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.

Documentation

Everything you need to call EvaEsi from your own code: how requests work, what they cost, and what comes back.

Every request goes to one endpoint, POST /api/v1/responses. You choose a model, send a prompt, and get an answer back along with the evidence behind it. There is an older /api/v1/chat route that still works, but it exists so that integrations written against it keep running. Use responses for anything new.

Rungs

EvaEsi measures and bills in rungs. One rung is one character of output. That is the whole rule.

Most platforms bill in tokens, which puts a tokeniser between your text and your invoice, deciding what your words were worth. Two sentences of the same length can cost different amounts and you cannot tell which until the bill arrives. Rungs remove that step. An answer of 2,000 characters is 2,000 rungs before the model multiplier, so you can work out what a request cost by counting.

Each model carries a multiplier that reflects how hard it works, set per model and per plan, and the rungs you are charged are the output characters times that multiplier. API usage is different again: it is priced per million characters and charged in both directions, which is why the usage API reports what you sent and what came back separately. Pricing has every figure.

Two kinds of route

There are two sets of routes and it is worth knowing which you are looking at, because they authenticate differently.

Routes under /api/v1 are for your code. They take an API key in an Authorization header, and they are what the rest of these pages describe.

Routes under /v1 belong to the browser console and use a signed in session instead of a key. You will not call those directly. They are what the console uses when it opens.

Base URL and keys

The base URL is https://evaesi.dev. Send your key as a bearer token on every request.

Authorization: Bearer esi_dev_YOUR_KEY

Keys are not being issued yet. When the console opens you will create them there, and authentication covers how they are scoped and rotated.

What you can call

EndpointWhat it does
POST /api/v1/responsesAsk a model something. Set stream to get the answer as it is written.
GET /api/v1/sources/{request_id}Fetch the evidence behind an answer you already have.
GET /api/v1/modelsEvery model, its limits, and whether it is available now.
GET /api/v1/usageWhat you have spent this billing period.
GET /api/v1/usage/historyEarlier billing periods, newest first.
GET /api/v1/limitsYour rate limits and how much allowance is left.
POST /api/v1/batchSubmit many requests at once. Not open yet.

Where to start

  • Quickstart gets you a working request in a few minutes.
  • Models explains what each one is for and what it costs.
  • Responses API is the full reference for the endpoint everything runs through.
  • Errors is worth reading before you need it.