Qwen3 Rerank evaluates candidate text against a supplied query and ranking instruction. The exact configured selector is qwen3-rerank. Its role is ordering the supplied candidates for retrieval and document-selection work; the request keeps the query, instruction and candidate passages together so the relevance judgment can be traced back to its inputs.
Prepare documents as an array of strings, with one candidate passage in each entry. Keep a separate mapping from each array position to your own document identifier, title or source location. This lets the application reconnect a ranked result with the original passage without adding undocumented identifier objects to the string array. For a support search, the candidates might be the relevant sections already retrieved from a product guide; the query should state the user's actual information need.
The documented request requires model, documents, query, top_n and instruct. The query and instruct fields are strings, and top_n is an explicitly supplied integer. The published example uses three candidate texts, top_n=2 and an instruction to retrieve relevant passages that answer a web-search query. Use instruct to state the relation that matters for the ranking, while keeping the actual question in query and the material to evaluate in documents.
The operation guide lists a maximum input length of 30K. Keep the candidate passages focused on the text needed to judge their relevance, retaining headings or nearby context when those change the meaning. Preserve source boundaries so a selected passage can still be checked in its original document. The exact request profile and its required fields remain the basis for preparing the input.
The returned structured result contains results entries with index and relevance_score. The index refers to the candidate's position in the original documents array, rather than its position in the ranked result list. Keep the returned ordering and use each index to recover the corresponding input text. Preserve every returned result so the application can inspect the selected candidates and their scores together.
Retain the complete JSON response, including its model, response id and usage.total_tokens. The returned document text can be absent, so keep the original candidate array available when processing the indices. The relevance scores and reported usage have separate roles: scores describe the ranking result, while usage records the quantity reported for the operation. Neither replaces the source passage that supports a later answer.
For a retrieval workflow, use the ranking to select the passages that the next step should inspect or cite. Compare a selected passage with the query and instruction before presenting its contents as evidence. A high position in a result list identifies a candidate for review; the application's eventual answer should remain connected to the actual text and its source identifier.
Review the result with representative queries and the candidate sets used by the application. Check that indices resolve to the intended original texts, that the ordering serves the supplied instruction and that the chosen passages address the question. Keep the exact selector, query, instruction, candidate mapping and complete response together, producing a reusable relevance-selection record for the next retrieval or document step.
", "aboutText": "Qwen3 Rerank evaluates candidate text against a supplied query and ranking instruction. The exact configured selector is qwen3-rerank. Its role is ordering the supplied candidates for retrieval and document-selection work; the request keeps the query, instruction and candidate passages together so the relevance judgment can be traced back to its inputs.\n\nPrepare documents as an array of strings, with one candidate passage in each entry. Keep a separate mapping from each array position to your own document identifier, title or source location. This lets the application reconnect a ranked result with the original passage without adding undocumented identifier objects to the string array. For a support search, the candidates might be the relevant sections already retrieved from a product guide; the query should state the user's actual information need.\n\nThe documented request requires model, documents, query, top_n and instruct. The query and instruct fields are strings, and top_n is an explicitly supplied integer. The published example uses three candidate texts, top_n=2 and an instruction to retrieve relevant passages that answer a web-search query. Use instruct to state the relation that matters for the ranking, while keeping the actual question in query and the material to evaluate in documents.\n\nThe operation guide lists a maximum input length of 30K. Keep the candidate passages focused on the text needed to judge their relevance, retaining headings or nearby context when those change the meaning. Preserve source boundaries so a selected passage can still be checked in its original document. The exact request profile and its required fields remain the basis for preparing the input.\n\nThe returned structured result contains results entries with index and relevance_score. The index refers to the candidate's position in the original documents array, rather than its position in the ranked result list. Keep the returned ordering and use each index to recover the corresponding input text. Preserve every returned result so the application can inspect the selected candidates and their scores together.\n\nRetain the complete JSON response, including its model, response id and usage.total_tokens. The returned document text can be absent, so keep the original candidate array available when processing the indices. The relevance scores and reported usage have separate roles: scores describe the ranking result, while usage records the quantity reported for the operation. Neither replaces the source passage that supports a later answer.\n\nFor a retrieval workflow, use the ranking to select the passages that the next step should inspect or cite. Compare a selected passage with the query and instruction before presenting its contents as evidence. A high position in a result list identifies a candidate for review; the application's eventual answer should remain connected to the actual text and its source identifier.\n\nReview the result with representative queries and the candidate sets used by the application. Check that indices resolve to the intended original texts, that the ordering serves the supplied instruction and that the chosen passages address the question. Keep the exact selector, query, instruction, candidate mapping and complete response together, producing a reusable relevance-selection record for the next retrieval or document step.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "491dd974a021369c0bd10f25cbdf756a868775102c2f3825ee2f7fec3becc994", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "en", "methods": [ { "html": "qwen3-rerankQwen3 Rerank orders candidate text for a supplied query and instruction. The exact qwen3-rerank profile accepts text-document lists and returns indexed relevance scores with usage metadata for retrieval and document-selection workflows.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Qwen3 Rerank evaluates candidate text against a supplied query and ranking instruction. The exact configured selector is qwen3-rerank. Its role is ordering the supplied candidates for retrieval and document-selection work; the request keeps the query, instruction and candidate passages together so the relevance judgment can be traced back to its inputs.
Prepare documents as an array of strings, with one candidate passage in each entry. Keep a separate mapping from each array position to your own document identifier, title or source location. This lets the application reconnect a ranked result with the original passage without adding undocumented identifier objects to the string array. For a support search, the candidates might be the relevant sections already retrieved from a product guide; the query should state the user's actual information need.
The documented request requires model, documents, query, top_n and instruct. The query and instruct fields are strings, and top_n is an explicitly supplied integer. The published example uses three candidate texts, top_n=2 and an instruction to retrieve relevant passages that answer a web-search query. Use instruct to state the relation that matters for the ranking, while keeping the actual question in query and the material to evaluate in documents.
The operation guide lists a maximum input length of 30K. Keep the candidate passages focused on the text needed to judge their relevance, retaining headings or nearby context when those change the meaning. Preserve source boundaries so a selected passage can still be checked in its original document. The exact request profile and its required fields remain the basis for preparing the input.
The returned structured result contains results entries with index and relevance_score. The index refers to the candidate's position in the original documents array, rather than its position in the ranked result list. Keep the returned ordering and use each index to recover the corresponding input text. Preserve every returned result so the application can inspect the selected candidates and their scores together.
Retain the complete JSON response, including its model, response id and usage.total_tokens. The returned document text can be absent, so keep the original candidate array available when processing the indices. The relevance scores and reported usage have separate roles: scores describe the ranking result, while usage records the quantity reported for the operation. Neither replaces the source passage that supports a later answer.
For a retrieval workflow, use the ranking to select the passages that the next step should inspect or cite. Compare a selected passage with the query and instruction before presenting its contents as evidence. A high position in a result list identifies a candidate for review; the application's eventual answer should remain connected to the actual text and its source identifier.
Review the result with representative queries and the candidate sets used by the application. Check that indices resolve to the intended original texts, that the ordering serves the supplied instruction and that the chosen passages address the question. Keep the exact selector, query, instruction, candidate mapping and complete response together, producing a reusable relevance-selection record for the next retrieval or document step.
POST /v1/reranktextstructured| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qwen3-rerank Conditions: Literal model selector. | Default— |
Fielddocuments | Typearray | RequirementRequired | Values & limits Conditions: Candidate text passages, kept in their original input order. | Default— |
Fieldquery | Typestring | RequirementRequired | Values & limits Conditions: Relevance query. | Default— |
Fieldtop_n | Typeinteger | RequirementRequired | Values & limits Conditions: Requested number of ranked results; no undocumented minimum, maximum or default is asserted. | Default— |
Fieldinstruct | Typestring | RequirementRequired | Values & limits Conditions: Instruction describing the retrieval task. | Default— |
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, documents, query, top_n, instruct |
Parameteroptional | Contract |
Parametermaterial_types | Contracttext |
Parameteradditional_properties | Contracttrue |
Lifecycle: synchronous
Tariff references do not add request options. Supported parameters are listed for the selected method.
Match each charge to the conditions shown. Use one rate for each set of alternative configurations.
| Configuration | Rate schedule | Billing unit | Charge |
|---|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Billing unit— | Charge Input · Input tokens — / 1K tokens Output · Output tokens — / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| Configurationtotal token | Rate schedule— | Billing unit/ 1K tokens | Charge Input · total token $0.00014 / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "qwen3-rerank",\n "query": "Which passage discusses text ranking?",\n "documents": [\n "Text ranking orders candidate passages by relevance.",\n "Quantum computing studies computation using quantum systems.",\n "Pretrained language models can improve text ranking."\n ],\n "top_n": 2,\n "instruct": "Given a web search query, retrieve relevant passages that answer the query."\n}Read indices and relevance scores and map each index back to your original documents. An echoed document can be absent.
Preserve the original response and request id after an ambiguous send; never replay it.
| Field | Type | Meaning |
|---|---|---|
Fieldresults[].index | Typeinteger | MeaningIndex of the corresponding original input document. |
Fieldresults[].relevance_score | Typenumber | MeaningReturned relevance score. |
Fieldmodel | Typestring | MeaningActual response model. |
Fieldid | Typestring | MeaningActual response identifier. |
Fieldusage.total_tokens | Typeinteger | MeaningMeasured total tokens used for billing. |
| Response | Condition | Next step |
|---|---|---|
Response400 · invalid_request_error | ConditionInvalid JSON or required model selection. | Next stepCorrect the indicated input before a new request. |
Response401 · authentication_error | ConditionInvalid API key. | Next stepUse your valid Ailoot API key. |
Response503 · price_unavailable | ConditionStructured method pricing or admission is unavailable. | Next stepPreserve the original response; do not replay an ambiguous send. |
Ailoot Ultra qwen3-rerank
Use the method paths shown above.