> ## Documentation Index > Fetch the complete documentation index at: https://docs.platform.toloka.ai/docs/llms.txt > Use this file to discover all available pages before exploring further. # Get a review > Only teams with customer review enabled: other teams get `403 The "customerReview" feature is not enabled for this team`. Return one review with the task content, the quality criteria a reject can name, and every decision so far. ## OpenAPI ````yaml /api-reference/openapi.json get /reviews/{reviewId} openapi: 3.1.0 info: description: >- Manage projects, datasets, labeling pipelines, and model training. **Beta:** endpoints, request and response shapes, and error contracts can change without notice or a backward-compatibility promise. title: Toloka Platform API version: 2.0.0 servers: - url: https://platform.toloka.ai/api/v2-beta security: - apiKeyAuth: [] - scopedTokenAuth: [] tags: - description: The authenticated API key owner. name: Account - description: A project is the container for pipelines, datasets, and files. name: Projects - description: Rows and typed fields. Field schemas are immutable once created. name: Datasets - description: Append rows to a dataset from a file. name: Dataset uploads - description: Read a dataset out as a file. name: Dataset exports - description: A pipeline is a graph of nodes that processes each dataset item. name: Pipelines - description: The nodes, connections, fields, and version of a pipeline graph. name: Pipeline graph - description: Execute a pipeline over a dataset and inspect each item. name: Runs - description: >- Only for teams with customer review enabled. Customer review of generation tasks: the team accepts or rejects every task of a node that uses customer review. name: Reviews - description: Per-node checks that a pipeline must pass before deployment. name: Checks - description: Named credentials available to pipeline code. name: Secrets - description: Project files available to pipeline code and labeling interfaces. name: Files - description: >- Global, read-only catalog of the models a synthetic generation node can use, with their budget bounds. name: Generation models - description: >- Global, read-only catalog of the expert audience: the values a node `audience` filter can use. name: Audience - description: Project lists of experts a node can take its workforce from. name: Expert lists - description: >- Experts banned in a project: they cannot be invited and are removed from the work they are in. Available only to teams with expert lists enabled. name: Expert ban list - description: Global, read-only base model catalog. name: Base models - description: Project-owned mutable model-training drafts. name: Trainings - description: Project-owned Models and immutable Model Versions. name: Models - name: Batch inference paths: /reviews/{reviewId}: get: tags: - Reviews summary: Get a review description: >- Only teams with customer review enabled: other teams get `403 The "customerReview" feature is not enabled for this team`. Return one review with the task content, the quality criteria a reject can name, and every decision so far. operationId: getReview parameters: - in: path name: reviewId required: true schema: $ref: '#/components/schemas/ReviewId' responses: '200': content: application/json: schema: $ref: '#/components/schemas/Review' description: The review headers: RateLimit-Limit: $ref: '#/components/headers/RateLimit-Limit' RateLimit-Policy: $ref: '#/components/headers/RateLimit-Policy' RateLimit-Remaining: $ref: '#/components/headers/RateLimit-Remaining' RateLimit-Reset: $ref: '#/components/headers/RateLimit-Reset' X-Request-Id: $ref: '#/components/headers/X-Request-Id' '403': description: >- Customer review is not enabled for the team of the run, or the scoped token lacks the needed `review` permission. Deciding needs `review:write`, which every preset except `read` and `labeling-read` includes. headers: RateLimit-Limit: $ref: '#/components/headers/RateLimit-Limit' RateLimit-Policy: $ref: '#/components/headers/RateLimit-Policy' RateLimit-Remaining: $ref: '#/components/headers/RateLimit-Remaining' RateLimit-Reset: $ref: '#/components/headers/RateLimit-Reset' X-Request-Id: $ref: '#/components/headers/X-Request-Id' '404': description: Review not found headers: RateLimit-Limit: $ref: '#/components/headers/RateLimit-Limit' RateLimit-Policy: $ref: '#/components/headers/RateLimit-Policy' RateLimit-Remaining: $ref: '#/components/headers/RateLimit-Remaining' RateLimit-Reset: $ref: '#/components/headers/RateLimit-Reset' X-Request-Id: $ref: '#/components/headers/X-Request-Id' '429': description: Rate limit exceeded headers: RateLimit-Limit: $ref: '#/components/headers/RateLimit-Limit' RateLimit-Policy: $ref: '#/components/headers/RateLimit-Policy' RateLimit-Remaining: $ref: '#/components/headers/RateLimit-Remaining' RateLimit-Reset: $ref: '#/components/headers/RateLimit-Reset' X-Request-Id: $ref: '#/components/headers/X-Request-Id' x-codeSamples: - label: TypeScript SDK lang: typescript source: | import { createClient } from "@toloka-platform/sdk"; const client = createClient({ baseUrl: "https://platform.toloka.ai", apiKey: process.env.TOLOKA_API_KEY!, }); const review = await client.reviews.get({ reviewId: "trr.019a0000-0000-7000-8000-000000000001" }); console.log(review); components: schemas: ReviewId: description: Review ID with prefix `trr.`. pattern: >- ^trr\.[0-9a-f]{8}-[0-9a-f]{4}-[7][0-9a-f]{3}-[89ab][0-9a-f]{3}-[0-9a-f]{12}$ type: string Review: description: >- A customer review of one task, with its content, quality criteria and decisions. properties: checkedRejectsLeft: description: >- How many more rejects the LLM QA check will check, out of 10. At 0, accept the task or send a forced reject. maximum: 9007199254740991 minimum: 0 type: integer closedAt: anyOf: - format: date-time pattern: >- ^(?:(?:\d\d[2468][048]|\d\d[13579][26]|\d\d0[48]|[02468][048]00|[13579][26]00)-02-29|\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\d|30)|(?:02)-(?:0[1-9]|1\d|2[0-8])))T(?:(?:[01]\d|2[0-3]):[0-5]\d:[0-5]\d(?:\.\d+)?(?:Z))$ type: string - type: 'null' description: >- Time the review closed, as an ISO 8601 timestamp, or null while it is open. deadlineAt: description: >- Deadline for a decision, as an ISO 8601 timestamp. From then on the review takes no decisions, but it closes a little later: a review waiting for a decision expires shortly after the deadline, and its task is accepted automatically (the expert is paid and the task is billed); a review checking a reject closes when the LLM QA check answers. format: date-time pattern: >- ^(?:(?:\d\d[2468][048]|\d\d[13579][26]|\d\d0[48]|[02468][048]00|[13579][26]00)-02-29|\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\d|30)|(?:02)-(?:0[1-9]|1\d|2[0-8])))T(?:(?:[01]\d|2[0-3]):[0-5]\d:[0-5]\d(?:\.\d+)?(?:Z))$ type: string id: $ref: '#/components/schemas/ReviewId' itemId: $ref: '#/components/schemas/RunItemId' nodeId: description: ID of the generation node whose task is under review. type: string nodeName: description: Name of that generation node. type: string performer: description: Who did the task. properties: expertId: description: ID of the expert who did the task, or null for a synthetic task. type: - string - 'null' type: description: >- `expert` for a human expert, `synthetic` for synthetic generation. enum: - expert - synthetic type: string required: - type - expertId type: object qualityCriteria: description: >- The quality criteria a reject can name, as they were when the task reached review. items: $ref: '#/components/schemas/ReviewQualityCriterion' type: array runId: $ref: '#/components/schemas/RunId' status: $ref: '#/components/schemas/ReviewStatus' submittedAt: description: Time the task was submitted, as an ISO 8601 timestamp. format: date-time pattern: >- ^(?:(?:\d\d[2468][048]|\d\d[13579][26]|\d\d0[48]|[02468][048]00|[13579][26]00)-02-29|\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\d|30)|(?:02)-(?:0[1-9]|1\d|2[0-8])))T(?:(?:[01]\d|2[0-3]):[0-5]\d:[0-5]\d(?:\.\d+)?(?:Z))$ type: string taskContent: description: >- What the task showed and what was submitted. Project files appear as file proxy URLs. properties: input: additionalProperties: {} description: The input values of the task, by field name. propertyNames: type: string type: object output: additionalProperties: {} description: The submitted answer, by field name. propertyNames: type: string type: object required: - input - output type: object verdicts: description: Decisions on this review, oldest first. items: $ref: '#/components/schemas/ReviewVerdict' type: array required: - id - runId - itemId - nodeId - nodeName - status - submittedAt - deadlineAt - closedAt - performer - taskContent - qualityCriteria - verdicts - checkedRejectsLeft type: object RunItemId: description: Run item ID with prefix `plri.`. pattern: >- ^plri\.[0-9a-f]{8}-[0-9a-f]{4}-[7][0-9a-f]{3}-[89ab][0-9a-f]{3}-[0-9a-f]{12}$ type: string ReviewQualityCriterion: description: >- A quality criterion of the reviewed node, as it was when the task reached review. properties: fail: description: What a task that fails this criterion looks like. type: string id: description: Criterion ID to name in a reject. type: string pass: description: What a task that passes this criterion looks like. type: string qualityElement: description: What the criterion checks. type: string required: - id - qualityElement - pass - fail type: object RunId: description: Pipeline run ID with prefix `plr.`. pattern: >- ^plr\.[0-9a-f]{8}-[0-9a-f]{4}-[7][0-9a-f]{3}-[89ab][0-9a-f]{3}-[0-9a-f]{12}$ type: string ReviewStatus: description: >- Review status. `needs_review`: waiting for the first decision. `returned`: the LLM QA check did not confirm the last reject, so the review waits for a new decision. `checking`: the LLM QA check is checking a reject, and decisions are refused until it answers. `accepted`: the team accepted the task. `rejected`: the reject is final, either forced or confirmed by the LLM QA check. `expired`: the deadline passed while the review was open, whether it waited for a decision or was checking a reject the check then did not confirm, so the task was accepted automatically. enum: - needs_review - returned - checking - accepted - rejected - expired type: string ReviewVerdict: description: One decision on a review. properties: comment: description: The comment of a reject; empty for an accept. type: string createdAt: description: Time the verdict was sent, as an ISO 8601 timestamp. format: date-time pattern: >- ^(?:(?:\d\d[2468][048]|\d\d[13579][26]|\d\d0[48]|[02468][048]00|[13579][26]00)-02-29|\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\d|30)|(?:02)-(?:0[1-9]|1\d|2[0-8])))T(?:(?:[01]\d|2[0-3]):[0-5]\d:[0-5]\d(?:\.\d+)?(?:Z))$ type: string criteria: description: IDs of the quality criteria a reject named; empty for an accept. items: type: string type: array decision: description: '`accept` or `reject`.' enum: - accept - reject type: string forced: description: True for a forced reject, which skipped the LLM QA check. type: boolean id: description: Verdict ID with prefix `trv.`. pattern: >- ^trv\.[0-9a-f]{8}-[0-9a-f]{4}-[7][0-9a-f]{3}-[89ab][0-9a-f]{3}-[0-9a-f]{12}$ type: string llmQaCheck: anyOf: - properties: checkedAt: description: Time the check answered, as an ISO 8601 timestamp. format: date-time pattern: >- ^(?:(?:\d\d[2468][048]|\d\d[13579][26]|\d\d0[48]|[02468][048]00|[13579][26]00)-02-29|\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\d|30)|(?:02)-(?:0[1-9]|1\d|2[0-8])))T(?:(?:[01]\d|2[0-3]):[0-5]\d:[0-5]\d(?:\.\d+)?(?:Z))$ type: string reason: description: Why the LLM QA check answered this way. type: string verdict: description: >- `agree`: the evidence holds, so the reject became final. `disagree`: the evidence does not hold, so the review returned for a new decision, or expired if its deadline had passed. `inconclusive`: the check could not decide; the review returned or expired the same way. enum: - agree - disagree - inconclusive type: string required: - verdict - reason - checkedAt type: object - type: 'null' description: >- Answer of the LLM QA check to a reject, or null for an accept, a forced reject, or a check still running. scopedTokenId: anyOf: - pattern: >- ^pst\.[0-9a-f]{8}-[0-9a-f]{4}-[7][0-9a-f]{3}-[89ab][0-9a-f]{3}-[0-9a-f]{12}$ type: string - type: 'null' description: >- ID of the scoped token the verdict was sent with, with prefix `pst.`, or null. source: description: '`ui` for the platform UI, `api` for the API, the CLI or the SDK.' enum: - ui - api type: string userId: description: Platform user ID of the author. type: string required: - id - decision - forced - criteria - comment - source - userId - scopedTokenId - llmQaCheck - createdAt type: object headers: RateLimit-Limit: description: The maximum number of requests allowed in the current window. schema: type: integer RateLimit-Policy: description: The rate limit policy (e.g., "60;w=60"). schema: type: string RateLimit-Remaining: description: The number of requests remaining in the current window. schema: type: integer RateLimit-Reset: description: The number of seconds until the current window resets. schema: type: integer X-Request-Id: description: >- The request id: the X-Request-Id you sent when it is 1-128 characters of letters, digits, ".", "_" or "-", otherwise a generated UUID. Present on every response, including errors; quote it when reporting a problem. schema: type: string securitySchemes: apiKeyAuth: description: >- Enter `ApiKey ` in Authorization, including the `ApiKey ` prefix. In cURL and Python samples, `` means this full value. The TypeScript SDK adds the prefix for you. in: header name: Authorization type: apiKey scopedTokenAuth: description: >- Enter the project-scoped token as `pst_...` in X-Scoped-Token, without an `ApiKey ` prefix. Create a token with POST /projects/{projectId}/tokens. in: header name: X-Scoped-Token type: apiKey ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.