API portal
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.

Limits

How many requests you can make, how much you can spend, and how to see exactly where you stand right now.

Request limits

Per-minute request ceilings are returned by the live /api/v1/limits route. The exact values depend on the authenticated key's current tier and include both requests_per_minute and rungs_per_minute.

Public bearer access currently requires the Developer tier or higher. In the live tier mapping, Developer keys use the Growth envelope (300 requests per minute, 5000000 rungs per minute) and Premium keys use the Scale envelope (1000 requests per minute, 20000000 rungs per minute).

What comes back

{
  "tier": "developer",
  "requests_per_minute": 300,
  "rungs_per_minute": 5000000,
  "monthly_allowance": 10000000,
  "monthly_used": 128400
}

Monthly usage

Current-period usage is returned by /api/v1/usage, historical periods are returned by /api/v1/usage/history, and live allowance totals are returned by /api/v1/limits.

The usage response includes allowance, remaining, and estimated_cost_pence. The current implementation returns 0 for estimated cost rather than a live metered overage calculation.

For the exact JSON contract of those endpoints, use Usage API.

{
  "period_start": "2026-04-01T00:00:00+00:00",
  "period_end": "2026-05-01T00:00:00+00:00",
  "input_rungs": 48100,
  "output_rungs": 80300,
  "total_rungs": 128400,
  "request_count": 93,
  "allowance": 10000000,
  "remaining": 9871600,
  "estimated_cost_pence": 0
}

Rate limit headers

Successful non-stream responses emit the rate headers plus rung-usage headers. 429 responses carry a different envelope: x-ratelimit-limit, x-ratelimit-remaining, x-ratelimit-reset, and retry-after: but no x-evaesi-*-rungs headers, because no inference ran.

HeaderDescription
x-ratelimit-limitRequests-per-minute ceiling
x-ratelimit-remainingRemaining requests in the current minute
x-ratelimit-resetReturned on 429 only. Seconds until the window resets (a delta, not a Unix timestamp)
x-evaesi-input-rungsInput bytes billed for the request
x-evaesi-output-rungsOutput bytes billed for the request
x-evaesi-total-rungsTotal bytes billed for the request
x-evaesi-region-countRegions activated; present only when the request set include_regions: true
retry-afterReturned on 429 responses. Computed from the shared limiter's window and varies. Always read the header rather than assuming a fixed value

Example headers

x-ratelimit-limit: 300
x-ratelimit-remaining: 287
x-evaesi-input-rungs: 29
x-evaesi-output-rungs: 118
x-evaesi-total-rungs: 147

Handling a limit

You receive a 429 RATE_LIMITED response with retry-after, x-ratelimit-reset, and the remaining-request count. Wait the advertised number of seconds before retrying. If a request would exceed a project hard cap instead, the platform returns 402 BUDGET_EXCEEDED before inference is dispatched. See Error Codes for retry guidance.

Tip: Monitor the live rate headers, and, once the console opens at launch, the developer workspace, so you can catch minute throttling, monthly allowance burn, and hard-cap pressure before requests fail.