Ling 3.1 Flash is inclusionAI’s hybrid reasoning language model for tasks that involve several stages rather than a single short answer. The manufacturer positions it for everyday office work, extended software engineering and complex agent workflows. It uses a mixture-of-experts architecture with approximately 560B total parameters and about 25B active for each token, balancing a large model capacity with a smaller amount of active computation.
Its central design goal is maintaining task state and correcting the course of longer work. In a tool-connected workflow, the model can plan several steps, interpret intermediate results and revise the next step when the evidence changes. Give it a precise objective, the available materials and a definition of completion. For example: “Review these incident notes, identify the unresolved causes, and produce a prioritized investigation plan. For each action, name the evidence needed to decide whether it worked.” This turns a vague request into a result that can be inspected and continued.
For office work, useful inputs include source notes, text extracted from documents, tables with clear column definitions, and the intended audience for a report. State the period, units and comparison to use. Ask for a written deliverable such as a management brief, a report outline or an explanation of the important changes. An example is: “Using only these quarterly tables, explain the largest changes, distinguish observed values from assumptions, and draft a briefing with the unanswered questions at the end.” Keep source labels with the input so the resulting claims can be traced back to the correct material.
For software development, the manufacturer highlights cross-language refactoring, performance optimization and analysis of frequently used areas of a codebase. Provide the relevant files as text, the behavior to preserve, the dependency versions and any failing output or measurements. A useful request asks for a proposed change and the checks needed to assess it: “Refactor this parser while preserving the documented output format. Explain the affected behavior, show the revised code, and identify cases that would reveal a regression.” For performance work, supply actual profiles or timings and ask it to connect each recommendation to a measured bottleneck.
For professional analysis, gather the relevant rules, definitions and evidence before asking for a recommendation. Ling 3.1 Flash is intended to synthesize scattered information, interpret indicators and develop action suggestions. Ask for a comparison that names the assumptions and remaining information needed, rather than an unsupported verdict. For example, supply several project proposals and request a decision memo using the same criteria for each, with source-backed observations separated from inferred consequences. When the evidence conflicts, request the conflicting passages and the question that would resolve them.
The manufacturer distinguishes a model context ceiling of 1M tokens from the 256K context currently opened by its official service. These figures describe different boundaries. Organize working material around the applicable window and reserve space for the response; a model-level ceiling does not mean every interface accepts that much input. For a large task, keep the objective, completed decisions, unresolved questions and source references together. Use explicit boundaries around documents and code so material to analyze is not confused with instructions to follow.
Prepare tool-connected tasks with clear tool descriptions, expected arguments and useful result records. Feed actual results back into the conversation so the next proposal is based on observations. Ask the model to explain what a returned result changes and what evidence is still missing. The model’s agent-oriented design supports this planning and feedback pattern; the surrounding application carries out the tool steps and preserves their results. A proposed command, code change or report is most useful when its status is clear: suggested, executed with a recorded result, or still awaiting verification.
Ling 3.1 Flash belongs to the language-model line; the separate Ling 3.0 Flash VL edition is the manufacturer’s visual model. For this text task, prepare textual source content and retain its structure, labels and provenance. Specify the output language and form, such as a concise memo, a table of findings, a patch explanation or a numbered plan. Ask the model to flag missing information and check the requested deliverable against the original constraints. Long workflows still need inspection of intermediate results: an early mistaken assumption can otherwise be carried into later reasoning and polished into a convincing final report.
", "aboutText": "Ling 3.1 Flash is inclusionAI’s hybrid reasoning language model for tasks that involve several stages rather than a single short answer. The manufacturer positions it for everyday office work, extended software engineering and complex agent workflows. It uses a mixture-of-experts architecture with approximately 560B total parameters and about 25B active for each token, balancing a large model capacity with a smaller amount of active computation.\n\nIts central design goal is maintaining task state and correcting the course of longer work. In a tool-connected workflow, the model can plan several steps, interpret intermediate results and revise the next step when the evidence changes. Give it a precise objective, the available materials and a definition of completion. For example: “Review these incident notes, identify the unresolved causes, and produce a prioritized investigation plan. For each action, name the evidence needed to decide whether it worked.” This turns a vague request into a result that can be inspected and continued.\n\nFor office work, useful inputs include source notes, text extracted from documents, tables with clear column definitions, and the intended audience for a report. State the period, units and comparison to use. Ask for a written deliverable such as a management brief, a report outline or an explanation of the important changes. An example is: “Using only these quarterly tables, explain the largest changes, distinguish observed values from assumptions, and draft a briefing with the unanswered questions at the end.” Keep source labels with the input so the resulting claims can be traced back to the correct material.\n\nFor software development, the manufacturer highlights cross-language refactoring, performance optimization and analysis of frequently used areas of a codebase. Provide the relevant files as text, the behavior to preserve, the dependency versions and any failing output or measurements. A useful request asks for a proposed change and the checks needed to assess it: “Refactor this parser while preserving the documented output format. Explain the affected behavior, show the revised code, and identify cases that would reveal a regression.” For performance work, supply actual profiles or timings and ask it to connect each recommendation to a measured bottleneck.\n\nFor professional analysis, gather the relevant rules, definitions and evidence before asking for a recommendation. Ling 3.1 Flash is intended to synthesize scattered information, interpret indicators and develop action suggestions. Ask for a comparison that names the assumptions and remaining information needed, rather than an unsupported verdict. For example, supply several project proposals and request a decision memo using the same criteria for each, with source-backed observations separated from inferred consequences. When the evidence conflicts, request the conflicting passages and the question that would resolve them.\n\nThe manufacturer distinguishes a model context ceiling of 1M tokens from the 256K context currently opened by its official service. These figures describe different boundaries. Organize working material around the applicable window and reserve space for the response; a model-level ceiling does not mean every interface accepts that much input. For a large task, keep the objective, completed decisions, unresolved questions and source references together. Use explicit boundaries around documents and code so material to analyze is not confused with instructions to follow.\n\nPrepare tool-connected tasks with clear tool descriptions, expected arguments and useful result records. Feed actual results back into the conversation so the next proposal is based on observations. Ask the model to explain what a returned result changes and what evidence is still missing. The model’s agent-oriented design supports this planning and feedback pattern; the surrounding application carries out the tool steps and preserves their results. A proposed command, code change or report is most useful when its status is clear: suggested, executed with a recorded result, or still awaiting verification.\n\nLing 3.1 Flash belongs to the language-model line; the separate Ling 3.0 Flash VL edition is the manufacturer’s visual model. For this text task, prepare textual source content and retain its structure, labels and provenance. Specify the output language and form, such as a concise memo, a table of findings, a patch explanation or a numbered plan. Ask the model to flag missing information and check the requested deliverable against the original constraints. Long workflows still need inspection of intermediate results: an early mistaken assumption can otherwise be carried into later reasoning and polished into a convincing final report.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "9dc65ccdf9dc9530ef9731186666af336b09c0b3f425996be95443addc08b80d", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "en", "methods": [ { "html": "inclusionai/ling-3.1-flashLing 3.1 Flash is inclusionAI’s hybrid reasoning model for office work, extended software development and complex agents. Its sparse 560B-parameter architecture activates about 25B parameters per token, supporting multi-step planning, tool interaction and revisions from intermediate results.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Ling 3.1 Flash is inclusionAI’s hybrid reasoning language model for tasks that involve several stages rather than a single short answer. The manufacturer positions it for everyday office work, extended software engineering and complex agent workflows. It uses a mixture-of-experts architecture with approximately 560B total parameters and about 25B active for each token, balancing a large model capacity with a smaller amount of active computation.
Its central design goal is maintaining task state and correcting the course of longer work. In a tool-connected workflow, the model can plan several steps, interpret intermediate results and revise the next step when the evidence changes. Give it a precise objective, the available materials and a definition of completion. For example: “Review these incident notes, identify the unresolved causes, and produce a prioritized investigation plan. For each action, name the evidence needed to decide whether it worked.” This turns a vague request into a result that can be inspected and continued.
For office work, useful inputs include source notes, text extracted from documents, tables with clear column definitions, and the intended audience for a report. State the period, units and comparison to use. Ask for a written deliverable such as a management brief, a report outline or an explanation of the important changes. An example is: “Using only these quarterly tables, explain the largest changes, distinguish observed values from assumptions, and draft a briefing with the unanswered questions at the end.” Keep source labels with the input so the resulting claims can be traced back to the correct material.
For software development, the manufacturer highlights cross-language refactoring, performance optimization and analysis of frequently used areas of a codebase. Provide the relevant files as text, the behavior to preserve, the dependency versions and any failing output or measurements. A useful request asks for a proposed change and the checks needed to assess it: “Refactor this parser while preserving the documented output format. Explain the affected behavior, show the revised code, and identify cases that would reveal a regression.” For performance work, supply actual profiles or timings and ask it to connect each recommendation to a measured bottleneck.
For professional analysis, gather the relevant rules, definitions and evidence before asking for a recommendation. Ling 3.1 Flash is intended to synthesize scattered information, interpret indicators and develop action suggestions. Ask for a comparison that names the assumptions and remaining information needed, rather than an unsupported verdict. For example, supply several project proposals and request a decision memo using the same criteria for each, with source-backed observations separated from inferred consequences. When the evidence conflicts, request the conflicting passages and the question that would resolve them.
The manufacturer distinguishes a model context ceiling of 1M tokens from the 256K context currently opened by its official service. These figures describe different boundaries. Organize working material around the applicable window and reserve space for the response; a model-level ceiling does not mean every interface accepts that much input. For a large task, keep the objective, completed decisions, unresolved questions and source references together. Use explicit boundaries around documents and code so material to analyze is not confused with instructions to follow.
Prepare tool-connected tasks with clear tool descriptions, expected arguments and useful result records. Feed actual results back into the conversation so the next proposal is based on observations. Ask the model to explain what a returned result changes and what evidence is still missing. The model’s agent-oriented design supports this planning and feedback pattern; the surrounding application carries out the tool steps and preserves their results. A proposed command, code change or report is most useful when its status is clear: suggested, executed with a recorded result, or still awaiting verification.
Ling 3.1 Flash belongs to the language-model line; the separate Ling 3.0 Flash VL edition is the manufacturer’s visual model. For this text task, prepare textual source content and retain its structure, labels and provenance. Specify the output language and form, such as a concise memo, a table of findings, a patch explanation or a numbered plan. Ask the model to flag missing information and check the requested deliverable against the original constraints. Long workflows still need inspection of intermediate results: an early mistaken assumption can otherwise be carried into later reasoning and polished into a convincing final report.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits inclusionai/ling-3.1-flash | 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 $0.0006 / 1K tokens Output · Output tokens $0.0018 / 1K tokens Input · Cache read $0.00012 / 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 $0.0006 / 1K tokens Output · Output tokens $0.0018 / 1K tokens Input · Cache read $0.00012 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model":"inclusionai/ling-3.1-flash","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="inclusionai/ling-3.1-flash", 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 inclusionai/ling-3.1-flash
/chat/completions
inclusionai/ling-3.1-flashLing 3.1 Flash is inclusionAI’s hybrid reasoning model for office work, extended software development and complex agents. Its sparse 560B-parameter architecture activates about 25B parameters per token, supporting multi-step planning, tool interaction and revisions from intermediate results.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Ling 3.1 Flash is inclusionAI’s hybrid reasoning language model for tasks that involve several stages rather than a single short answer. The manufacturer positions it for everyday office work, extended software engineering and complex agent workflows. It uses a mixture-of-experts architecture with approximately 560B total parameters and about 25B active for each token, balancing a large model capacity with a smaller amount of active computation.
Its central design goal is maintaining task state and correcting the course of longer work. In a tool-connected workflow, the model can plan several steps, interpret intermediate results and revise the next step when the evidence changes. Give it a precise objective, the available materials and a definition of completion. For example: “Review these incident notes, identify the unresolved causes, and produce a prioritized investigation plan. For each action, name the evidence needed to decide whether it worked.” This turns a vague request into a result that can be inspected and continued.
For office work, useful inputs include source notes, text extracted from documents, tables with clear column definitions, and the intended audience for a report. State the period, units and comparison to use. Ask for a written deliverable such as a management brief, a report outline or an explanation of the important changes. An example is: “Using only these quarterly tables, explain the largest changes, distinguish observed values from assumptions, and draft a briefing with the unanswered questions at the end.” Keep source labels with the input so the resulting claims can be traced back to the correct material.
For software development, the manufacturer highlights cross-language refactoring, performance optimization and analysis of frequently used areas of a codebase. Provide the relevant files as text, the behavior to preserve, the dependency versions and any failing output or measurements. A useful request asks for a proposed change and the checks needed to assess it: “Refactor this parser while preserving the documented output format. Explain the affected behavior, show the revised code, and identify cases that would reveal a regression.” For performance work, supply actual profiles or timings and ask it to connect each recommendation to a measured bottleneck.
For professional analysis, gather the relevant rules, definitions and evidence before asking for a recommendation. Ling 3.1 Flash is intended to synthesize scattered information, interpret indicators and develop action suggestions. Ask for a comparison that names the assumptions and remaining information needed, rather than an unsupported verdict. For example, supply several project proposals and request a decision memo using the same criteria for each, with source-backed observations separated from inferred consequences. When the evidence conflicts, request the conflicting passages and the question that would resolve them.
The manufacturer distinguishes a model context ceiling of 1M tokens from the 256K context currently opened by its official service. These figures describe different boundaries. Organize working material around the applicable window and reserve space for the response; a model-level ceiling does not mean every interface accepts that much input. For a large task, keep the objective, completed decisions, unresolved questions and source references together. Use explicit boundaries around documents and code so material to analyze is not confused with instructions to follow.
Prepare tool-connected tasks with clear tool descriptions, expected arguments and useful result records. Feed actual results back into the conversation so the next proposal is based on observations. Ask the model to explain what a returned result changes and what evidence is still missing. The model’s agent-oriented design supports this planning and feedback pattern; the surrounding application carries out the tool steps and preserves their results. A proposed command, code change or report is most useful when its status is clear: suggested, executed with a recorded result, or still awaiting verification.
Ling 3.1 Flash belongs to the language-model line; the separate Ling 3.0 Flash VL edition is the manufacturer’s visual model. For this text task, prepare textual source content and retain its structure, labels and provenance. Specify the output language and form, such as a concise memo, a table of findings, a patch explanation or a numbered plan. Ask the model to flag missing information and check the requested deliverable against the original constraints. Long workflows still need inspection of intermediate results: an early mistaken assumption can otherwise be carried into later reasoning and polished into a convincing final report.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits inclusionai/ling-3.1-flash | 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 $0.0006 / 1K tokens Output · Output tokens $0.0018 / 1K tokens Input · Cache read $0.00012 / 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 $0.0006 / 1K tokens Output · Output tokens $0.0018 / 1K tokens Input · Cache read $0.00012 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "inclusionai/ling-3.1-flash",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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': 'inclusionai/ling-3.1-flash', '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': 'inclusionai/ling-3.1-flash', '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 inclusionai/ling-3.1-flash
/chat/completions