> ## Documentation Index > Fetch the complete documentation index at: /docs/llms.txt > Use this file to discover all available pages before exploring further. # Compact response > Referência da API para POST /v1/responses/compact. Resuma itens mais antigos da conversa em um único item de compactação. > [!NOTE] > > **Guia relacionado**: compactação de contexto. Consulte [Compactação de contexto](/docs/pt-BR/ai-gateway/features/context-compaction.md) para limites, compactação automática e o item a partir do qual continuar. ## OpenAPI ````yaml post /v1/responses/compact openapi: 3.1.0 info: title: Toqan Router API version: '2.0' description: Toqan Router API documentation servers: - url: https://router.toqan.ai/eu description: Frankfurt (Europe) - url: https://router.toqan.ai/br description: São Paulo (Brazil) security: - ApiKey: [] tags: - description: >- API keys authenticate programmatic access to the workspace. They expose opaque tokens, per-domain access grants, and budget and rate-limit constraints. name: API keys - name: Logs description: >- OpenTelemetry log query API. Search, filter, aggregate, and facet log records ingested via OTLP. - name: Reporting description: >- GenAI reporting API over canonical analytics rollups. Accepts a metric name, time range, grain, group-by, and filters; returns a typed time series and optional totals. - name: Telemetry description: >- Unified query envelope for traces, metrics, and logs. One request shape, one filter dialect, and one response shape per source, validated by a per-source registry. - name: Traces description: >- Query and inspect ingested trace data: search trace summaries, aggregate metrics, and read individual traces and their spans. - name: Views description: Saved filters and columns for workspace observability pages. - description: List models available through the AI Router. name: Models - name: Alerts description: >- Alerts evaluate a telemetry metric on a fixed interval and fire notifications through notifiers when the value breaches a threshold. Each breach opens a trigger that tracks the incident until the value recovers. - name: Annotation Queues description: Annotation queues collect spans for human review. - name: Budgets description: >- Budgets govern spend, token usage, and request rate across six scopes: workspace, project, identity, API key, provider, and model. Every applicable budget is enforced, and the most restrictive limit applies per dimension. - name: Files description: File upload and retrieval operations. - name: Guardrail Rules description: >- Guardrail Rules conditionally enforce evaluators and plugins for AI Gateway traffic. Rules may be scoped to a project or the whole workspace. - name: Identities description: >- Identities represent end users from your system for usage and engagement tracking. - name: Management keys description: >- Management keys are workspace-scoped credentials that authenticate programmatic access to workspace administration surfaces (API keys, budgets). Unlike project-scoped API keys, a management key always operates at the workspace level. - name: MCP Gateway description: >- Register upstream MCP servers, discover and sync their tools, and assemble gateways that expose a curated tool surface to MCP clients. - name: Model Catalog description: >- Browse the Toqan Router model catalog: every model Toqan Router offers, across every provider, with pricing, capabilities and benchmark data. List endpoints only return models that are not deprecated. This API is public, requires no authentication, and is rate limited to 120 requests per minute per IP. Responses carry a 5-minute cache-control max-age. - name: Monitors description: >- Monitors are custom observability dashboards for traces, runtime metrics, and logs. Each monitor holds widgets that chart one telemetry query. List the metrics, operations, and dimensions available to your workspace with `GET /v3/telemetry/capabilities`, or start from a preset with `GET /v2/monitors/presets`. - name: Notifiers description: Notifier destinations used to send delivery and workflow notifications. - name: Routing Rules description: >- Routing Rules conditionally select models and enforce request plugins for AI Gateway traffic. Rules are evaluated by ascending priority and may be scoped to a project or the whole workspace. - name: Threads description: Threads group related trace invocations and their aggregate usage - name: Smart Routers description: >- Create and manage workspace Smart Routers. A Smart Router selects a model from an eligible pool for each request according to a quality, balanced, or cost profile. - name: Responses - name: Embeddings - description: Beta. Run typed classification questions against a classify model. name: Classify - description: Beta. Run classification decisions with the classify contract. name: Decisions - description: >- Run large offline workloads as JSONL batches and download OpenAI-compatible result files. name: Batches paths: /v1/responses/compact: post: tags: - Responses summary: Compact response description: >- Compacts a conversation by summarizing older items to free up context window space. Returns the next context window: a compaction item containing the generated summary, followed by the most recent items verbatim. operationId: compact-response requestBody: content: application/json: examples: compact_conversation: summary: Compact a conversation to free context space value: input: - content: Tell me about machine learning role: user type: message - content: Machine learning is a subset of AI... role: assistant type: message model: openai/gpt-4o schema: additionalProperties: false properties: input: anyOf: - description: A simple text string. title: Text type: string - description: An array of input items. items: description: >- An input item. The "type" field determines the item kind. properties: content: anyOf: - title: Text type: string - items: anyOf: - description: A text content part. properties: cache_control: properties: ttl: default: 5m description: >- The time-to-live for the cache control breakpoint. This may be one of the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. Only supported by Anthropic Claude models. enum: - 5m - 1h type: string type: type: string enum: - ephemeral description: >- Create a cache control breakpoint at this content block. Accepts only the value "ephemeral". required: - type title: Cache control type: object prompt_cache_breakpoint: description: >- An explicit OpenAI cache boundary for GPT-5.6 and later. Omitted ttl inherits prompt_cache_options.ttl. properties: mode: enum: - explicit type: string ttl: enum: - 30m - 12h type: string required: - mode type: object text: type: string description: The text content. type: enum: - input_text type: string required: - type - text title: Text type: object - description: An image content part. properties: cache_control: properties: ttl: default: 5m description: >- The time-to-live for the cache control breakpoint. This may be one of the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. Only supported by Anthropic Claude models. enum: - 5m - 1h type: string type: type: string enum: - ephemeral description: >- Create a cache control breakpoint at this content block. Accepts only the value "ephemeral". required: - type title: Cache control type: object detail: description: >- The detail level for image understanding. enum: - auto - low - high type: string file_id: description: The ID of a previously uploaded file. type: string image_url: description: The URL of the image. type: string prompt_cache_breakpoint: description: >- An explicit OpenAI cache boundary for GPT-5.6 and later. Omitted ttl inherits prompt_cache_options.ttl. properties: mode: enum: - explicit type: string ttl: enum: - 30m - 12h type: string required: - mode type: object type: enum: - input_image type: string required: - type title: Image type: object - description: >- A file content part. Provide file_id, file_data (base64), or file_url. properties: cache_control: properties: ttl: default: 5m description: >- The time-to-live for the cache control breakpoint. This may be one of the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. Only supported by Anthropic Claude models. enum: - 5m - 1h type: string type: type: string enum: - ephemeral description: >- Create a cache control breakpoint at this content block. Accepts only the value "ephemeral". required: - type title: Cache control type: object file_data: description: Base64-encoded file content. type: string file_id: description: The ID of a previously uploaded file. type: string file_url: description: A URL to fetch the file from. type: string filename: description: The name of the file. type: string mime_type: description: >- The MIME type of the file (e.g., application/pdf). type: string prompt_cache_breakpoint: description: >- An explicit OpenAI cache boundary for GPT-5.6 and later. Omitted ttl inherits prompt_cache_options.ttl. properties: mode: enum: - explicit type: string ttl: enum: - 30m - 12h type: string required: - mode type: object type: enum: - input_file type: string required: - type title: File type: object description: A content part within a message. title: Content parts type: array description: >- The content of the item: a string or an array of content parts. id: description: The ID of the item. type: string role: description: >- The role of the message sender (for message items). enum: - user - assistant - system type: string type: description: The type of item. enum: - message - function_call - function_call_output - item_reference - reasoning - custom_tool_call - custom_tool_call_output - compaction type: string type: object title: Items type: array description: >- Input to compact: a string or an array of input items (messages, files, etc.). instructions: description: Custom instructions for the compaction summarization. type: string model: description: >- The model to use for compaction in provider/model format (e.g. openai/gpt-4o). Required. type: string previous_response_id: description: >- The ID of a stored response whose conversation is compacted; input is appended after it. type: string prompt_cache_key: description: Key for prompt caching across requests. type: string type: object required: true responses: '200': content: application/json: schema: additionalProperties: false properties: created_at: description: Unix timestamp (seconds) when the response was created. format: int64 type: integer id: description: The ID of the compaction response. type: string object: description: Always "response.compaction". enum: - response.compaction type: string output: description: >- The next context window: a compaction item summarizing older items, followed by the most recent items verbatim. Pass it as the input of the next request, without previous_response_id. items: {} type: - array - 'null' usage: $ref: '#/components/schemas/PublicUsage' description: Token usage information for the compaction request. required: - id - object - output - created_at - usage type: object description: Compaction completed successfully. '400': content: application/json: schema: type: object additionalProperties: false properties: error: $ref: '#/components/schemas/APIError' required: - error description: Model is required or request is invalid. '401': content: application/json: schema: type: object additionalProperties: false properties: error: $ref: '#/components/schemas/APIError' required: - error description: Unauthorized. '502': content: application/json: schema: type: object additionalProperties: false properties: error: $ref: '#/components/schemas/APIError' required: - error description: Failed to compact conversation. security: - ApiKey: [] x-code-samples: [] components: schemas: PublicUsage: additionalProperties: false properties: input_cost: description: >- Cost (USD) of input tokens. Present when billing was computed for this response. format: double type: number input_tokens: format: int64 type: integer input_tokens_details: $ref: '#/components/schemas/InputTokensDetails' output_cost: description: >- Cost (USD) of output tokens. Present when billing was computed for this response. format: double type: number output_tokens: format: int64 type: integer output_tokens_details: $ref: '#/components/schemas/OutputTokensDetails' server_tool_use: $ref: '#/components/schemas/ServerToolUseDetails' description: >- Per-tool breakdown of server tool calls (provider-native and router-executed) made during this response. speed: description: Inference speed reported by Anthropic and used for billing. enum: - standard - fast type: string total_cost: description: >- Total cost (USD) of the response. Present when billing was computed for this response. format: double type: number total_tokens: format: int64 type: integer web_search_requests: format: int64 type: integer required: - input_tokens - output_tokens - total_tokens - input_tokens_details - output_tokens_details type: object APIError: additionalProperties: false properties: code: type: - string - 'null' failures: {} message: type: string param: type: - string - 'null' type: type: string required: - message - type - param - code type: object InputTokensDetails: additionalProperties: false properties: cache_creation_1h_tokens: format: int64 type: integer cache_creation_5m_tokens: format: int64 type: integer cache_creation_tokens: format: int64 type: integer cache_write_tokens: format: int64 type: integer cache_write_tokens_details: $ref: '#/components/schemas/CacheWriteTokensDetails' cached_tokens: format: int64 type: integer required: - cached_tokens - cache_write_tokens - cache_creation_tokens type: object OutputTokensDetails: additionalProperties: false properties: reasoning_tokens: format: int64 type: integer required: - reasoning_tokens type: object ServerToolUseDetails: additionalProperties: false properties: advisor_requests: format: int64 type: integer code_interpreter_sessions: format: int64 type: integer datetime_requests: format: int64 type: integer fusion_requests: format: int64 type: integer image_generation_calls: format: int64 type: integer search_models_requests: format: int64 type: integer shell_commands: format: int64 type: integer subagent_requests: format: int64 type: integer tool_search_requests: format: int64 type: integer web_fetch_requests: format: int64 type: integer web_search_requests: format: int64 type: integer type: object CacheWriteTokensDetails: additionalProperties: false properties: ttl_12h_tokens: format: int64 type: integer ttl_30m_tokens: format: int64 type: integer required: - ttl_30m_tokens - ttl_12h_tokens type: object securitySchemes: ApiKey: type: http scheme: bearer bearerFormat: JWT ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.