Create a prompt
Submit a text request or read, comment on, or edit one document. Prompt targets support DOCX, Markdown, HTML, and plain text. Convert other upload formats first. Edit access exports clean and tracked-changes DOCX artifacts; read/comment access requires export_document=true to export. A 202 response confirms admission; poll the receipt for completion and inspect incomplete and stop_reason even on success. Use /v1/models for supported providers and models.
TypeScript
Authorizations
Revise API key from https://revise.io/console/api-keys. Send Authorization: Bearer .
Headers
1 - 200Body
Submit text-only work or one document target. comment/edit access and export require a document. Native web search is enabled. The resolved provider credential is pinned at submission; replacing or deleting it can fail the next model call without managed fallback. See the guides for pricing, continuation, and retention.
Nonempty instruction, at most 1 MiB of UTF-8 bytes. The entire JSON body is limited to 2 MiB.
1 - 1048576read, comment, edit Latest successful head of the same conversation, with retained content and no active successor. Cannot be combined with inputs. Inherits provider/model and omitted response options; document_access still defaults to read. Encrypted-output requests cannot be continued.
At most one target, with exactly one file_id or artifact_id. Uploaded targets support DOCX, Markdown, HTML, and text. Direct artifact inputs require input_eligible=true and an unencrypted new request.
1- Option 1
- Option 2
Export clean and tracked-changes DOCX artifacts for read/comment requests. edit always exports. Requires a target.
Optional execution and spending thresholds. Spending limits are opt-in: omitted cost limits are unlimited. The time limit defaults to 900 seconds. Prompt platform cost is base fee plus tool CPU; conversion platform cost is its flat/page fee. Prompt cost limits may each be at most $500,000; conversion cost limits may each be at most $1,000,000. These thresholds do not reserve account credit.
Up to 16 string values for application attribution. Keys are 1–64 UTF-8 bytes; values at most 512 UTF-8 bytes. Metadata is deleted with request content; persist your own job mapping for long-term attribution.
Encrypt exported artifact bytes using compact JWE, RSA-OAEP-256 and A256GCM. Only encrypted files are downloadable. Disables prompt continuation and artifact reuse; cannot be combined with previous_prompt_id or artifact_id input. Prompts require editing or export_document=true.
Persisted response policy. False omits the corresponding top-level JSON field from submission, polling, history and replay responses; it does not change the document or native state. Omitted options inherit from an unencrypted predecessor or reused artifact, otherwise default to true.
Response
Admission receipt, including on idempotent replay. May already be running or terminal. Save the ID and poll for the result.
queued, running, paused, succeeded, failed, cancelled Customer-facing settled charges and usage. Supplier costs, margins and internal reconciliation diagnostics are not exposed. Historical charges are never recalculated using current prices.
Up to 16 string values for application attribution. Keys are 1–64 UTF-8 bytes; values at most 512 UTF-8 bytes. Metadata is deleted with request content; persist your own job mapping for long-term attribution.
Non-secret ID of the key that originally submitted this prompt; null when not recorded. Idempotent retries preserve the original key.
True disables continuation and reuse. Artifacts are encrypted for the supplied public key.
24 hours after terminal completion. Result content and new continuation become unavailable at this deadline.
True when the request returned a partial result.
Flat native comment records; replies use parentId. Omitted when disabled by response_options or when content is unavailable.
Pending native tracked changes. Replacements can appear as linked insertion/deletion entries. Omitted when disabled by response_options or when content is unavailable.
Limit that ended further agent work. The current result is returned; successful partial results incur the base fee even without inference, plus actual billable usage.
spending_limit, time_limit