SenseChat-5 is the V5 general language model in SenseTime’s SenseNova series. The manufacturer describes its task scope across language, knowledge, reasoning, mathematics and code, with particular attention to open-ended questions, multi-turn dialogue, information extraction and writing. Its documented conversation input is text, and the useful result is a written answer, draft, analysis or tool-related instruction.
Keep the task instructions separate from the material to analyze. The maker’s compatible conversation example uses a system message to define the role and answer format, followed by a user message containing the request. Its native conversation reference also distinguishes system, user and assistant messages. Retain the relevant dialogue in order when a follow-up depends on an earlier answer.
For an extraction task, provide the document and name the fields to return. A useful brief is: “Extract the stated deadline, responsible team and required deliverable into a table, and identify the passage supporting each value.” For a writing task, give the audience, purpose, tone and required sections. Treat a requested word count as a writing instruction and inspect the finished answer for compliance.
The maker lists a 128K context for SenseChat-5. Its native conversation reference explains that the supplied input and the reserved maximum response must fit within the model’s context. Retrieved knowledge or injected reference text also occupies input space. Keep the question, important source passages and enough room for the response together rather than filling the entire allowance with documents.
For a long-source comparison, label each document and preserve section boundaries. Ask which requirements agree, which conflict and which passage supports the difference. Give important definitions and identifiers explicitly. If the task only concerns a few sections, select those sections and the context needed to interpret them so the final comparison remains easy to check.
Supply a complete problem with its assumptions, units and requested final form. Ask for a calculation to identify the values it uses and for an explanation to distinguish a stated fact from an assumption. A conclusion should be checked against the conditions in the problem, especially when several steps depend on one early interpretation.
For code work, include the relevant source, observed behavior and expected result. A useful output is a proposed change with the condition it addresses and the checks needed to assess it. Return the actual error or execution result when the next turn depends on whether a proposal worked. The written answer and the result of running that answer are separate artifacts.
SenseTime’s V5 release documents custom function calling: a connected application can provide tool definitions for the model to select and use. Define each tool’s purpose and arguments around the real operation, then keep its returned observation with the conversation. Ask the final answer to use the actual lookup or operation result rather than infer that a requested action succeeded.
The same V5 release describes a code-interpreter workflow that generates Python for mathematical calculation. This is a connected calculation workflow, not a reason to treat every generated code block as executed. Supply the data to calculate, retain the interpreter’s result and inspect how the written explanation relates to that result.
The producer’s conversation examples show both completed responses and streamed text. A completed answer provides the assistant’s message; streaming delivers successive pieces that must be assembled into the final response. Preserve that final text with the request and source material before using it as a document, report or application response.
Keep the model edition explicit. SenseChat-Turbo is a separate lightweight dialogue model, and SenseChat-5-Cantonese is a separately named adaptation. The producer also publishes distinct vision, fusion-modality and character-dialogue models. Use this SenseChat-5 profile for its documented text-conversation and tool-assisted language work, and review extracted values, reasoning steps and proposed operations against the supplied evidence.
", "aboutText": "### General language and reasoning work\n\nSenseChat-5 is the V5 general language model in SenseTime’s SenseNova series. The manufacturer describes its task scope across language, knowledge, reasoning, mathematics and code, with particular attention to open-ended questions, multi-turn dialogue, information extraction and writing. Its documented conversation input is text, and the useful result is a written answer, draft, analysis or tool-related instruction.\n\n### Prepare the conversation\n\nKeep the task instructions separate from the material to analyze. The maker’s compatible conversation example uses a system message to define the role and answer format, followed by a user message containing the request. Its native conversation reference also distinguishes system, user and assistant messages. Retain the relevant dialogue in order when a follow-up depends on an earlier answer.\n\nFor an extraction task, provide the document and name the fields to return. A useful brief is: “Extract the stated deadline, responsible team and required deliverable into a table, and identify the passage supporting each value.” For a writing task, give the audience, purpose, tone and required sections. Treat a requested word count as a writing instruction and inspect the finished answer for compliance.\n\n### Work with the 128K context\n\nThe maker lists a 128K context for SenseChat-5. Its native conversation reference explains that the supplied input and the reserved maximum response must fit within the model’s context. Retrieved knowledge or injected reference text also occupies input space. Keep the question, important source passages and enough room for the response together rather than filling the entire allowance with documents.\n\nFor a long-source comparison, label each document and preserve section boundaries. Ask which requirements agree, which conflict and which passage supports the difference. Give important definitions and identifiers explicitly. If the task only concerns a few sections, select those sections and the context needed to interpret them so the final comparison remains easy to check.\n\n### Reasoning, mathematics and code\n\nSupply a complete problem with its assumptions, units and requested final form. Ask for a calculation to identify the values it uses and for an explanation to distinguish a stated fact from an assumption. A conclusion should be checked against the conditions in the problem, especially when several steps depend on one early interpretation.\n\nFor code work, include the relevant source, observed behavior and expected result. A useful output is a proposed change with the condition it addresses and the checks needed to assess it. Return the actual error or execution result when the next turn depends on whether a proposal worked. The written answer and the result of running that answer are separate artifacts.\n\n### Custom tools and calculation\n\nSenseTime’s V5 release documents custom function calling: a connected application can provide tool definitions for the model to select and use. Define each tool’s purpose and arguments around the real operation, then keep its returned observation with the conversation. Ask the final answer to use the actual lookup or operation result rather than infer that a requested action succeeded.\n\nThe same V5 release describes a code-interpreter workflow that generates Python for mathematical calculation. This is a connected calculation workflow, not a reason to treat every generated code block as executed. Supply the data to calculate, retain the interpreter’s result and inspect how the written explanation relates to that result.\n\n### Completed answers and streaming\n\nThe producer’s conversation examples show both completed responses and streamed text. A completed answer provides the assistant’s message; streaming delivers successive pieces that must be assembled into the final response. Preserve that final text with the request and source material before using it as a document, report or application response.\n\nKeep the model edition explicit. SenseChat-Turbo is a separate lightweight dialogue model, and SenseChat-5-Cantonese is a separately named adaptation. The producer also publishes distinct vision, fusion-modality and character-dialogue models. Use this SenseChat-5 profile for its documented text-conversation and tool-assisted language work, and review extracted values, reasoning steps and proposed operations against the supplied evidence.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Extract an action from meeting notes\n\nExtract action details from this note: "The logistics team must send the revised packing list by 16:00 on Monday. Finance will review costs later; no date agreed." Return team, deliverable, deadline and supporting quotation for each action. Mark the finance deadline as not stated and keep it separate from the logistics deadline.A two-action table with responsible team, deliverable, deadline and a supporting quote.Ensure the Monday 16:00 deadline is not copied into the finance action.SenseChat-5SenseTime’s SenseChat-5 is a text conversation model for language, knowledge, reasoning, mathematics and code tasks. Its documented 128K context supports longer source material, while the producer’s V5 workflow includes custom function calling and calculation with a code interpreter.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
SenseChat-5 is the V5 general language model in SenseTime’s SenseNova series. The manufacturer describes its task scope across language, knowledge, reasoning, mathematics and code, with particular attention to open-ended questions, multi-turn dialogue, information extraction and writing. Its documented conversation input is text, and the useful result is a written answer, draft, analysis or tool-related instruction.
Keep the task instructions separate from the material to analyze. The maker’s compatible conversation example uses a system message to define the role and answer format, followed by a user message containing the request. Its native conversation reference also distinguishes system, user and assistant messages. Retain the relevant dialogue in order when a follow-up depends on an earlier answer.
For an extraction task, provide the document and name the fields to return. A useful brief is: “Extract the stated deadline, responsible team and required deliverable into a table, and identify the passage supporting each value.” For a writing task, give the audience, purpose, tone and required sections. Treat a requested word count as a writing instruction and inspect the finished answer for compliance.
The maker lists a 128K context for SenseChat-5. Its native conversation reference explains that the supplied input and the reserved maximum response must fit within the model’s context. Retrieved knowledge or injected reference text also occupies input space. Keep the question, important source passages and enough room for the response together rather than filling the entire allowance with documents.
For a long-source comparison, label each document and preserve section boundaries. Ask which requirements agree, which conflict and which passage supports the difference. Give important definitions and identifiers explicitly. If the task only concerns a few sections, select those sections and the context needed to interpret them so the final comparison remains easy to check.
Supply a complete problem with its assumptions, units and requested final form. Ask for a calculation to identify the values it uses and for an explanation to distinguish a stated fact from an assumption. A conclusion should be checked against the conditions in the problem, especially when several steps depend on one early interpretation.
For code work, include the relevant source, observed behavior and expected result. A useful output is a proposed change with the condition it addresses and the checks needed to assess it. Return the actual error or execution result when the next turn depends on whether a proposal worked. The written answer and the result of running that answer are separate artifacts.
SenseTime’s V5 release documents custom function calling: a connected application can provide tool definitions for the model to select and use. Define each tool’s purpose and arguments around the real operation, then keep its returned observation with the conversation. Ask the final answer to use the actual lookup or operation result rather than infer that a requested action succeeded.
The same V5 release describes a code-interpreter workflow that generates Python for mathematical calculation. This is a connected calculation workflow, not a reason to treat every generated code block as executed. Supply the data to calculate, retain the interpreter’s result and inspect how the written explanation relates to that result.
The producer’s conversation examples show both completed responses and streamed text. A completed answer provides the assistant’s message; streaming delivers successive pieces that must be assembled into the final response. Preserve that final text with the request and source material before using it as a document, report or application response.
Keep the model edition explicit. SenseChat-Turbo is a separate lightweight dialogue model, and SenseChat-5-Cantonese is a separately named adaptation. The producer also publishes distinct vision, fusion-modality and character-dialogue models. Use this SenseChat-5 profile for its documented text-conversation and tool-assisted language work, and review extracted values, reasoning steps and proposed operations against the supplied evidence.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits SenseChat-5 | Default— |
Fieldmessages | Typemessage[] | RequirementRequired | Values & limits Minimum items: 1 | Default— |
Fieldmessages[].role | Typestring | RequirementRequired | Values & limits Examples: system, user, assistant, tool, function Conditions: These roles are explicitly represented by Source compatibility types; the exact model role set remains model-specific. Model-specific | Default— |
Fieldmessages[].content | Typestring|content_part[]|null | RequirementOptional | Values & limits | Default— |
Fieldmessages[].tool_calls | Typetool_call[] | RequirementOptional | Values & limits | Default— |
Fieldmessages[].tool_call_id | Typestring | RequirementOptional | Values & limits Applies when: role=tool; use actual returned ID | Default— |
Fieldmessages[].name | Typestring | RequirementOptional | Values & limits | Default— |
Fieldmessages[].reasoning_content | Typestring | RequirementOptional | Values & limits Applies when: Round-trip actual returned reasoning where this model uses it | Default— |
Fieldmessages[].reasoning_details | Typeobject|array | RequirementOptional | Values & limits Model-specific | Default— |
Fieldmax_tokens | Typeinteger | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
Fieldmax_completion_tokens | Typeinteger | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
Fieldstream_options.include_usage | Typeboolean | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtemperature | Typenumber | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtop_p | Typenumber | RequirementOptional | Values & limits Model-specific | Default— |
Fieldstop | Typestring|string[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtools | Typefunction_tool[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtools[].type | Typestring | RequirementOptional | Values & limits function Model-specific | Default— |
Fieldtools[].function.name | Typestring | RequirementRequired | Values & limits Applies when: function tool supplied | Default— |
Fieldtools[].function.description | Typestring | RequirementOptional | Values & limits | Default— |
Fieldtools[].function.parameters | TypeJSON_schema | RequirementOptional | Values & limits | Default— |
Fieldtool_choice | Typestring|object | RequirementOptional | Values & limits Model-specific | Default— |
Fieldparallel_tool_calls | Typeboolean | RequirementOptional | Values & limits Model-specific | Default— |
Fieldresponse_format | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Fieldreasoning_effort | Typestring | RequirementOptional | Values & limits Model-specific | Default— |
Fieldreasoning | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Fieldservice_tier | Typestring | RequirementOptional | Values & limits Model-specific | Default— |
Fieldinstructions | Typestring | RequirementOptional | Values & limits Compatibility field | Default— |
Fieldfunctions | Typefunction[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldfunction_call | Typestring|object | RequirementOptional | Values & limits Model-specific | Default— |
Fieldprompt_cache_options | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Fieldmodalities | Typestring[] | RequirementOptional | Values & limits text | Default— |
Fieldprovider | Typeobject | RequirementOptional | Values & limits Conditions: provider.options is rejected on this Ultra text route | Default— |
Fieldcache_control.ttl | Typestring | RequirementOptional | Values & limits Conditions: 1h is rejected in actual prompt-cache locations | Default— |
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, temperature, top_p, stop, max_tokens, max_completion_tokens, reasoning, response_format, tools, tool_choice |
Parametercontrol_scope | Contractmodel-specific; user function tools differ from hosted tools |
Parameteroutput_modalities | Contracttext |
Parameterhosted_operations | Contractfalse |
Parametermultimodal_input_binding | Contractnull |
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.
| Configuration | Rate schedule | Charge |
|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Charge Input · Input tokens $0.0132 / 1K tokens Output · Output tokens $0.0308 / 1K tokens Input · Cache read $0 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "SenseChat-5", "messages": [{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}]}')\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='SenseChat-5',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}])\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"))\nfrom openai import OpenAI\nimport os\nfrom pathlib import Path\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)\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\nwith client.chat.completions.stream(model='SenseChat-5',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:\n with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:\n for event in stream:\n payload=event.to_dict(mode="json")\n log.write(json.dumps(payload,ensure_ascii=False)+"\\n"); log.flush()\n print(json.dumps(payload,ensure_ascii=False))\n final=stream.get_final_completion()\n save_result(final.to_dict(mode="json"),"stream-result")\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 SenseChat-5
Use the method paths shown above.
SenseChat-5SenseTime’s SenseChat-5 is a text conversation model for language, knowledge, reasoning, mathematics and code tasks. Its documented 128K context supports longer source material, while the producer’s V5 workflow includes custom function calling and calculation with a code interpreter.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
SenseChat-5 is the V5 general language model in SenseTime’s SenseNova series. The manufacturer describes its task scope across language, knowledge, reasoning, mathematics and code, with particular attention to open-ended questions, multi-turn dialogue, information extraction and writing. Its documented conversation input is text, and the useful result is a written answer, draft, analysis or tool-related instruction.
Keep the task instructions separate from the material to analyze. The maker’s compatible conversation example uses a system message to define the role and answer format, followed by a user message containing the request. Its native conversation reference also distinguishes system, user and assistant messages. Retain the relevant dialogue in order when a follow-up depends on an earlier answer.
For an extraction task, provide the document and name the fields to return. A useful brief is: “Extract the stated deadline, responsible team and required deliverable into a table, and identify the passage supporting each value.” For a writing task, give the audience, purpose, tone and required sections. Treat a requested word count as a writing instruction and inspect the finished answer for compliance.
The maker lists a 128K context for SenseChat-5. Its native conversation reference explains that the supplied input and the reserved maximum response must fit within the model’s context. Retrieved knowledge or injected reference text also occupies input space. Keep the question, important source passages and enough room for the response together rather than filling the entire allowance with documents.
For a long-source comparison, label each document and preserve section boundaries. Ask which requirements agree, which conflict and which passage supports the difference. Give important definitions and identifiers explicitly. If the task only concerns a few sections, select those sections and the context needed to interpret them so the final comparison remains easy to check.
Supply a complete problem with its assumptions, units and requested final form. Ask for a calculation to identify the values it uses and for an explanation to distinguish a stated fact from an assumption. A conclusion should be checked against the conditions in the problem, especially when several steps depend on one early interpretation.
For code work, include the relevant source, observed behavior and expected result. A useful output is a proposed change with the condition it addresses and the checks needed to assess it. Return the actual error or execution result when the next turn depends on whether a proposal worked. The written answer and the result of running that answer are separate artifacts.
SenseTime’s V5 release documents custom function calling: a connected application can provide tool definitions for the model to select and use. Define each tool’s purpose and arguments around the real operation, then keep its returned observation with the conversation. Ask the final answer to use the actual lookup or operation result rather than infer that a requested action succeeded.
The same V5 release describes a code-interpreter workflow that generates Python for mathematical calculation. This is a connected calculation workflow, not a reason to treat every generated code block as executed. Supply the data to calculate, retain the interpreter’s result and inspect how the written explanation relates to that result.
The producer’s conversation examples show both completed responses and streamed text. A completed answer provides the assistant’s message; streaming delivers successive pieces that must be assembled into the final response. Preserve that final text with the request and source material before using it as a document, report or application response.
Keep the model edition explicit. SenseChat-Turbo is a separate lightweight dialogue model, and SenseChat-5-Cantonese is a separately named adaptation. The producer also publishes distinct vision, fusion-modality and character-dialogue models. Use this SenseChat-5 profile for its documented text-conversation and tool-assisted language work, and review extracted values, reasoning steps and proposed operations against the supplied evidence.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits SenseChat-5 | 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.
| Configuration | Rate schedule | Charge |
|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Charge Input · Input tokens $0.0132 / 1K tokens Output · Output tokens $0.0308 / 1K tokens Input · Cache read $0 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "SenseChat-5",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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': 'SenseChat-5', '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': 'SenseChat-5', '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 SenseChat-5
Use the method paths shown above.
Technical example in English
Extract an action from meeting notes\n\nExtract action details from this note: "The logistics team must send the revised packing list by 16:00 on Monday. Finance will review costs later; no date agreed." Return team, deliverable, deadline and supporting quotation for each action. Mark the finance deadline as not stated and keep it separate from the logistics deadline.A two-action table with responsible team, deliverable, deadline and a supporting quote.Ensure the Monday 16:00 deadline is not copied into the finance action.