> ## Documentation Index > Fetch the complete documentation index at: https://docs.octen.ai/llms.txt > Use this file to discover all available pages before exploring further. # Deep Research > Generates a deep research report. Always returns Server-Sent Events. **Two-phase invocation** - **Phase 1:** the server generates a research plan. If the plan has no ambiguity, the server proceeds directly to research and streams the final report. If the plan is ambiguous, the `plan` event carries `requires_selection=true` together with a `plan_id`, and the SSE stream ends there — waiting for the client to confirm. - **Phase 2:** call this endpoint again with the `plan_id` and `selections`. The server loads the stored plan, applies the selections, and streams the final report. **Notes** - Phase 2 only inherits the stored `plan` via `plan_id`. Other parameters are NOT inherited from Phase 1 — they must be supplied again in Phase 2, otherwise they fall back to defaults. - `messages` is required in both phases and should carry the same user question. ## OpenAPI ````yaml /api-reference/openapi.json post /v1/research openapi: 3.1.0 info: title: Octen API description: >- Octen API provides Search, Extract, Embeddings, VL Embeddings, Web Chat, Broad Search, and Deep Research services. The Search API searches ranked web results with optional filters, highlights, and full content. The Extract API extracts clean markdown content from URLs, with optional query-focused highlights, page classification, and multimedia resources. The Embeddings API converts text into vector representations. The VL Embeddings API converts multimodal inputs (text, images, videos) into vector representations. The Web Chat API provides LLM chat completions with search augmentation. The Broad Search API automatically decomposes queries into multiple sub-queries for comprehensive search and synthesis. The Deep Research API runs a multi-round adaptive research pipeline that produces a structured research plan, executes iterative web searches, builds a report brief with evidence, and streams a final long-form report. version: 1.0.0 servers: - url: https://api.octen.ai security: - apiKeyAuth: [] paths: /v1/research: post: summary: Deep Research description: >- Generates a deep research report. Always returns Server-Sent Events. **Two-phase invocation** - **Phase 1:** the server generates a research plan. If the plan has no ambiguity, the server proceeds directly to research and streams the final report. If the plan is ambiguous, the `plan` event carries `requires_selection=true` together with a `plan_id`, and the SSE stream ends there — waiting for the client to confirm. - **Phase 2:** call this endpoint again with the `plan_id` and `selections`. The server loads the stored plan, applies the selections, and streams the final report. **Notes** - Phase 2 only inherits the stored `plan` via `plan_id`. Other parameters are NOT inherited from Phase 1 — they must be supplied again in Phase 2, otherwise they fall back to defaults. - `messages` is required in both phases and should carry the same user question. operationId: deep-research requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/DeepResearchRequest' examples: phase1: summary: Phase 1 — Initial request value: model: minimax/minimax-m2.5 messages: - role: user content: Progress and key milestones of the Artemis program max_tokens: 20000 reasoning: effort: medium web_search_options: count: 10 highlight: enable: true max_tokens: 300 phase2: summary: Phase 2 — Continue with plan_id and selections value: model: minimax/minimax-m2.5 messages: - role: user content: Progress and key milestones of the Artemis program max_tokens: 20000 reasoning: effort: medium web_search_options: count: 10 highlight: enable: true max_tokens: 300 plan_id: plan_20260403abc123 selections: - term: Artemis chosen: nasa_program indices: - 0 - 1 - 3 extra_context: >- Focus on developments after 2024; de-emphasize early program background. responses: '200': description: >- Successful Deep Research response. Always streamed as Server-Sent Events. content: application/json: schema: $ref: '#/components/schemas/DeepResearchChunk' examples: streamStatus: summary: 'Streaming chunk — pipeline progress (type: status)' value: type: status request_id: 20260403120000003ABCDE12345 object: research.chunk created: 1775361600 model: minimax/minimax-m2.5 status: Analyzing your question... streamPlan: summary: >- Streaming chunk — research plan (type: plan, requires_selection=true ends the stream) value: type: plan request_id: 20260403120000003ABCDE12345 object: research.chunk created: 1775361600 model: minimax/minimax-m2.5 plan_id: plan_20260403abc123 latency: 4120 plan: title: Artemis program research plan overview: ... interpretations: - term: Artemis meanings: - id: nasa_program label: NASA-led crewed lunar program - id: greek_goddess label: Greek goddess of the hunt and the moon chosen: nasa_program reasoning: >- The user asks about 'progress and milestones', which strongly points to the NASA program. angles: - focus: Artemis I-III mission progress focus_desc: >- Timeline, payloads, and outcomes of launched and upcoming missions interpretation_id: nasa_program queries: - Artemis I mission summary - Artemis II crew launch date - Artemis III lunar landing timeline sub_question_ids: - sq_progress requires_selection: true streamQueries: summary: 'Streaming chunk — sub-queries for this round (type: queries)' value: type: queries request_id: 20260403120000003ABCDE12345 object: research.chunk created: 1775361600 model: minimax/minimax-m2.5 round: 1 latency: 312 queries: - Artemis I mission summary - Artemis II crew launch date - Artemis III lunar landing timeline streamSearchDone: summary: >- Streaming chunk — search results for this round (type: search_done) value: type: search_done request_id: 20260403120000003ABCDE12345 object: research.chunk created: 1775361600 model: minimax/minimax-m2.5 round: 1 latency: 1820 search_result_count: 28 search_results: - query: Artemis I mission summary results: - title: Artemis I Mission Overview - NASA url: https://www.nasa.gov/... highlight: >- Artemis I successfully launched on November 16, 2022... full_content: '' authors: NASA time_published: '2022-12-11T00:00:00Z' time_last_crawled: '2026-04-02T03:18:46Z' latency: 69 streamAnalysis: summary: 'Streaming chunk — per-round findings (type: analysis)' value: type: analysis request_id: 20260403120000003ABCDE12345 object: research.chunk created: 1775361600 model: minimax/minimax-m2.5 round: 1 latency: 2940 analysis: findings: - >- Artemis I completed a 25.5-day uncrewed lunar flyby in November 2022. - >- Artemis II crewed lunar flyby is scheduled for 2026 with a 4-person crew. - >- Artemis III lunar landing has slipped from 2025 to 2027. should_continue: true follow_up_suggestions: - SLS Block 1B upgrade progress - Starship HLS lander test milestones streamBrief: summary: 'Streaming chunk — report outline and evidence (type: brief)' value: type: brief request_id: 20260403120000003ABCDE12345 object: research.chunk created: 1775361600 model: minimax/minimax-m2.5 latency: 5310 brief: report_type: trend total_word_budget: 1800 assertiveness_required: false tables: - table_id: t_milestones title: Artemis mission milestones columns: - Mission - Type - Planned date - Status description: Key milestones across Artemis I-V. placement: sec_timeline outline: - section_id: sec_overview section_title: Program background and goals thesis: >- Artemis is NASA's first crewed lunar program since Apollo, aiming to return astronauts to the lunar surface before 2027. target_words: 300 evidence: - content: Artemis was formally announced by NASA in 2017. source_indices: - 1 confidence: strong unresolved: contradictions: [] weak_claims: - Artemis IV commercial payload manifest unanswered: [] suggested_title: 'Artemis program: from uncrewed flyby to crewed landing' references: - index: 1 url: https://www.nasa.gov/... title: Artemis I Mission Overview streamContent: summary: 'Streaming chunk — incremental report text (type: content)' value: type: content request_id: 20260403120000003ABCDE12345 object: research.chunk created: 1775361600 model: minimax/minimax-m2.5 choices: - index: 0 delta: content: |- ## Program background and goals Artemis finish_reason: null streamFinish: summary: 'Streaming chunk — report stream complete (type: finish)' value: type: finish request_id: 20260403120000003ABCDE12345 object: research.chunk created: 1775361600 model: minimax/minimax-m2.5 latency: 18420 choices: - index: 0 delta: {} finish_reason: stop streamUsage: summary: >- Streaming chunk — usage and totals, last event in the stream (type: usage) value: type: usage request_id: 20260403120000003ABCDE12345 object: research.chunk created: 1775361600 model: minimax/minimax-m2.5 meta: usage: num_search_queries: 14 prompt_tokens: 58210 completion_tokens: 1832 total_tokens: 60042 latency: 32480 total_rounds: 3 total_search_count: 84 '400': description: Missing parameter messages content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' example: code: 400 msg: Missing parameter messages '401': $ref: '#/components/responses/Unauthorized' '403': $ref: '#/components/responses/InsufficientBalance' '429': $ref: '#/components/responses/RateLimited' '500': $ref: '#/components/responses/InternalError' security: - apiKeyAuth: [] - bearerAuth: [] components: schemas: DeepResearchRequest: type: object required: - messages description: Request body for the Deep Research API. properties: model: type: string enum: - anthropic/claude-opus-4.8 - anthropic/claude-opus-4.6 - anthropic/claude-sonnet-4.6 - anthropic/claude-haiku-4.5 - google/gemini-3.5-flash - google/gemini-3.1-pro-preview - google/gemini-3.1-flash-lite - google/gemini-3-flash-preview - openai/gpt-5.5-pro - openai/gpt-5.5 - openai/gpt-5.4 - moonshotai/kimi-k2.6 - moonshotai/kimi-k2.5 - minimax/minimax-m2.5 - qwen/qwen3.6-plus default: minimax/minimax-m2.5 description: >- The model used for plan generation, analysis, brief construction, and the final report. messages: type: array description: >- Conversation messages. Only the last `role=user` message is used as the research question; other messages are ignored and do not enter plan generation, search, analysis, or report writing. items: $ref: '#/components/schemas/DeepResearchMessage' extra_context: type: string description: >- Additional research background, constraints, or preferences, used as extra context for query rewriting and research direction supplementation. max_tokens: type: integer description: >- Maximum output tokens for the final report. When unset or 0, the selected model uses its own default. max_rounds: type: integer minimum: 1 maximum: 10 default: 5 description: Upper bound on the number of research rounds. reasoning: allOf: - $ref: '#/components/schemas/DeepResearchReasoningOptions' description: Controls reasoning effort. Only applied to reasoning-capable models. skip_brief: type: boolean default: false description: >- Skip the Research Brief stage and write the final report directly from raw search and analysis results. Note: when enabled, no `brief` event is emitted. Clients can rebuild the citation index by accumulating `search_results` events in the order they arrive (round-by-round / query-by-query / result-by-result) into a global index, then look up the corresponding url/title by the `N` in `[^N]`. skip_plan: type: boolean default: false description: >- Phase 1 only. Skip the Research Plan stage and proceed straight to the search loop. With `skip_plan=true`, the call never enters the Phase 2 pause mechanism. skip_plan_confirm: type: boolean default: false description: >- Phase 1 only. When `true`, the run continues with all angles even if the plan is ambiguous, instead of pausing and waiting for the user to confirm a selection. plan_id: type: string description: >- Phase 2 only. The plan ID returned by a Phase 1 `plan` event with `requires_selection=true`. When provided, the server skips plan generation and applies the supplied `selections` against the stored plan. Each `plan_id` is retained for 30 minutes; after expiry the plan is regenerated. selections: type: array description: >- Phase 2 only. The user's corrections and angle filtering against the Phase 1 plan. items: $ref: '#/components/schemas/DeepResearchSelection' web_search_options: allOf: - $ref: '#/components/schemas/ChatWebSearchOptions' description: >- Search-related options. Queries are generated by the plan / adaptive stage. `highlight.max_tokens` defaults to **256**. DeepResearchChunk: type: object description: A streaming chunk of a Deep Research response. required: - request_id - created - model properties: type: type: string enum: - status - plan - queries - search_done - analysis - brief - content - finish - usage - error description: The type of this streaming chunk. request_id: type: string description: The unique identifier for this request. object: type: string enum: - research.chunk description: The object type, always `research.chunk`. created: type: number description: Unix timestamp (in seconds) of when the chunk was created. model: type: string description: The model used for this completion. round: type: integer description: >- Current research round. Present only in `queries`, `search_done`, and `analysis` chunks. latency: type: integer description: Latency in milliseconds for the stage represented by this chunk. status: type: string description: Pipeline progress copy. Present only in `status` chunks. plan: $ref: '#/components/schemas/DeepResearchPlan' plan_id: type: string description: >- Plan ID carried by `plan` chunks. The client must echo this back as `plan_id` when entering Phase 2. queries: type: array items: type: string description: >- Sub-queries generated for this round. Present only in `queries` chunks. search_result_count: type: integer description: >- Total number of search results returned this round. Present only in `search_done` chunks. search_results: type: array description: >- Search results for this round, one group per sub-query. Present only in `search_done` chunks. items: $ref: '#/components/schemas/BroadSearchResultGroup' analysis: $ref: '#/components/schemas/DeepResearchAnalysis' brief: $ref: '#/components/schemas/DeepResearchBrief' choices: type: array description: >- Incremental choices for the final report. Present in `content` and `finish` chunks. items: $ref: '#/components/schemas/DeepResearchChunkChoice' meta: $ref: '#/components/schemas/DeepResearchMeta' ErrorResponse: type: object properties: code: type: integer description: Business status code. Non-zero values indicate an error. msg: type: string description: A human-readable message describing the error. required: - code - msg DeepResearchMessage: type: object required: - role - content description: A single message in the Deep Research request. properties: role: type: string enum: - system - user - assistant description: The role of the message author. content: description: >- The content of the message. Can be a plain string, or an array of text content blocks. oneOf: - type: string - type: array items: $ref: '#/components/schemas/DeepResearchTextContentBlock' DeepResearchReasoningOptions: type: object description: Options for reasoning models. Only applies to reasoning-capable models. properties: effort: type: string enum: - none - low - medium - high description: >- The reasoning effort level. `none` disables reasoning; `low` / `medium` / `high` control reasoning intensity. When unset, the model's default is used. DeepResearchSelection: type: object description: A single user correction or angle filter applied against a Phase 1 plan. properties: term: type: string description: >- An ambiguous term, matching `plan.interpretations[].term`. When present, overrides the LLM's default `chosen` meaning. chosen: type: string description: >- The selected meaning ID (from `plan.interpretations[].meanings[].id`, e.g. `"nasa_program"`). Pass `"all"` to keep every meaning. When used as an angle filter, this carries the `interpretation_id` of the angles to keep. indices: type: array items: type: integer description: >- 0-based angle indices within the group identified by `chosen`. Absent means keep every angle in that group. ChatWebSearchOptions: type: object description: >- Search-related options for the Web Chat API. All parameters are optional and share the same semantics and defaults as the Search API. The query is automatically generated from the messages and does not need to be provided. properties: count: type: integer minimum: 1 maximum: 100 description: Number of search results to return. include_domains: type: array items: type: string description: Domains to include in search results. exclude_domains: type: array items: type: string description: Domains to exclude from search results. include_text: type: array items: type: string maxItems: 5 description: Strings that must appear in the result page text. exclude_text: type: array items: type: string maxItems: 5 description: Strings that must not appear in the result page text. time_basis: type: string enum: - auto - published - crawled description: Determines which time field is used for time filtering. start_time: type: string format: date-time description: Start time for filtering results. ISO 8601 format. end_time: type: string format: date-time description: End time for filtering results. ISO 8601 format. highlight: $ref: '#/components/schemas/HighlightOptions' format: type: string enum: - markdown - text description: Controls the formatting of highlight outputs. safesearch: type: string enum: - 'off' - strict description: Controls filtering of explicit/adult content. full_content: $ref: '#/components/schemas/FullContentOptions' DeepResearchPlan: type: object description: Research plan generated in Phase 1. Carried by `plan` chunks. properties: title: type: string description: Plan title. overview: type: string description: Plan overview. interpretations: type: array description: >- Ambiguous terms in the question along with their possible meanings. Empty when the question has no ambiguity. items: $ref: '#/components/schemas/DeepResearchInterpretation' angles: type: array description: Research angles the plan will explore. items: $ref: '#/components/schemas/DeepResearchAngle' requires_selection: type: boolean description: >- When `true`, the SSE stream ends at this `plan` chunk and waits for the client to continue via Phase 2 (`plan_id` + `selections`). When `false`, research continues automatically. BroadSearchResultGroup: type: object description: >- A group of search results for a single auto-generated sub-query in Broad Search. properties: query: type: string description: The auto-generated sub-query that produced these results. results: type: array description: The search results for this sub-query. items: $ref: '#/components/schemas/BroadSearchResultItem' latency: type: integer description: Search latency for this query in milliseconds. DeepResearchAnalysis: type: object description: Analysis output for one research round. Carried by `analysis` chunks. properties: findings: type: array items: type: string description: Key findings extracted from this round. should_continue: type: boolean description: Whether the pipeline should run another research round. follow_up_suggestions: type: array items: type: string description: Suggested research directions for the next round. DeepResearchBrief: type: object description: Report outline and evidence set. Carried by `brief` chunks. properties: report_type: type: string enum: - general - comparison - trend - how-to - evaluation - framework - deep_explainer - theoretical_analysis - landscape_mapping - multi_part description: >- Report type, classified by the LLM from the question. `general`: general synthesis; `comparison`: cross-entity comparison; `trend`: time-axis trend analysis; `how-to`: step-by-step guide; `evaluation`: ranked or scored evaluation; `framework`: methodology or scoring framework; `deep_explainer`: deep explanation of a single topic; `theoretical_analysis`: scholarly analysis across multiple theoretical lenses; `landscape_mapping`: taxonomy and players in a domain; `multi_part`: composite question with explicit sub-questions. secondary_report_types: type: array items: type: string description: Secondary type tags for hybrid reports, combined with `report_type`. total_word_budget: type: integer description: Total word budget for the report. assertiveness_required: type: boolean description: Whether the report must deliver a clear verdict. verdict_scaffold: $ref: '#/components/schemas/DeepResearchVerdictScaffold' tables: type: array description: >- Table metadata to render in the report. Mutually exclusive with `presentation_notes`. items: $ref: '#/components/schemas/DeepResearchTable' presentation_notes: type: array items: type: string description: >- Presentation notes for reports that do not use tables. Mutually exclusive with `tables`. outline: type: array description: Report outline in section order. items: $ref: '#/components/schemas/DeepResearchOutlineSection' sub_question_to_section_map: type: object additionalProperties: type: string description: Mapping from sub-question ID to section ID. unresolved: $ref: '#/components/schemas/DeepResearchUnresolved' suggested_title: type: string description: Suggested title for the report. references: type: array description: List of cited references. items: $ref: '#/components/schemas/DeepResearchReference' DeepResearchChunkChoice: type: object description: >- A single choice in a Deep Research streaming chunk. Carried by `content` and `finish` chunks. properties: index: type: number description: The index of this choice. Usually `0`. delta: $ref: '#/components/schemas/DeepResearchChunkDelta' finish_reason: type: string nullable: true enum: - stop - length - content_filter - error description: >- The reason generation stopped. `null` in `content` chunks; populated in the `finish` chunk. DeepResearchMeta: type: object description: >- Usage and latency metadata for the Deep Research call. Carried by `usage` chunks. properties: usage: allOf: - $ref: '#/components/schemas/BroadSearchUsage' description: Token and search usage. latency: type: integer description: Total request latency in milliseconds. total_rounds: type: integer description: Total number of research rounds completed. total_search_count: type: integer description: Total search results accumulated across all rounds. DeepResearchTextContentBlock: type: object required: - type description: A text content block. properties: type: type: string enum: - text description: The block type. Always `text` for Deep Research. text: type: string description: The text content. HighlightOptions: type: object description: Controls highlight extraction from result pages. properties: enable: type: boolean default: true description: If true, returns query-relevant highlight in each result. max_tokens: type: integer default: 512 minimum: 100 maximum: 20000 description: Max tokens returned per highlight. FullContentOptions: type: object description: Controls whether to return the full raw content of each result page. properties: enable: type: boolean default: false description: If true, returns full_content for each result. max_tokens: type: integer default: 2048 minimum: 100 maximum: 100000 description: Maximum tokens of full content included per result. DeepResearchInterpretation: type: object description: An ambiguous term and its candidate meanings. properties: term: type: string description: The ambiguous term. meanings: type: array description: All candidate meanings for this term. items: $ref: '#/components/schemas/DeepResearchMeaning' chosen: type: string description: The meaning ID the LLM picked by default. reasoning: type: string description: The LLM's rationale for the chosen meaning. DeepResearchAngle: type: object description: A single research angle within the plan. properties: focus: type: string description: Angle name. focus_desc: type: string description: Angle description. interpretation_id: type: string description: >- The meaning ID this angle serves. `"general"` denotes a cross-interpretation angle. queries: type: array items: type: string description: Search queries planned for this angle. sub_question_ids: type: array items: type: string description: Sub-question IDs covered by this angle. BroadSearchResultItem: type: object description: A single search result item within a Broad Search result group. properties: title: type: string description: The title of the result page. url: type: string description: The URL of the result page. highlight: type: string description: >- Query-relevant highlight content. Only returned when `highlight.enable` is `true`. full_content: type: string description: >- Full page content. Only returned when `full_content.enable` is `true`. authors: type: string description: Website name or author. time_published: type: string format: date-time description: Publish time in ISO 8601. time_last_crawled: type: string format: date-time description: Last crawl time in ISO 8601. DeepResearchVerdictScaffold: type: object description: Structured scaffold for reports that need to deliver a verdict. properties: verdict_type: type: string enum: - ranked_list - single_pick - tiered_recommendation - qualified_pick description: >- Shape of the verdict. `ranked_list`: ordered ranking; `single_pick`: a single best answer; `tiered_recommendation`: tiered recommendation; `qualified_pick`: conditional recommendation. items_expected: type: integer description: Expected number of items in the verdict. justification_dimensions: type: array items: type: string description: Data dimensions supporting the verdict. DeepResearchTable: type: object description: Table metadata referenced from an outline section. properties: table_id: type: string description: Unique table ID, referenced by `outline.table_ids`. title: type: string description: Table title. columns: type: array items: type: string description: Column names. description: type: string description: >- Description of the table contents, guiding how the report-writing stage should populate the cells. placement: type: string description: Section ID this table belongs to. DeepResearchOutlineSection: type: object description: A single section in the report outline. properties: section_id: type: string description: >- Unique section ID, referenced by `sub_question_to_section_map` and `table.placement`. section_title: type: string description: Section title. thesis: type: string description: Central claim of this section. table_ids: type: array items: type: string description: Table IDs belonging to this section. covers_sub_questions: type: array items: type: string description: Sub-question IDs covered by this section. target_words: type: integer description: Target word count for this section. evidence: type: array description: Evidence supporting this section. items: $ref: '#/components/schemas/DeepResearchEvidence' DeepResearchUnresolved: type: object description: Items the brief stage flagged as unresolved. properties: contradictions: type: array items: type: string description: Contradictions between sources. weak_claims: type: array items: type: string description: Claims with thin evidence. depth_gaps: type: array items: type: string description: Depth-layer gaps across sections. unanswered: type: array items: type: string description: Sub-questions left unanswered. DeepResearchReference: type: object description: A single cited reference. properties: index: type: integer description: Reference index; cited in the report body as `[^N]`. url: type: string description: Source URL. title: type: string description: Source title. DeepResearchChunkDelta: type: object description: Incremental content in a Deep Research streaming chunk. properties: content: type: string description: >- Incremental report text. Concatenate across `content` chunks to build the final report. BroadSearchUsage: type: object description: >- Token usage information for the Broad Search response. When `stream=true`, this is only present in the `usage` type chunk. required: - num_search_queries - prompt_tokens - completion_tokens - total_tokens properties: num_search_queries: type: integer description: Total number of search queries executed across all sub-queries. prompt_tokens: type: integer description: Number of input tokens. completion_tokens: type: integer description: Number of output tokens. total_tokens: type: integer description: Total tokens used (prompt_tokens + completion_tokens). DeepResearchMeaning: type: object description: A candidate meaning for an ambiguous term. properties: id: type: string description: Unique meaning ID. label: type: string description: Human-readable description of the meaning. DeepResearchEvidence: type: object description: A single piece of evidence within a section. properties: content: type: string description: Evidence content. source_indices: type: array items: type: integer description: >- Source indices cited by this evidence (matching `brief.references[].index`). confidence: type: string enum: - strong - moderate - weak - conflicting description: Confidence level of the evidence. layer: type: string enum: - phenomenon - mechanism - evidence - implication description: Depth layer of the evidence. responses: Unauthorized: description: Invalid API Key — Returned when the API key is missing or invalid. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' example: code: 401 msg: Invalid API Key InsufficientBalance: description: >- Insufficient balance in account — Returned when the account balance is insufficient to complete the request. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' example: code: 403 msg: Insufficient balance in account RateLimited: description: >- Exceeding the rate limit — Returned when the request exceeds the configured rate limit. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' example: code: 429 msg: Exceeding the rate limit InternalError: description: Internal error — Returned when an unexpected server-side error occurs. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' example: code: 500 msg: Internal error securitySchemes: apiKeyAuth: type: apiKey in: header name: x-api-key description: >- API key used for request authentication. Obtain an API key before using the API. Note: A payment method is required to use the API. bearerAuth: type: http scheme: bearer description: >- Bearer token authentication. Compatible with OpenAI protocol. Pass the API key as `Authorization: Bearer `. ````