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.

Quickstart

Your first EvaEsi request, start to finish, in about two minutes.

Get a key

Keys come from the console, which opens when the platform launches. They are not being issued yet, so you cannot run the request below today. Everything else on this page is accurate, and the moment you hold a key it will work as written.

A key looks like esi_dev_a1b2c3d4e5f6... and you will see it once. Store it somewhere safe when you create it. If you lose it, revoke it and make another rather than hunting for it. Public API access needs the Developer tier or higher.

Keep the key out of your code. The samples here read it from an environment variable, which is the least you should do.

Make a request

Send a prompt and name a model. max_output_rungs caps how much the answer can cost you, and is worth setting while you are experimenting.

curl https://evaesi.dev/api/v1/responses \  -H "Authorization: Bearer $EVAESI_API_KEY" \  -H "Content-Type: application/json" \  -d '{    "model": "instant",    "prompt": "Explain quantum entanglement in simple terms.",    "max_output_rungs": 512  }'

Read the response

{  "request_id": "uuid",  "content": "Quantum entanglement is...",  "sources": [],  "sources_url": "/api/v1/sources/uuid",  "usage": {    "input_rungs": 52,    "output_rungs": 847,    "total_rungs": 899,    "regions_activated": null  },  "model": "instant"}

The answer is in content. Keep request_id if you want to come back to this request later, either to fetch its evidence or to find it in your usage records.

sources holds the evidence the model used, and sources_url is where to fetch it again while the request is still live. See the sources API.

usage tells you what it cost. Input and output are counted separately because they are priced separately.

Headers

A normal response carries the cost and your rate limit position.

x-evaesi-input-rungs: 52
x-evaesi-output-rungs: 847
x-evaesi-total-rungs: 899
x-ratelimit-limit: 300
x-ratelimit-remaining: 299

x-evaesi-region-count appears as well, but only if you asked for it with include_regions.

Streaming is different, and the difference catches people out. Headers are sent when the stream opens, before any answer exists, so the output and total counts cannot be there yet. You get the input cost and your rate limit position, and the usage object arrives at the end on the response.completed event. Streaming covers the rest.

Where to go next

  • Responses API documents every field on the request and the reply.
  • Streaming shows you how to display an answer as it is written.
  • Models helps you pick something other than the default.
  • Errors lists what can go wrong and what to do about it.
  • Pricing explains rungs and what each model costs.