> ## Documentation Index > Fetch the complete documentation index at: https://aisa.one/docs/llms.txt > Use this file to discover all available pages before exploring further. > ## Agent Instructions > - Base URLs: models `https://api.aisa.one/v1` (Gemini GenerateContent: `https://api.aisa.one/v1beta`); data APIs `https://api.aisa.one/apis/v1`. The `servers` of each operation in https://aisa.one/openapi.yaml is authoritative. > - Auth: `Authorization: Bearer $AISA_API_KEY`. Never print, log, or commit the key. > - MCP (preferred for agents): `https://mcp.aisa.one/mcp`, signed in with OAuth, so there is no key to paste. > - Agent Skill: `npx skills add AIsa-team/agent-skills --skill aisa`. Fallback with the AIsa CLI: `aisa skills install aisa`. > - Spending: docs, https://aisa.one/models, https://aisa.one/api, `/v1/models`, and MCP `search`, `list_categories`, `get_details`, `batch_quote`, and the `account` operation are free. Quote the exact calls before running them (MCP `batch_quote`, CLI `aisa quote --json`). If the quote reports `auto_execute_eligible: true`, run it unless the user set a tighter limit or asked only for a quote. Otherwise, tell the user in one message the planned calls, the quoted price, and a total USD budget for the task, then wait for approval. Direct HTTP calls follow the stricter rule at https://aisa.one/docs/get-started/cli.md#direct-http-fallback. Do not make paid calls to test availability. Full rule: https://aisa.one/llms.txt # extract > Extracts relevant content from specific web URLs. Usage-based billing; Default request estimate: $0.02 USD (not a fixed price). Account-specific pricing and final settlement may differ. ## Request contract * **Method and path:** POST /apis/v1/parallel/extract * **Availability:** enabled * **Request URL template:** [https://api.aisa.one/apis/v1/parallel/extract](https://api.aisa.one/apis/v1/parallel/extract) * **Runtime facts:** 5d413ff65ac53e696e28c5a12c4dbbb99e94b7667cbafba2e2c6b9da9156a731 [Complete OpenAPI definition](https://aisa.one/docs/openapi/parallel.ai.json) Effective request and pricing declaration (including authentication and referenced schemas): ```json theme={null} { "operationId": "any_parallel_ai_apis_v1_parallel_extract", "method": "POST", "path": "/apis/v1/parallel/extract", "servers": [ { "url": "https://api.aisa.one" } ], "parameters": [], "security": [ { "bearerAuth": [] } ], "requestBody": { "content": { "application/json": { "schema": { "additionalProperties": false, "description": "Extract request.", "properties": { "advanced_settings": { "anyOf": [ { "additionalProperties": false, "description": "Advanced extract configuration.\n\nThese settings may impact result quality and latency unless used carefully.\nSee https://docs.parallel.ai/search/advanced-extract-settings for more info.", "properties": { "excerpt_settings": { "anyOf": [ { "additionalProperties": false, "description": "Optional settings for returning relevant excerpts.", "properties": { "max_chars_per_result": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "description": "Optional upper bound on the total number of characters to include per url. Excerpts may contain fewer characters than this limit to maximize relevance and token efficiency.", "title": "Max Chars Per Result" } }, "title": "V1ExcerptSettings", "type": "object" }, { "type": "null" } ], "description": "Controls excerpt sizes. Provide excerpt settings for fine-grained control, or omit to use defaults." }, "fetch_policy": { "anyOf": [ { "description": "Policy for live fetching web results.", "properties": { "disable_cache_fallback": { "default": false, "description": "If false, fallback to cached content older than max-age if live fetch fails or times out. If true, returns an error instead.", "title": "Disable Cache Fallback", "type": "boolean" }, "max_age_seconds": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "description": "Maximum age of cached content in seconds to trigger a live fetch. Minimum value 600 seconds (10 minutes).", "examples": [ 86400 ], "title": "Max Age Seconds" }, "timeout_seconds": { "anyOf": [ { "type": "number" }, { "type": "null" } ], "description": "Timeout in seconds for fetching live content if unavailable in cache.", "examples": [ 60.0 ], "title": "Timeout Seconds" } }, "title": "FetchPolicy", "type": "object" }, { "type": "null" } ], "description": "Fetch policy: determines when to return cached content from the index (faster) vs fetching live content (fresher). Default is to use a dynamic policy based on the search objective and url. Note: enabling live fetch significantly increases extract latency because it requires fetching content from source websites." }, "full_content": { "anyOf": [ { "description": "Optional settings for returning full content.", "properties": { "max_chars_per_result": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "description": "Optional limit on the number of characters to include in the full content for each url. Full content always starts at the beginning of the page and is truncated at the limit if necessary.", "title": "Max Chars Per Result" } }, "title": "FullContentSettings", "type": "object" }, { "type": "boolean" } ], "default": false, "description": "Controls full content extraction. Set to true to enable with defaults, false to disable, or provide FullContentSettings for fine-grained control.", "title": "Full Content" } }, "title": "AdvancedExtractSettings", "type": "object" }, { "type": "null" } ], "description": "Advanced configuration for fetch policy, excerpt settings, and full content settings. May impact result quality and latency unless used carefully. When omitted, excerpts are enabled and full content is disabled by default." }, "client_model": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "description": "The model generating this request and consuming the results. Enables optimizations and tailors default settings for the model's capabilities.", "examples": [ "claude-opus-4-7", "gpt-5.4", "gemini-3.1-pro" ], "title": "Client Model" }, "max_chars_total": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "description": "Upper bound on total characters across excerpts from all extracted results.", "title": "Max Chars Total" }, "objective": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "description": "As in SearchRequest, a natural-language description of the underlying question or goal driving the request. Used together with search_queries to focus excerpts on the most relevant content.", "title": "Objective" }, "search_queries": { "anyOf": [ { "items": { "type": "string" }, "type": "array" }, { "type": "null" } ], "description": "Optional keyword search queries, as in SearchRequest. Used together with objective to focus excerpts on the most relevant content.", "title": "Search Queries" }, "session_id": { "anyOf": [ { "maxLength": 1000, "type": "string" }, { "type": "null" } ], "description": "Session identifier to track calls across separate search and extract calls, to be used as part of a larger task. Specifying it may give better contextual results for subsequent API calls.", "title": "Session Id" }, "urls": { "description": "URLs to extract content from. Up to 20 URLs.", "items": { "type": "string" }, "title": "Urls", "type": "array" } }, "required": [ "urls" ], "title": "V1ExtractRequest", "type": "object" } } }, "required": true }, "x-aisa-status": "enabled", "x-aisa-pricing": { "cost_contract": "response_count", "customer_multiplier": 1.0, "customer_pricing": "provider_cost_multiplier", "default_request_estimate_usd": 0.02, "estimate_source": "profile_seed", "evidence_source": "response_body" }, "components": { "securitySchemes": { "bearerAuth": { "scheme": "bearer", "type": "http" } } } } ``` ## Cost and request rules Usage-based billing; Default request estimate: \$0.02 USD (not a fixed price). Account-specific pricing and final settlement may differ. Published reference values are not an account-specific quote or a settled charge. For endpoints supporting X-AISA-Cost-Mode: quote, obtain a free quote for your exact request before execution; reconcile the settled cost with response metadata and Usage Logs. USD amounts use 1,000,000 integer micro-USD per dollar. * **Default request reference estimate (USD):** 0.02 * **Cost contract:** response\_count * **Published reference multiplier:** 1.0 * **Settlement evidence source:** response\_body ## OpenAPI ````yaml openapi/parallel.ai.json POST /apis/v1/parallel/extract openapi: 3.1.0 info: description: '' title: Parallel.ai version: '1' x-aisa-capabilities: idempotency: Idempotency-Key max_price: X-AISA-Max-Price-USD quote: header: X-AISA-Cost-Mode value: quote x-aisa-catalogs: parallel.ai: description: '' title: Parallel.ai x-aisa-capabilities: idempotency: Idempotency-Key max_price: X-AISA-Max-Price-USD quote: header: X-AISA-Cost-Mode value: quote x-aisa-document: facts_hash: 5d413ff65ac53e696e28c5a12c4dbbb99e94b7667cbafba2e2c6b9da9156a731 generator_version: '3' protocol_version: '1' schema_version: '1' x-aisa-plans: builder: 1 display_plan: payg payg: 1 similarweb_payg: 1 team: 1 version: e70a0959cd1b93b84ae16dffd7a538273ddb9c1d46277b82823c37ff1b6bc0fb x-aisa-configured-paths: - /apis/v1/parallel/chat/completions - /apis/v1/parallel/extract - /apis/v1/parallel/findall/ingest - /apis/v1/parallel/findall/runs/{findall_id} - /apis/v1/parallel/findall/runs/{findall_id}/cancel - /apis/v1/parallel/findall/runs/{findall_id}/events - /apis/v1/parallel/findall/runs/{findall_id}/result - /apis/v1/parallel/findall/runs/{findall_id}/schema - /apis/v1/parallel/monitors/{monitor_id} - /apis/v1/parallel/monitors/{monitor_id}/cancel - /apis/v1/parallel/monitors/{monitor_id}/events - /apis/v1/parallel/monitors/{monitor_id}/update - /apis/v1/parallel/tasks/groups - /apis/v1/parallel/tasks/groups/{taskgroup_id} - /apis/v1/parallel/tasks/groups/{taskgroup_id}/events - /apis/v1/parallel/tasks/groups/{taskgroup_id}/runs/{run_id} - /apis/v1/parallel/tasks/runs/{run_id} - /apis/v1/parallel/tasks/runs/{run_id}/events - /apis/v1/parallel/tasks/runs/{run_id}/input - /apis/v1/parallel/tasks/runs/{run_id}/result - /apis/v1/parallel/v1beta/tasks/runs/{run_id}/events x-aisa-document: composer_version: '20' document_hash: sha256:faf7bdc612cf28356fbb13a4aafcba6664c0f5f6176fe3ef56b5c4d887f62c03 facts_hash: 5d413ff65ac53e696e28c5a12c4dbbb99e94b7667cbafba2e2c6b9da9156a731 generator_version: '3' protocol_version: '1' response_pending: [] schema_version: '1' x-aisa-plans: builder: 1 display_plan: payg payg: 1 similarweb_payg: 1 team: 1 version: e70a0959cd1b93b84ae16dffd7a538273ddb9c1d46277b82823c37ff1b6bc0fb x-aisa-provider: parallel.ai servers: - url: https://api.aisa.one security: - bearerAuth: [] paths: /apis/v1/parallel/extract: post: tags: - default summary: extract description: >- Extracts relevant content from specific web URLs. Usage-based billing; Default request estimate: $0.02 USD (not a fixed price). Account-specific pricing and final settlement may differ. operationId: any_parallel_ai_apis_v1_parallel_extract requestBody: content: application/json: schema: additionalProperties: false description: Extract request. properties: advanced_settings: anyOf: - additionalProperties: false description: >- Advanced extract configuration. These settings may impact result quality and latency unless used carefully. See https://docs.parallel.ai/search/advanced-extract-settings for more info. properties: excerpt_settings: anyOf: - additionalProperties: false description: >- Optional settings for returning relevant excerpts. properties: max_chars_per_result: anyOf: - type: integer - type: 'null' description: >- Optional upper bound on the total number of characters to include per url. Excerpts may contain fewer characters than this limit to maximize relevance and token efficiency. title: Max Chars Per Result title: V1ExcerptSettings type: object - type: 'null' description: >- Controls excerpt sizes. Provide excerpt settings for fine-grained control, or omit to use defaults. fetch_policy: anyOf: - description: Policy for live fetching web results. properties: disable_cache_fallback: default: false description: >- If false, fallback to cached content older than max-age if live fetch fails or times out. If true, returns an error instead. title: Disable Cache Fallback type: boolean max_age_seconds: anyOf: - type: integer - type: 'null' description: >- Maximum age of cached content in seconds to trigger a live fetch. Minimum value 600 seconds (10 minutes). examples: - 86400 title: Max Age Seconds timeout_seconds: anyOf: - type: number - type: 'null' description: >- Timeout in seconds for fetching live content if unavailable in cache. examples: - 60 title: Timeout Seconds title: FetchPolicy type: object - type: 'null' description: >- Fetch policy: determines when to return cached content from the index (faster) vs fetching live content (fresher). Default is to use a dynamic policy based on the search objective and url. Note: enabling live fetch significantly increases extract latency because it requires fetching content from source websites. full_content: anyOf: - description: Optional settings for returning full content. properties: max_chars_per_result: anyOf: - type: integer - type: 'null' description: >- Optional limit on the number of characters to include in the full content for each url. Full content always starts at the beginning of the page and is truncated at the limit if necessary. title: Max Chars Per Result title: FullContentSettings type: object - type: boolean default: false description: >- Controls full content extraction. Set to true to enable with defaults, false to disable, or provide FullContentSettings for fine-grained control. title: Full Content title: AdvancedExtractSettings type: object - type: 'null' description: >- Advanced configuration for fetch policy, excerpt settings, and full content settings. May impact result quality and latency unless used carefully. When omitted, excerpts are enabled and full content is disabled by default. client_model: anyOf: - type: string - type: 'null' description: >- The model generating this request and consuming the results. Enables optimizations and tailors default settings for the model's capabilities. examples: - claude-opus-4-7 - gpt-5.4 - gemini-3.1-pro title: Client Model max_chars_total: anyOf: - type: integer - type: 'null' description: >- Upper bound on total characters across excerpts from all extracted results. title: Max Chars Total objective: anyOf: - type: string - type: 'null' description: >- As in SearchRequest, a natural-language description of the underlying question or goal driving the request. Used together with search_queries to focus excerpts on the most relevant content. title: Objective search_queries: anyOf: - items: type: string type: array - type: 'null' description: >- Optional keyword search queries, as in SearchRequest. Used together with objective to focus excerpts on the most relevant content. title: Search Queries session_id: anyOf: - maxLength: 1000 type: string - type: 'null' description: >- Session identifier to track calls across separate search and extract calls, to be used as part of a larger task. Specifying it may give better contextual results for subsequent API calls. title: Session Id urls: description: URLs to extract content from. Up to 20 URLs. items: type: string title: Urls type: array required: - urls title: V1ExtractRequest type: object required: true responses: '200': content: application/json: example: errors: - content: Error fetching content from https://www.example.com error_type: fetch_error http_status_code: 500 url: https://www.example.com extract_id: extract_8a911eb27c7a4afaa20d0d9dc98d07c0 results: - excerpts: - Excerpted text ... full_content: Full content ... title: Example Title url: https://www.example.com session_id: session_8a911eb27c7a4afaa20d0d9dc98d07c0 schema: $ref: '#/components/schemas/ResponseB67C75A8Feba_V1ExtractResponse' description: Successful Response default: content: application/json: schema: {} description: >- Error response; upstream passthrough responses may use provider formats components: schemas: ResponseB67C75A8Feba_V1ExtractResponse: description: Extract response. properties: errors: description: 'Extract errors: requested URLs not in the results.' items: $ref: '#/components/schemas/ResponseB67C75A8Feba_ExtractError' title: Errors type: array extract_id: description: Extract request ID, e.g. `extract_cad0a6d2dec046bd95ae900527d880e7` title: Extract Id type: string results: description: Successful extract results. items: $ref: '#/components/schemas/ResponseB67C75A8Feba_V1ExtractResult' title: Results type: array session_id: description: >- Session identifier. Echoed back from the request if provided, otherwise generated by the server. Should be passed to future search and extract calls made by the agent as part of the same larger task. examples: - session_8a911eb27c7a4afaa20d0d9dc98d07c0 title: Session Id type: string usage: anyOf: - items: $ref: '#/components/schemas/ResponseB67C75A8Feba_UsageItem' type: array - type: 'null' description: Usage metrics for the extract request. title: Usage warnings: anyOf: - items: $ref: '#/components/schemas/ResponseB67C75A8Feba_Warning' type: array - type: 'null' description: Warnings for the extract request, if any. title: Warnings required: - extract_id - results - errors - session_id title: V1ExtractResponse type: object ResponseB67C75A8Feba_ExtractError: description: Extract error details. properties: content: anyOf: - type: string - type: 'null' description: Content returned for http client or server errors, if any. title: Content error_type: description: Error type. title: Error Type type: string http_status_code: anyOf: - type: integer - type: 'null' description: HTTP status code, if available. title: Http Status Code url: title: Url type: string required: - url - error_type - http_status_code - content title: ExtractError type: object ResponseB67C75A8Feba_V1ExtractResult: description: Extract result for a single URL. properties: excerpts: description: Relevant excerpted content from the URL, formatted as markdown. items: type: string title: Excerpts type: array full_content: anyOf: - type: string - type: 'null' description: Full content from the URL formatted as markdown, if requested. title: Full Content publish_date: anyOf: - type: string - type: 'null' description: Publish date of the webpage in YYYY-MM-DD format, if available. title: Publish Date title: anyOf: - type: string - type: 'null' description: Title of the webpage, if available. title: Title url: description: URL associated with the search result. title: Url type: string required: - url - excerpts title: V1ExtractResult type: object ResponseB67C75A8Feba_UsageItem: description: Usage item for a single operation. properties: count: description: Count of the SKU. examples: - 1 title: Count type: integer name: description: Name of the SKU. examples: - sku_search - sku_extract_excerpts title: Name type: string required: - name - count title: UsageItem type: object ResponseB67C75A8Feba_Warning: description: Human-readable message for a task. properties: detail: anyOf: - additionalProperties: true type: object - type: 'null' description: Optional detail supporting the warning. title: Detail message: description: Human-readable message. title: Message type: string type: description: >- Type of warning. Note that adding new warning types is considered a backward-compatible change. enum: - spec_validation_warning - input_validation_warning - warning examples: - spec_validation_warning - input_validation_warning title: Type type: string required: - type - message title: Warning type: object securitySchemes: bearerAuth: scheme: bearer type: http ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.