsi ReasoningEvidence-gather plus Elements synthesis for harder questions.Reasoning DeepA longer deliberation budget and the widest evidence sweep.Reasoning VerifyChecks claims against evidence and reports what it cannot support.Reasoning FastReasoning held to an interactive latency budget.ElementsCoding and Studio model. Routes directly without the evidence-gather pass.Elements FastSingle-file edits and short-range changes, tuned for latency.Elements CodebaseRepository-wide context for migrations and cross-file work.

API Reference

Responses APICanonical inference route for synchronous requests and output.Sources APIFetch evidence bundles and provenance for prior responses.Usage APICurrent period totals, history windows, and live limits envelopes.Models CatalogEvery model version, its canonical ID and its published rates.Batch APIDurable batches of up to 100 requests: submit, poll, collect.WebhooksSigned event deliveries: envelope, headers, and verification.StreamingServer sent events, frame shapes and handling failures mid stream.SchemaOpenAPI and JSON Schema documents, and generating a client from them.Error CodesOperational error contract, retry semantics, and failure classes.

Operations

Developer ConsoleThe console surfaces that open at launch, mapped honestly.Rungs & PricingBilling units, plan allowances, project budgets, and spend model.Rate LimitsHeaders, envelopes, throttling behavior, and budget enforcement.

Enterprise

EnterpriseReserved and dedicated deployments, isolation, data handling and controls.

Console

API keysIssue, scope and rotate API keys. Opens at launch.UsageRungs consumed, per model and per key. Opens at launch.BillingBudgets, invoices and payment. Opens at launch.SettingsOrganisation, members and security. Opens at launch.

Policies

Terms of ServiceOperational policy, legal terms, or support guidance.Privacy PolicyOperational policy, legal terms, or support guidance.Cookie PolicyOperational policy, legal terms, or support guidance.Community GuidelinesOperational policy, legal terms, or support guidance.Acceptable Use PolicyOperational policy, legal terms, or support guidance.Refund PolicyOperational policy, legal terms, or support guidance.Billing & TiersOperational policy, legal terms, or support guidance.HelpOperational policy, legal terms, or support guidance.API TermsOperational policy, legal terms, or support guidance.AI Use and Output SafetyOperational policy, legal terms, or support guidance.Accessibility StatementOperational policy, legal terms, or support guidance.SecurityOperational policy, legal terms, or support guidance.Service CommitmentsOperational policy, legal terms, or support guidance.SupportOperational policy, legal terms, or support guidance.ContactOperational policy, legal terms, or support guidance.

Sources

Every answer is built from evidence. This is how you fetch that evidence for an answer you already have, while the request is still live.

Endpoint

GET https://evaesi.dev/api/v1/sources/{request_id}

The nested /api/v1/responses/{request_id}/sources route remains mounted as a compatibility alias. Both routes require a valid API key on the Developer tier with the inference scope, and only the account that issued the original request can read its bundle, any other account's key receives 404 SOURCES_NOT_FOUND (any key belonging to the issuing account works; it does not have to be the specific key that made the request).

How long evidence lasts

This endpoint is a live lookup, not a permanent archive. The responses API returns sources_url so clients can re-fetch evidence while the request remains resident in the gateway. Once the live source bundle is gone, the API returns 404 SOURCES_NOT_FOUND.

The response

{
  "request_id": "req_123",
  "model": "instant",
  "sources": [
    {
      "url": "https://example.com/report",
      "domain": "example.com",
      "title": "Example report",
      "tier": "t1_authoritative",
      "retrieved_at": "2026-04-20T12:34:56Z",
      "snippet": "Quoted evidence snippet...",
      "stance": "supports"
    }
  ]
}

Source Fields

Field	Type	Meaning
`request_id`	string	The original inference request ID.
`model`	string?	Model identifier when the gateway still has it. Omitted from the response entirely when unknown, not `null`.
`sources`	array	Live evidence list for the request. Omitted when empty rather than returned as `[]`.
`url`	string	Canonical source URL.
`domain`	string	Domain extracted from the URL.
`title`	string	Human-readable page or document title.
`tier`	enum	Evidence tier, one of `t1_authoritative`, `t2_established`, `t3_community`, `t4_unverified`.
`retrieved_at`	RFC3339 timestamp	When the source was gathered.
`snippet`	string	Short quoted or extracted evidence fragment.
`stance`	enum	How the source relates to the answer: supports, contradicts, mixed, or context.

Errors

404 SOURCES_NOT_FOUND when the gateway no longer has live evidence for that request ID
503 DB_UNAVAILABLE when the database is not available (checked before gateway connectivity)
503 EVA_UNAVAILABLE when the inference gateway is not connected
401 INVALID_API_KEY and related auth failures for missing, expired, or revoked keys
403 INSUFFICIENT_SCOPE when the key lacks the inference scope
429 RATE_LIMITED: this endpoint draws on the same per-minute request budget as inference