api reference
curl https://api.hawktalk.ai/v1/*

API primer.

One key, one base URL, three interfaces. The HawkTalk models — the Hawk Alpha family — served on AWS Inferentia, reachable over REST, WebSockets, and HawkTalkLive. Everything here is the same auth, the same models, the same trace format.

authmodelsinterfacesrate limitserrorstracing

Authentication

Every request is authenticated with a bearer key from your dashboard. REST + WS take it as a header or a session.start field; keep it server-side.

Base URL   https://api.hawktalk.ai
Header     Authorization: Bearer $HAWKTALK_API_KEY

Models — the Hawk Alpha family

Tiny-to-capable, all function-calling native, all runnable on-device and served in the cloud. Pick the smallest one that clears your task; escalate up the family (or up the Blade Frontier) only when you need to.

model idrolegood for
hawk-saplingsmallest · fastestClassification, routing, tight function-calling. Sub-second on the edge.
hawk-feedseedgrounded / retrievalRAG, extraction, answers pinned to your data.
hawk-sakurabalanced · conversationalEveryday voice + chat, the default for assistants.
hawk-oaklargest · most capableComplex reasoning, multi-tool agents, the hard turns.

Voices are separate from models — pass voice: "af_heart" (and others) on any streaming tier.

Three interfaces, one engine

interfaceendpointuse it for
RESTPOST /v1/generateOne-shot text + function-calling. Stateless, everywhere.
WebSocketswss /v1/streamToken-by-token + streamed voice, barge-in. "Realtime."
HawkTalkLivewss /v1/liveReactive-state voice — text, tools, thinking & async on independent channels.

Rate limits by plan

planmodel accessthroughputlive tier
Pro $120/yrSapling → SakuraStandard · batched under load
Dev $600/yrFull family, incl. hawk-oakHigher concurrency + priority · generous creditsCapped rates
Freedom $3000/yrFull familyFlat per-1M-token · dedicated dl2q · no capsIncluded

Full trace logs on every plan. See pricing for the breakdown.

Errors

Standard HTTP status + a typed JSON body. Retriable errors set retry_after.

statuscodemeaning
400invalid_requestMalformed body or unknown field.
401unauthorizedMissing or bad API key.
404unknown_modelThat model id isn't in the family.
429rate_limitedOver your plan's throughput — back off retry_afters.
503capacityTier saturated; retry or step down a model.

Tracing & audit

Every response — REST, WS, or Live — carries a trace_id. Pull the full, human-readable trace of exactly what ran (tokens, tool calls, channel activity) from the dashboard or the API. Built on mkmdmcp principles: nothing the engine does is a black box.

curl https://api.hawktalk.ai/v1/traces/trc_c14a90 \
  -H "Authorization: Bearer $HAWKTALK_API_KEY"