Tongyi FaRui Plus, identified by the producer as farui-plus, is built on the Qwen foundation and specialized with legal data and knowledge. The maker describes development using model fine-tuning, reinforcement learning, retrieval augmentation and legal-agent technology. Its task scope includes legal questions, identifying applicable legal provisions, case analysis, legal-document generation and contract-clause review.
The documented input and output are text. Prepare the passage, facts or clauses to analyze as readable text, and specify the result wanted. A useful artifact can be a draft section, a list of issues, an explanation of a supplied provision or a comparison between contract wording.
The producer examples support a single instruction or a messages-based conversation. Messages carry a role and content; the optional system instruction comes first, followed by user and assistant turns. The guide recommends messages for continuing dialogue, with relevant prior answers retained when a follow-up changes a fact or requirement.
For a case question, provide the parties’ roles, chronology, disputed issue and evidence relevant to the question. State the jurisdiction and date that matter to the task, and include the legal text to examine when the answer must rely on a particular provision. Keep an asserted fact separate from a disputed allegation or an assumption.
For a follow-up, identify exactly what changed. For example, supply a corrected date or an additional clause and ask which part of the earlier draft needs revision. Retaining the actual earlier answer makes the requested change concrete rather than inviting a new analysis of an incomplete case.
For a legal question, define the issue and the form of the answer. Request the conclusion, supporting provision and facts that would change the analysis. When the source does not establish an important detail, ask the result to identify that missing information.
For drafting, specify the document type, intended audience, required sections and supplied facts. A useful brief is: “Draft the requested section using this chronology and these facts, preserve the parties’ defined roles, and identify the information still needed to complete the document.” Review names, dates, amounts and cited provisions against the original material.
For contract review, provide the exact clause and the concern to examine. Ask for a comparison of the wording, the issue it raises and a proposed revision that preserves the intended commercial meaning. Keep the original clause alongside the proposed text so the change can be inspected.
The published model overview lists a maximum input of 12,000 tokens and a maximum output of 2,000 tokens. Select the relevant excerpts and an answer length suited to the task, leaving room for the requested response within the applicable conversation configuration. A long contract review can be divided into clearly labeled issues or sections while retaining any clause needed to understand the relationship between them.
The producer’s response-length setting can reduce the output allowance for a concise explanation or a specific draft section. Its documented default is 2,000 tokens. Check whether a returned answer is complete before treating it as a finished document.
The producer reference documents top_p in the open interval from 0 to 1, with 0.8 as the default. Its top_k setting restricts the candidate set; leaving it unset, or setting it above 100, disables that strategy. Keep the task and source material stable when comparing the effect of a supported generation setting.
Non-streaming is the default workflow. Streaming delivers text while generation continues. The documented default streaming chunks contain accumulated content; enabling incremental output returns new portions instead. Assemble the chosen format correctly so repeated cumulative text is not appended twice, and retain the completed answer for review.
The response can use a text or message envelope. The envelope is the delivery structure around the generated legal text; the model’s capabilities table does not list schema-enforced structured output, function calling or native web search. Supply the evidence and provisions needed for the task rather than assuming an external lookup occurred.
Preserve the source text, supplied facts, requested document form and final response together. Check the actual wording of references and the jurisdiction or date on which an interpretation depends. A clause comparison or case explanation is most useful when its assumptions and supporting passages remain identifiable.
Use Farui Plus for its named legal-text workflow. The final artifact should connect the requested legal question or draft to the material actually supplied.
", "aboutText": "### A legal-industry text model\n\nTongyi FaRui Plus, identified by the producer as farui-plus, is built on the Qwen foundation and specialized with legal data and knowledge. The maker describes development using model fine-tuning, reinforcement learning, retrieval augmentation and legal-agent technology. Its task scope includes legal questions, identifying applicable legal provisions, case analysis, legal-document generation and contract-clause review.\n\nThe documented input and output are text. Prepare the passage, facts or clauses to analyze as readable text, and specify the result wanted. A useful artifact can be a draft section, a list of issues, an explanation of a supplied provision or a comparison between contract wording.\n\n### Prepare one request or a continuing dialogue\n\nThe producer examples support a single instruction or a messages-based conversation. Messages carry a role and content; the optional system instruction comes first, followed by user and assistant turns. The guide recommends messages for continuing dialogue, with relevant prior answers retained when a follow-up changes a fact or requirement.\n\nFor a case question, provide the parties’ roles, chronology, disputed issue and evidence relevant to the question. State the jurisdiction and date that matter to the task, and include the legal text to examine when the answer must rely on a particular provision. Keep an asserted fact separate from a disputed allegation or an assumption.\n\nFor a follow-up, identify exactly what changed. For example, supply a corrected date or an additional clause and ask which part of the earlier draft needs revision. Retaining the actual earlier answer makes the requested change concrete rather than inviting a new analysis of an incomplete case.\n\n### Ask for an analysis or document draft\n\nFor a legal question, define the issue and the form of the answer. Request the conclusion, supporting provision and facts that would change the analysis. When the source does not establish an important detail, ask the result to identify that missing information.\n\nFor drafting, specify the document type, intended audience, required sections and supplied facts. A useful brief is: “Draft the requested section using this chronology and these facts, preserve the parties’ defined roles, and identify the information still needed to complete the document.” Review names, dates, amounts and cited provisions against the original material.\n\nFor contract review, provide the exact clause and the concern to examine. Ask for a comparison of the wording, the issue it raises and a proposed revision that preserves the intended commercial meaning. Keep the original clause alongside the proposed text so the change can be inspected.\n\n### Work within the documented response bounds\n\nThe published model overview lists a maximum input of 12,000 tokens and a maximum output of 2,000 tokens. Select the relevant excerpts and an answer length suited to the task, leaving room for the requested response within the applicable conversation configuration. A long contract review can be divided into clearly labeled issues or sections while retaining any clause needed to understand the relationship between them.\n\nThe producer’s response-length setting can reduce the output allowance for a concise explanation or a specific draft section. Its documented default is 2,000 tokens. Check whether a returned answer is complete before treating it as a finished document.\n\n### Choose generation and delivery settings\n\nThe producer reference documents top_p in the open interval from 0 to 1, with 0.8 as the default. Its top_k setting restricts the candidate set; leaving it unset, or setting it above 100, disables that strategy. Keep the task and source material stable when comparing the effect of a supported generation setting.\n\nNon-streaming is the default workflow. Streaming delivers text while generation continues. The documented default streaming chunks contain accumulated content; enabling incremental output returns new portions instead. Assemble the chosen format correctly so repeated cumulative text is not appended twice, and retain the completed answer for review.\n\nThe response can use a text or message envelope. The envelope is the delivery structure around the generated legal text; the model’s capabilities table does not list schema-enforced structured output, function calling or native web search. Supply the evidence and provisions needed for the task rather than assuming an external lookup occurred.\n\n### Keep the analysis inspectable\n\nPreserve the source text, supplied facts, requested document form and final response together. Check the actual wording of references and the jurisdiction or date on which an interpretation depends. A clause comparison or case explanation is most useful when its assumptions and supporting passages remain identifiable.\n\nUse Farui Plus for its named legal-text workflow. The final artifact should connect the requested legal question or draft to the material actually supplied.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "38b4dff3eb6b02dd4f89fe4791ea83f81e60bb0910d42b8eb4b5cf33ed76e9c5", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "en", "methods": [ { "html": "farui-plusAlibaba’s Tongyi FaRui Plus is a text model specialized in legal questions, case analysis, legal-document drafting and contract review. Prepare the facts and relevant clauses as text, then use a focused question or dialogue to obtain a written analysis or draft.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Tongyi FaRui Plus, identified by the producer as farui-plus, is built on the Qwen foundation and specialized with legal data and knowledge. The maker describes development using model fine-tuning, reinforcement learning, retrieval augmentation and legal-agent technology. Its task scope includes legal questions, identifying applicable legal provisions, case analysis, legal-document generation and contract-clause review.
The documented input and output are text. Prepare the passage, facts or clauses to analyze as readable text, and specify the result wanted. A useful artifact can be a draft section, a list of issues, an explanation of a supplied provision or a comparison between contract wording.
The producer examples support a single instruction or a messages-based conversation. Messages carry a role and content; the optional system instruction comes first, followed by user and assistant turns. The guide recommends messages for continuing dialogue, with relevant prior answers retained when a follow-up changes a fact or requirement.
For a case question, provide the parties’ roles, chronology, disputed issue and evidence relevant to the question. State the jurisdiction and date that matter to the task, and include the legal text to examine when the answer must rely on a particular provision. Keep an asserted fact separate from a disputed allegation or an assumption.
For a follow-up, identify exactly what changed. For example, supply a corrected date or an additional clause and ask which part of the earlier draft needs revision. Retaining the actual earlier answer makes the requested change concrete rather than inviting a new analysis of an incomplete case.
For a legal question, define the issue and the form of the answer. Request the conclusion, supporting provision and facts that would change the analysis. When the source does not establish an important detail, ask the result to identify that missing information.
For drafting, specify the document type, intended audience, required sections and supplied facts. A useful brief is: “Draft the requested section using this chronology and these facts, preserve the parties’ defined roles, and identify the information still needed to complete the document.” Review names, dates, amounts and cited provisions against the original material.
For contract review, provide the exact clause and the concern to examine. Ask for a comparison of the wording, the issue it raises and a proposed revision that preserves the intended commercial meaning. Keep the original clause alongside the proposed text so the change can be inspected.
The published model overview lists a maximum input of 12,000 tokens and a maximum output of 2,000 tokens. Select the relevant excerpts and an answer length suited to the task, leaving room for the requested response within the applicable conversation configuration. A long contract review can be divided into clearly labeled issues or sections while retaining any clause needed to understand the relationship between them.
The producer’s response-length setting can reduce the output allowance for a concise explanation or a specific draft section. Its documented default is 2,000 tokens. Check whether a returned answer is complete before treating it as a finished document.
The producer reference documents top_p in the open interval from 0 to 1, with 0.8 as the default. Its top_k setting restricts the candidate set; leaving it unset, or setting it above 100, disables that strategy. Keep the task and source material stable when comparing the effect of a supported generation setting.
Non-streaming is the default workflow. Streaming delivers text while generation continues. The documented default streaming chunks contain accumulated content; enabling incremental output returns new portions instead. Assemble the chosen format correctly so repeated cumulative text is not appended twice, and retain the completed answer for review.
The response can use a text or message envelope. The envelope is the delivery structure around the generated legal text; the model’s capabilities table does not list schema-enforced structured output, function calling or native web search. Supply the evidence and provisions needed for the task rather than assuming an external lookup occurred.
Preserve the source text, supplied facts, requested document form and final response together. Check the actual wording of references and the jurisdiction or date on which an interpretation depends. A clause comparison or case explanation is most useful when its assumptions and supporting passages remain identifiable.
Use Farui Plus for its named legal-text workflow. The final artifact should connect the requested legal question or draft to the material actually supplied.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits farui-plus | 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 $0.0058 / 1K tokens Output · Output tokens $0.0058 / 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 $0.0058 / 1K tokens Output · Output tokens $0.0058 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model":"farui-plus","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="farui-plus", 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 farui-plus
/chat/completions
farui-plusAlibaba’s Tongyi FaRui Plus is a text model specialized in legal questions, case analysis, legal-document drafting and contract review. Prepare the facts and relevant clauses as text, then use a focused question or dialogue to obtain a written analysis or draft.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Tongyi FaRui Plus, identified by the producer as farui-plus, is built on the Qwen foundation and specialized with legal data and knowledge. The maker describes development using model fine-tuning, reinforcement learning, retrieval augmentation and legal-agent technology. Its task scope includes legal questions, identifying applicable legal provisions, case analysis, legal-document generation and contract-clause review.
The documented input and output are text. Prepare the passage, facts or clauses to analyze as readable text, and specify the result wanted. A useful artifact can be a draft section, a list of issues, an explanation of a supplied provision or a comparison between contract wording.
The producer examples support a single instruction or a messages-based conversation. Messages carry a role and content; the optional system instruction comes first, followed by user and assistant turns. The guide recommends messages for continuing dialogue, with relevant prior answers retained when a follow-up changes a fact or requirement.
For a case question, provide the parties’ roles, chronology, disputed issue and evidence relevant to the question. State the jurisdiction and date that matter to the task, and include the legal text to examine when the answer must rely on a particular provision. Keep an asserted fact separate from a disputed allegation or an assumption.
For a follow-up, identify exactly what changed. For example, supply a corrected date or an additional clause and ask which part of the earlier draft needs revision. Retaining the actual earlier answer makes the requested change concrete rather than inviting a new analysis of an incomplete case.
For a legal question, define the issue and the form of the answer. Request the conclusion, supporting provision and facts that would change the analysis. When the source does not establish an important detail, ask the result to identify that missing information.
For drafting, specify the document type, intended audience, required sections and supplied facts. A useful brief is: “Draft the requested section using this chronology and these facts, preserve the parties’ defined roles, and identify the information still needed to complete the document.” Review names, dates, amounts and cited provisions against the original material.
For contract review, provide the exact clause and the concern to examine. Ask for a comparison of the wording, the issue it raises and a proposed revision that preserves the intended commercial meaning. Keep the original clause alongside the proposed text so the change can be inspected.
The published model overview lists a maximum input of 12,000 tokens and a maximum output of 2,000 tokens. Select the relevant excerpts and an answer length suited to the task, leaving room for the requested response within the applicable conversation configuration. A long contract review can be divided into clearly labeled issues or sections while retaining any clause needed to understand the relationship between them.
The producer’s response-length setting can reduce the output allowance for a concise explanation or a specific draft section. Its documented default is 2,000 tokens. Check whether a returned answer is complete before treating it as a finished document.
The producer reference documents top_p in the open interval from 0 to 1, with 0.8 as the default. Its top_k setting restricts the candidate set; leaving it unset, or setting it above 100, disables that strategy. Keep the task and source material stable when comparing the effect of a supported generation setting.
Non-streaming is the default workflow. Streaming delivers text while generation continues. The documented default streaming chunks contain accumulated content; enabling incremental output returns new portions instead. Assemble the chosen format correctly so repeated cumulative text is not appended twice, and retain the completed answer for review.
The response can use a text or message envelope. The envelope is the delivery structure around the generated legal text; the model’s capabilities table does not list schema-enforced structured output, function calling or native web search. Supply the evidence and provisions needed for the task rather than assuming an external lookup occurred.
Preserve the source text, supplied facts, requested document form and final response together. Check the actual wording of references and the jurisdiction or date on which an interpretation depends. A clause comparison or case explanation is most useful when its assumptions and supporting passages remain identifiable.
Use Farui Plus for its named legal-text workflow. The final artifact should connect the requested legal question or draft to the material actually supplied.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits farui-plus | 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 $0.0058 / 1K tokens Output · Output tokens $0.0058 / 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 $0.0058 / 1K tokens Output · Output tokens $0.0058 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "farui-plus",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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': 'farui-plus', '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': 'farui-plus', '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 farui-plus
/chat/completions