dev.cocore.inference.submit

Submit an inference request for the authenticated requester. Builds a (paymentAuthorization, job) pair scoped to the configured exchange, publishes both to the requester's PDS, and returns the job/authorization URIs so the caller can poll for a receipt via `dev.cocore.inference.status`.

Repository @cocore.dev did:plc:5quuhkmwe2q4k3azfsgg7kdz namespace authority
Details · procedure
Kindprocedure
Authorityinference.cocore.dev
Indexed

Procedure

procedure · POST

Input

application/json

maxTokensOut

requiredinteger
  • minimum: 1

model

requiredstring

Opaque model identifier honored by the provider.

  • minLength: 1

Optional JSON Schema to constrain the model output. When present, the published job record carries this schema and the provider passes it to the inference engine as response_format guided decoding. The schema is public (not encrypted) — it describes the output shape, not the input.

priceCeiling

requiredobject

Maximum the requester will pay. Integer minor units plus an ISO 4217 / XBT-style currency code.

prompt

requiredstring
  • minLength: 1

Optional tool choice strategy. 'auto' (default), 'none', or 'required'. Additive.

  • knownValues: auto | none | required

When toolChoice is 'required', force the model to call this specific function. Maps to OpenAI tool_choice object form. Additive.

  • maxLength: 256

tools

array

Optional list of tool/function definitions the model may call. Public (not encrypted). The published job record carries this list and the provider passes it to the inference engine.

  • maxLength: 128
itemsobject

Output

application/json

authUri

requiredstring · at-uri

inputCommitment

requiredstring

SHA-256 (lowercase hex) over the input bytes.

jobUri

requiredstring · at-uri

Errors

AuthRequired

The caller is not authenticated.

InvalidRequest

The body failed validation.

Similar lexicons

semantic match

Lexicons whose schemas describe something close to this one. Check them before publishing a new one that overlaps.

  • A request for computational work. Published by the requester in their own repo before the work runs, so the provider has something to commit a receipt against.

  • Submit an inference request and stream the result back as Server-Sent Events. Authenticates the requester, runs the dispatch core, and emits typed SSE frames. Unlike `submit` (which returns URIs to poll), `dispatch` drives the full request and streams plaintext output chunks until completion. Confidentiality: by default the AppView seals the prompt to the chosen provider on the caller's behalf (`best-effort` tier) — convenient, but the AppView is in the plaintext path. A caller that needs priva