scrape

Added value: +{
+  "default": true,
+  "description": "Render the page and read computed styles for colour roles, buttons and type (default: true; false keeps branding to the HTML and CSS)",
+  "type": "boolean"
+}

Added value: +{
+  "default": false,
+  "description": "Also return the tokens as W3C Design Tokens (DTCG 2025.10) JSON, under dtcg",
+  "type": "boolean"
+}

Added value: +{
+  "default": false,
+  "description": "Also return every CSS custom property as found, under cssVariables (large on design-system sites)",
+  "type": "boolean"
+}

Previous value: -"Static design tokens: colors, fonts, logo"New value: +"Brand style: colour roles, button components and type (computed or inferred), logo, fonts and grouped design tokens"

Added value: +{
+  "description": "Reuse this session's copy of the page if it was fetched within this many ms (default 600000 = 10 min); 0 always fetches fresh.",
+  "maximum": 9007199254740991,
+  "minimum": 0,
+  "type": "integer"
+}

Previous value: -"Cost-transparency metadata (D3.5), present when injected into the text copy of the result"New value: +"Cost-transparency metadata (D3.5): what this call was projected to cost and what it was charged"

Previous value: -"Credits actually charged (0 in creator mode, half-rate on error)"New value: +"Credits actually charged (0 in creator mode, and 0 for a failed call)"

Added value: +{
+  "additionalProperties": {},
+  "description": "Page cache: whether this call reused a copy of the page fetched earlier in the session",
+  "properties": {
+    "ageMs": {
+      "description": "Age of that copy in ms",
+      "type": [
+        "number",
+        "null"
+      ]
+    },
+    "fetchedAt": {
+      "description": "When the oldest page used was fetched (ISO 8601)",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "note": {
+      "description": "Hits only: how old the copy is and how to force a fresh fetch",
+      "type": "string"
+    },
+    "state": {
+      "description": "hit: every page came from this session's copy; bypass: fetched fresh on request (maxAge 0) or not cacheable; miss: fetched",
+      "enum": [
+        "hit",
+        "miss",
+        "bypass"
+      ],
+      "type": "string"
+    }
+  },
+  "type": "object"
+}

Added value: +{
+  "description": "Failed calls only: the tool or fix to try next",
+  "type": "string"
+}

Previous value: -"Formats to return (default: [\"markdown\"])"New value: +"Formats to return (default: [\"markdown\"]); at most one highlights and one question format per call"

Added value: +"\"heading\" occurs only in question evidence"

Previous value: -[
-  "sentence",
-  "table_row",
-  "code_block"
-]New value: +[
+  "sentence",
+  "table_row",
+  "code_block",
+  "heading"
+]

Previous value: -"True when every number and proper noun in text appears in the evidence or the question; always true in extractive mode"New value: +"False when no unit matched (text is empty) or, in model mode, when the model found no answer in the evidence (text is empty) or used a number or proper noun that appears in neither the evidence nor the question"

Added value: +"\"heading\" occurs only in question evidence"

Previous value: -[
-  "sentence",
-  "table_row",
-  "code_block"
-]New value: +[
+  "sentence",
+  "table_row",
+  "code_block",
+  "heading"
+]

Added value: +"The document <title>; og:title, then the first H1, only when the page has none. og:title itself is og_tags.title"

Previous value: -"When the plain fetch comes back blocked (403/429/challenge page/empty shell), retry once in the stealth browser and return its content instead of the block. Projected at 2+5; the actual charge stays at the base price when the plain fetch succeeded. Default: false"New value: +"When the plain fetch comes back blocked (403/429/challenge page/empty shell), retry once in the stealth browser and return its content instead of the block. Under escalate_engine \"auto\" a Chrome TLS handshake with the honest CrawlForge User-Agent (impit) is tried first, and the browser runs only when that does not get the page. Projected at 2+5; the actual charge stays at the base price when the plain fetch succeeded. Default: false"

Previous value: -"Present when escalated is true: the stealth engine that ran, and the bot-defence vendor the plain fetch hit (null when the block named none)"New value: +"Present when escalated is true: the stealth engine that ran (\"impit\" when the Chrome TLS handshake got the page without a browser), and the bot-defence vendor the plain fetch hit (null when the block named none)"

Previous value: -"playwright"New value: +"auto"

Previous value: -"Stealth engine for the escalated retry (default: \"playwright\")"New value: +"Stealth engine for the escalated retry: \"auto\" (default — Camoufox when it is installed, Chromium otherwise, reported in warnings), \"playwright\" (Chromium) or \"camoufox\""

Previous value: -[
-  "playwright",
-  "camoufox"
-]New value: +[
+  "auto",
+  "playwright",
+  "camoufox"
+]

Removed value: -false

Removed value: -false

Added value: +{
+  "default": false,
+  "description": "When the plain fetch comes back blocked (403/429/challenge page/empty shell), retry once in the stealth browser and return its content instead of the block. Projected at 2+5; the actual charge stays at the base price when the plain fetch succeeded. Default: false",
+  "type": "boolean"
+}

Added value: +{
+  "default": "playwright",
+  "description": "Stealth engine for the escalated retry (default: \"playwright\")",
+  "enum": [
+    "playwright",
+    "camoufox"
+  ],
+  "type": "string"
+}

Previous value: -[
-  {
-    "enum": [
-      "markdown",
-      "html",
-      "rawHtml",
-      "text",
-      "links",
-      "metadata",
-      "screenshot",
-      "branding"
-    ],
-    "type": "string"
-  },
-  {
-    "additionalProperties": false,
-    "properties": {
-      "prompt": {
-        "description": "Extraction instruction for the LLM",
-        "type": "string"
-      },
-      "schema": {
-        "additionalProperties": {},
-        "description": "JSON schema for extraction",
-        "type": "object"
-      },
-      "type": {
-        "const": "json",
-        "type": "string"
-      }
-    },
-    "required": [
-      "type"
-    ],
-    "type": "object"
-  }
-]New value: +[
+  {
+    "enum": [
+      "markdown",
+      "html",
+      "rawHtml",
+      "text",
+      "links",
+      "metadata",
+      "screenshot",
+      "branding"
+    ],
+    "type": "string"
+  },
+  {
+    "properties": {
+      "prompt": {
+        "description": "Extraction instruction for the LLM",
+        "type": "string"
+      },
+      "schema": {
+        "additionalProperties": {},
+        "description": "JSON schema for extraction",
+        "propertyNames": {
+          "type": "string"
+        },
+        "type": "object"
+      },
+      "type": {
+        "const": "json",
+        "type": "string"
+      }
+    },
+    "required": [
+      "type"
+    ],
+    "type": "object"
+  },
+  {
+    "properties": {
+      "max_highlights": {
+        "default": 10,
+        "description": "How many units to return (default 10)",
+        "maximum": 50,
+        "minimum": 1,
+        "type": "integer"
+      },
+      "mode": {
+        "default": "extractive",
+        "description": "\"extractive\" (default) returns verbatim page text, no model; \"model\" adds an LLM step (+3 credits)",
+        "enum": [
+          "extractive",
+          "model"
+        ],
+        "type": "string"
+      },
+      "query": {
+        "description": "What to look for; the matching sentences, table rows and code blocks come back verbatim with offsets into the markdown",
+        "maxLength": 500,
+        "minLength": 1,
+        "type": "string"
+      },
+      "type": {
+        "const": "highlights",
+        "type": "string"
+      }
+    },
+    "required": [
+      "type",
+      "query"
+    ],
+    "type": "object"
+  },
+  {
+    "properties": {
+      "mode": {
+        "default": "extractive",
+        "description": "\"extractive\" (default) returns verbatim page text, no model; \"model\" adds an LLM step (+3 credits)",
+        "enum": [
+          "extractive",
+          "model"
+        ],
+        "type": "string"
+      },
+      "question": {
+        "description": "The question to answer from the page; the evidence units come back verbatim with offsets",
+        "maxLength": 500,
+        "minLength": 1,
+        "type": "string"
+      },
+      "type": {
+        "const": "question",
+        "type": "string"
+      }
+    },
+    "required": [
+      "type",
+      "question"
+    ],
+    "type": "object"
+  }
+]

Added value: +{
+  "description": "Largest result to return inline, in characters of its JSON. Over it, the call returns a preview plus a result_handle for read_result instead of the whole result (default 40,000; env CRAWLFORGE_MAX_INLINE_CHARS)",
+  "maximum": 10000000,
+  "minimum": 1000,
+  "type": "integer"
+}

Added value: +{
+  "anyOf": [
+    {
+      "type": "boolean"
+    },
+    {
+      "properties": {
+        "entities": {
+          "description": "Which classes to redact, case-insensitive: EMAIL, PHONE, FINANCIAL, SECRET, plus PERSON and LOCATION when mode is \"model\". Omitted or empty means all four regex classes (and both model classes in \"model\" mode). An unknown name, or a model-only name without mode:\"model\", is rejected",
+          "items": {
+            "type": "string"
+          },
+          "type": "array"
+        },
+        "mode": {
+          "description": "\"fast\" (default) is regex only and free; \"model\" adds an Ollama NER pass for PERSON and LOCATION (+3 credits once per call)",
+          "enum": [
+            "fast",
+            "model"
+          ],
+          "type": "string"
+        },
+        "replace_style": {
+          "description": "\"tag\" (default) writes <EMAIL>, \"mask\" writes [REDACTED], \"remove\" deletes the value",
+          "enum": [
+            "tag",
+            "mask",
+            "remove"
+          ],
+          "type": "string"
+        }
+      },
+      "type": "object"
+    }
+  ],
+  "description": "Redact personal data from the text this call returns, before it reaches your context window. true means the free regex pass over EMAIL, PHONE, FINANCIAL and SECRET. The result carries redaction:{entities,count}. Default: off"
+}

Removed value: -false

Previous value: -trueNew value: +{}

Added value: +{
+  "additionalProperties": {},
+  "description": "Present when a bot-defence vendor served a challenge page; the fallback hint names the tool to try next",
+  "properties": {
+    "evidence": {
+      "type": "string"
+    },
+    "vendor": {
+      "type": "string"
+    }
+  },
+  "type": "object"
+}

Previous value: -trueNew value: +{}

Added value: +{
+  "additionalProperties": {},
+  "description": "Result of the {type:\"question\"} format",
+  "properties": {
+    "evidence": {
+      "description": "The units the answer rests on, verbatim with offsets",
+      "items": {
+        "additionalProperties": {},
+        "properties": {
+          "kind": {
+            "enum": [
+              "sentence",
+              "table_row",
+              "code_block"
+            ],
+            "type": "string"
+          },
+          "length": {
+            "type": "number"
+          },
+          "offset": {
+            "description": "JS string index into the markdown format of this call",
+            "type": "number"
+          },
+          "score": {
+            "description": "BM25 relevance to the query, higher is better",
+            "type": "number"
+          },
+          "text": {
+            "description": "Verbatim page text: markdown.slice(offset, offset + length) === text",
+            "type": "string"
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "grounded": {
+      "description": "True when every number and proper noun in text appears in the evidence or the question; always true in extractive mode",
+      "type": "boolean"
+    },
+    "text": {
+      "description": "Extractive mode: the evidence texts joined; model mode: the model's answer",
+      "type": "string"
+    }
+  },
+  "type": "object"
+}

Added value: +{
+  "type": "string"
+}

Added value: +{
+  "description": "Result of the {type:\"highlights\"} format: the units matching the query, best first, verbatim with offsets",
+  "items": {
+    "additionalProperties": {},
+    "properties": {
+      "kind": {
+        "enum": [
+          "sentence",
+          "table_row",
+          "code_block"
+        ],
+        "type": "string"
+      },
+      "length": {
+        "type": "number"
+      },
+      "offset": {
+        "description": "JS string index into the markdown format of this call",
+        "type": "number"
+      },
+      "score": {
+        "description": "BM25 relevance to the query, higher is better",
+        "type": "number"
+      },
+      "text": {
+        "description": "Verbatim page text: markdown.slice(offset, offset + length) === text",
+        "type": "string"
+      }
+    },
+    "type": "object"
+  },
+  "type": "array"
+}

Previous value: -trueNew value: +{}

Previous value: -trueNew value: +{}

Previous value: -trueNew value: +{}

Added value: +{
+  "type": "string"
+}

Added value: +{
+  "type": "string"
+}

Previous value: -trueNew value: +{}

Added value: +{
+  "description": "Why success is false: a challenge page, an empty shell or an error placeholder was served instead of the content",
+  "type": "string"
+}

Added value: +{
+  "description": "Present only when escalate:true was passed: whether the blocked plain fetch was retried in the stealth browser. False means the plain fetch sufficed and the call is charged at the base price",
+  "type": "boolean"
+}

Added value: +{
+  "description": "When the stored result is dropped (ISO 8601)",
+  "type": "string"
+}

Added value: +{
+  "description": "The first max_inline_chars characters of the view named by view_path (or of the pretty-printed JSON)",
+  "type": "string"
+}

Added value: +{
+  "additionalProperties": {},
+  "description": "Present when redact_pii was set: what was redacted from the text of this result",
+  "properties": {
+    "count": {
+      "description": "Total spans replaced",
+      "type": "number"
+    },
+    "entities": {
+      "additionalProperties": {
+        "type": "number"
+      },
+      "description": "How many spans were replaced, by entity class; a class with no hits is omitted",
+      "propertyNames": {
+        "type": "string"
+      },
+      "type": "object"
+    },
+    "mode": {
+      "description": "\"fast\" is the free regex pass; \"model\" added an Ollama NER pass for PERSON and LOCATION",
+      "enum": [
+        "fast",
+        "model"
+      ],
+      "type": "string"
+    },
+    "model_ran": {
+      "description": "mode \"model\" only: whether a model actually answered. False means no LLM route existed and the model surcharge was not charged",
+      "type": "boolean"
+    }
+  },
+  "type": "object"
+}

Added value: +{
+  "description": "Handle for read_result; the full result is kept 1 hour",
+  "type": "string"
+}

Added value: +{
+  "description": "HTTP status of the fetch; present when success is false",
+  "type": "number"
+}

Added value: +{
+  "additionalProperties": {},
+  "description": "Present when escalated is true: the stealth engine that ran, and the bot-defence vendor the plain fetch hit (null when the block named none)",
+  "properties": {
+    "engine": {
+      "type": "string"
+    },
+    "vendor_detected": {
+      "type": [
+        "string",
+        "null"
+      ]
+    }
+  },
+  "type": "object"
+}

Added value: +{
+  "description": "Document title; present when success is false",
+  "type": "string"
+}

Added value: +{
+  "description": "Length of the full view in characters",
+  "type": "number"
+}

Added value: +{
+  "description": "True when the inline result is a preview",
+  "type": "boolean"
+}

Added value: +{
+  "description": "Whether preview and read_result offsets index a text field or the pretty-printed JSON",
+  "enum": [
+    "text",
+    "json"
+  ],
+  "type": "string"
+}

Added value: +{
+  "description": "Dotted path of the text field the view was cut from; null for the JSON view",
+  "type": [
+    "string",
+    "null"
+  ]
+}

Added value: +{
+  "description": "Respect the target site's robots.txt (default: true). Setting this to false is honoured, returns a warning in the response, and is recorded against your API key — it is your decision, not a silent default.",
+  "type": "boolean"
+}

Added value: +{
+  "description": "Override the outbound User-Agent. CrawlForge identifies itself honestly by default; use this only for targets you have your own agreement with.",
+  "type": "string"
+}

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

Previous value: -nullNew value: +{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "additionalProperties": false,
+  "properties": {
+    "_cost": {
+      "additionalProperties": true,
+      "description": "Cost-transparency metadata (D3.5), present when injected into the text copy of the result",
+      "properties": {
+        "actual": {
+          "description": "Credits actually charged (0 in creator mode, half-rate on error)",
+          "type": "number"
+        },
+        "projected": {
+          "description": "Credits projected for this call before execution",
+          "type": "number"
+        },
+        "projection_note": {
+          "description": "Human-readable note about how the cost was projected",
+          "type": "string"
+        },
+        "remaining_credits": {
+          "description": "Credits remaining on the account after this call, if known",
+          "type": [
+            "number",
+            "null"
+          ]
+        }
+      },
+      "type": "object"
+    },
+    "content": {
+      "additionalProperties": true,
+      "description": "One key per requested format",
+      "properties": {
+        "branding": {
+          "additionalProperties": {},
+          "description": "Static design tokens: colors, fonts, logo",
+          "type": "object"
+        },
+        "html": {
+          "type": "string"
+        },
+        "json": {
+          "description": "Result of the {type:\"json\"} format (LLM-structured extraction)"
+        },
+        "links": {
+          "additionalProperties": true,
+          "properties": {
+            "external_count": {
+              "type": "number"
+            },
+            "internal_count": {
+              "type": "number"
+            },
+            "links": {
+              "items": {
+                "additionalProperties": true,
+                "properties": {
+                  "href": {
+                    "type": "string"
+                  },
+                  "is_external": {
+                    "type": "boolean"
+                  },
+                  "original_href": {
+                    "type": "string"
+                  },
+                  "text": {
+                    "type": "string"
+                  }
+                },
+                "type": "object"
+              },
+              "type": "array"
+            },
+            "total_count": {
+              "type": "number"
+            }
+          },
+          "type": "object"
+        },
+        "markdown": {
+          "type": "string"
+        },
+        "metadata": {
+          "additionalProperties": true,
+          "properties": {
+            "author": {
+              "type": "string"
+            },
+            "canonical_url": {
+              "type": "string"
+            },
+            "description": {
+              "type": "string"
+            },
+            "json_ld": {
+              "items": {},
+              "type": "array"
+            },
+            "keywords": {
+              "items": {
+                "type": "string"
+              },
+              "type": "array"
+            },
+            "microdata": {
+              "items": {},
+              "type": "array"
+            },
+            "og_tags": {
+              "additionalProperties": {},
+              "type": "object"
+            },
+            "robots": {
+              "type": "string"
+            },
+            "title": {
+              "type": "string"
+            },
+            "twitter_tags": {
+              "additionalProperties": {},
+              "type": "object"
+            },
+            "url": {
+              "type": "string"
+            },
+            "viewport": {
+              "type": "string"
+            }
+          },
+          "type": "object"
+        },
+        "rawHtml": {
+          "type": "string"
+        },
+        "screenshots": {
+          "description": "Present for the \"screenshot\" format; each item carries a resourceUri once published",
+          "items": {
+            "additionalProperties": true,
+            "properties": {},
+            "type": "object"
+          },
+          "type": "array"
+        },
+        "text": {
+          "type": "string"
+        }
+      },
+      "type": "object"
+    },
+    "success": {
+      "description": "Whether the scrape completed",
+      "type": "boolean"
+    },
+    "url": {
+      "description": "Final URL after redirects",
+      "type": "string"
+    },
+    "warnings": {
+      "description": "Per-format warnings; partial success never fails the whole call",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    }
+  },
+  "type": "object"
+}