Summarize is ScaleDown’s abstractive summarization model. It condenses supplied text and documents into a fluent rewrite rather than selecting a few original sentences verbatim. Its published uses include document review, transcript digests and shortening retrieved material before another model consumes it.
Give the task a focus and an intended reader. A meeting digest can retain decisions, responsibilities and open questions. A document review can retain the main claims and supporting evidence. A retrieval workflow can retain the facts that matter to the question the next model will answer.
Specify the desired language, length and layout in the content instructions. The published model uses system-prompt direction for those choices, while its sampling configuration is fixed for faithful output. A summary for a person and a compact passage for another model can therefore use different layouts without treating sampling variation as the main control.
Keep document names and important section boundaries with the source. Ask the summary to preserve names, numbers, stated decisions and any disagreement that affects interpretation. For a transcript, distinguish a proposal from a decision and an unresolved question from an assigned action.
After generation, compare the condensed text with the original material. Check whether a sentence changes the certainty of a claim, drops a condition or combines statements that belong to different speakers or sections. The purpose of a shorter result is to make the evidence easier to consume while keeping its meaning.
The published input range includes text, images and files such as PDFs, and the model returns text. Supply readable material and define whether the task concerns the whole document or a selected section. A collection benefits from consistent summary questions and a document identifier retained with each result.
For retrieval pre-processing, shorten content around the specific question that downstream reasoning must address. Retain the passages or facts that support an answer instead of producing a generic overview of the source. Keep the original retrieved material available so the later result can still be checked against it.
The published context window is 1,000,000 tokens and the completion limit is 4,000 tokens. Set a summary length that fits the intended artifact. If a large collection needs substantial detail, organise it into identified documents or sections and retain a separate result for each before composing a collection-level digest.
The result is a text summary. Validate any machine-consumed structure in the application, while keeping the written summary readable for its intended audience. Save the summary with the source identity and the instructions that determined its focus, language and length.
scaledown/summarizeSummarize rewrites long text and documents into a fluent, faithful condensation. Set the focus, language, length and format through instructions, then use the result for document review, transcript digests or shorter retrieval context. The published window is 1,000,000 tokens, with a 4,000-token completion limit.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Summarize is ScaleDown’s abstractive summarization model. It condenses supplied text and documents into a fluent rewrite rather than selecting a few original sentences verbatim. Its published uses include document review, transcript digests and shortening retrieved material before another model consumes it.
Give the task a focus and an intended reader. A meeting digest can retain decisions, responsibilities and open questions. A document review can retain the main claims and supporting evidence. A retrieval workflow can retain the facts that matter to the question the next model will answer.
Specify the desired language, length and layout in the content instructions. The published model uses system-prompt direction for those choices, while its sampling configuration is fixed for faithful output. A summary for a person and a compact passage for another model can therefore use different layouts without treating sampling variation as the main control.
Keep document names and important section boundaries with the source. Ask the summary to preserve names, numbers, stated decisions and any disagreement that affects interpretation. For a transcript, distinguish a proposal from a decision and an unresolved question from an assigned action.
After generation, compare the condensed text with the original material. Check whether a sentence changes the certainty of a claim, drops a condition or combines statements that belong to different speakers or sections. The purpose of a shorter result is to make the evidence easier to consume while keeping its meaning.
The published input range includes text, images and files such as PDFs, and the model returns text. Supply readable material and define whether the task concerns the whole document or a selected section. A collection benefits from consistent summary questions and a document identifier retained with each result.
For retrieval pre-processing, shorten content around the specific question that downstream reasoning must address. Retain the passages or facts that support an answer instead of producing a generic overview of the source. Keep the original retrieved material available so the later result can still be checked against it.
The published context window is 1,000,000 tokens and the completion limit is 4,000 tokens. Set a summary length that fits the intended artifact. If a large collection needs substantial detail, organise it into identified documents or sections and retain a separate result for each before composing a collection-level digest.
The result is a text summary. Validate any machine-consumed structure in the application, while keeping the written summary readable for its intended audience. Save the summary with the source identity and the instructions that determined its focus, language and length.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits scaledown/summarize | Default— |
Fieldmessages | Typemessage[] | RequirementRequired | Values & limits Minimum items: 1 | Default— |
Fieldmessages[].role | Typestring | RequirementRequired | Values & limits Model-specific | Default— |
Fieldmessages[].content | Typestring | RequirementOptional | Values & limits Applies when: Text conversation | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
Text · UTF8 text
messages[].content
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, messages |
Parametermaterial_types | Contracttext |
Parametermessages | Contractmessage array with role/content shape |
Parameterfile_material | Contractactual UTF-8 document inserted as literal text; no file ID inferred |
Parameteroptional_controls | Contractstream |
Parametercontrol_scope | ContractText conversation; stream is a boolean and defaults to false. |
Parameteroutput_modalities | Contracttext |
Parameterhosted_operations | Contractfalse |
Parametermultimodal_input_binding | Contractnull |
Method aliases: /chat/completions
Lifecycle: synchronous_or_streamed
Send exact model ID with messages.
Context length is not an output cap.
A text file may supply literal text; image/audio/file-object inputs need exact binding.
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 | Context tokens, more than | Context tokens, up to and including | Charge |
|---|---|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0001 / 1K tokens Output · Output tokens $0 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationRequest-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0001 / 1K tokens Output · Output tokens $0 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model":"scaledown/summarize","messages":[{"role":"user","content":"hello"}],"stream":false}')\n\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path("result.json").read_text())\nfor x in r.get("choices",[]):\n if x.get("message",{}).get("content"): print(x["message"]["content"])\nPY_RESULT\nfrom openai import OpenAI\nimport os\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nresult=client.chat.completions.create(model="scaledown/summarize", messages=[{"role":"user","content":"hello"}], stream=False)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(result.to_dict(mode="json"))\njson or SSE
Keep every complete returned response, file and content part.
Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.
Keep request/response IDs and headers. No generic text job retrieval URL is supplied.
| Field | Type |
|---|---|
Fieldchoices[].index | Typeinteger |
Fieldchoices[].message.content | Typestring|null |
Fieldchoices[].message.tool_calls | Typetool_call[] |
Fieldchoices[].message.reasoning_content | Typestring |
Fieldchoices[].message.reasoning_details | Typeobject|array |
Fieldchoices[].finish_reason | Typestring|null |
Fieldusage | Typeobject |
| Response | Condition | Next step |
|---|---|---|
Response400 · invalid_request_error | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |
Ailoot Ultra scaledown/summarize
/chat/completions
scaledown/summarizeSummarize rewrites long text and documents into a fluent, faithful condensation. Set the focus, language, length and format through instructions, then use the result for document review, transcript digests or shorter retrieval context. The published window is 1,000,000 tokens, with a 4,000-token completion limit.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Summarize is ScaleDown’s abstractive summarization model. It condenses supplied text and documents into a fluent rewrite rather than selecting a few original sentences verbatim. Its published uses include document review, transcript digests and shortening retrieved material before another model consumes it.
Give the task a focus and an intended reader. A meeting digest can retain decisions, responsibilities and open questions. A document review can retain the main claims and supporting evidence. A retrieval workflow can retain the facts that matter to the question the next model will answer.
Specify the desired language, length and layout in the content instructions. The published model uses system-prompt direction for those choices, while its sampling configuration is fixed for faithful output. A summary for a person and a compact passage for another model can therefore use different layouts without treating sampling variation as the main control.
Keep document names and important section boundaries with the source. Ask the summary to preserve names, numbers, stated decisions and any disagreement that affects interpretation. For a transcript, distinguish a proposal from a decision and an unresolved question from an assigned action.
After generation, compare the condensed text with the original material. Check whether a sentence changes the certainty of a claim, drops a condition or combines statements that belong to different speakers or sections. The purpose of a shorter result is to make the evidence easier to consume while keeping its meaning.
The published input range includes text, images and files such as PDFs, and the model returns text. Supply readable material and define whether the task concerns the whole document or a selected section. A collection benefits from consistent summary questions and a document identifier retained with each result.
For retrieval pre-processing, shorten content around the specific question that downstream reasoning must address. Retain the passages or facts that support an answer instead of producing a generic overview of the source. Keep the original retrieved material available so the later result can still be checked against it.
The published context window is 1,000,000 tokens and the completion limit is 4,000 tokens. Set a summary length that fits the intended artifact. If a large collection needs substantial detail, organise it into identified documents or sections and retain a separate result for each before composing a collection-level digest.
The result is a text summary. Validate any machine-consumed structure in the application, while keeping the written summary readable for its intended audience. Save the summary with the source identity and the instructions that determined its focus, language and length.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits scaledown/summarize | Default— |
Fieldmessages | Typemessage[] | RequirementRequired | Values & limits | Default— |
Fieldmessages[].role | Typestring | RequirementRequired | Values & limits user, assistant | Default— |
Fieldmessages[].content | Typestring | RequirementRequired | Values & limits | Default— |
Fieldmax_tokens | Typeinteger | RequirementRequired | Values & limits | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
Text · UTF-8 text
messages[].content string
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, messages, max_tokens |
Parameteroptional_controls | Contractstream |
Parametermaterial_types | Contracttext |
Parametertext_file_material | ContractRead the actual UTF-8 document and put its text in the indicated input or message content string. |
Lifecycle: synchronous_or_streamed
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 | Context tokens, more than | Context tokens, up to and including | Charge |
|---|---|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0001 / 1K tokens Output · Output tokens $0 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationRequest-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0001 / 1K tokens Output · Output tokens $0 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "scaledown/summarize",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 document}"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ['AILOOT_TEXT_FILE'])\nif not source_file.is_file():\n raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')\ntext = source_file.read_text(encoding='utf-8')\nif not text.strip():\n raise SystemExit('Choose a document containing text')\npayload = {'model': 'scaledown/summarize', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}\npayload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\\n\\n' + text\nPath('request.json').write_text(json.dumps(payload, ensure_ascii=False), encoding='utf-8')\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\n\nresult = json.loads(Path('result.json').read_text(encoding='utf-8'))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\nPY_RESULT\nimport json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ['AILOOT_TEXT_FILE'])\nif not source_file.is_file():\n raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')\ntext = source_file.read_text(encoding='utf-8')\nif not text.strip():\n raise SystemExit('Choose a document containing text')\npayload = {'model': 'scaledown/summarize', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}\npayload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\\n\\n' + text\nfrom urllib.request import Request, urlopen\nfrom urllib.error import HTTPError\n\napi_key = os.environ['AILOOT_API_KEY']\nif not api_key.strip():\n raise SystemExit('Set AILOOT_API_KEY before making a request')\nheaders = {'x-api-key': 'PLACEHOLDER_KEY', 'anthropic-version': '2023-06-01', 'Content-Type': 'application/json'}\nheaders['x-api-key'] = api_key\nrequest = Request('https://api.ailoot.ai/v1/messages', data=json.dumps(payload, ensure_ascii=False).encode('utf-8'), headers=headers, method='POST')\ntry:\n with urlopen(request, timeout=120) as response:\n raw = response.read()\n Path('response-headers.txt').write_text(str(response.headers), encoding='utf-8')\nexcept HTTPError as error:\n Path('result.json').write_bytes(error.read())\n Path('response-headers.txt').write_text(str(error.headers), encoding='utf-8')\n raise\nPath('result.json').write_bytes(raw)\nimport json\nfrom pathlib import Path\n\nresult = json.loads(Path('result.json').read_text(encoding='utf-8'))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\nJSON or SSE
Keep every complete returned response, file and content part.
Keep all content blocks, thinking signatures and actual tool-use IDs. Assemble all SSE block deltas; a first text block is not the complete output.
Keep request/response IDs and headers. No generic text job retrieval URL is supplied.
| Field | Type |
|---|---|
Fieldid | Typestring |
Fieldmodel | Typestring |
Fieldcontent[] | Typetext|thinking|tool_use|other content block |
Fieldstop_reason | Typestring|null |
Fieldusage | Typeobject |
| Response | Condition | Next step |
|---|---|---|
Response400 · invalid_request_error | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |
Ailoot Ultra scaledown/summarize
/chat/completions