SenseNova V6 Reasoner is SenseTime’s multimodal profile for complex, deliberate reasoning over written questions and images. The producer’s profile table describes image/text conversation and output containing a reasoning process and a final answer. Its V6 family emphasizes mixed visual-language understanding, mathematical analysis and coding-related reasoning. Reasoner is distinct from the Pro and lightweight Turbo profiles.
Supply the question, the relevant values and the conditions that a solution must satisfy. If the task uses a chart, diagram or document image, make its labels and governing relationships clear. Keep given values separate from assumptions and identify missing information. A useful request can ask which interpretation is supported by the pictured evidence and what condition would change the conclusion.
For a mathematical problem, preserve the original expression or visible figure and the definitions it uses. For a document comparison, identify the pages and the rule that governs a disagreement. The final artifact should make the decisive result and its assumptions inspectable rather than simply producing a lengthy explanation around an underspecified task.
The manufacturer distinguishes the Reasoner’s thinking output from its final response. Keep those parts in their roles when reviewing the outcome. The final answer should clearly state the conclusion, the values or conditions that establish it and any unresolved case. Extended reasoning is useful when it connects the evidence to that result; its length is not independent proof that the conclusion is correct.
Check consequential calculations and source associations against the supplied material. A diagram can be interpreted incorrectly even when the explanation appears coherent. A code-related answer should retain the concrete input case and expected behavior that make its proposed logic assessable. Ask a follow-up about a specific unresolved condition instead of treating confidence as verification.
The V6 release describes a fused model series trained for text and multimodal reasoning, with long-thought and global-memory research. Its announcement also demonstrates ten-minute video analysis in the wider family and separately describes Omni real-time interaction. Those workflows are distinct from the image/text Reasoner profile table and should not be turned into an undocumented per-request media or output cap.
The family’s published long-reasoning training description is separate from a complete native API token-limit table. Preserve the selected Reasoner profile and the actual evidence returned by the producer interface rather than assuming that Pro, Turbo, Omni or later V6.5 releases have identical controls.
A useful result can be a solution, a comparison or an explanation grounded in a document image. Keep the original question and source material with the final answer so the decisive inference can be checked or extended. Distinguish a value read from the source, a calculation based on it and an assumption the task did not establish. This makes the complex-thinking profile useful for a finite, traceable reasoning task.
", "aboutText": "SenseNova V6 Reasoner is SenseTime’s multimodal profile for complex, deliberate reasoning over written questions and images. The producer’s profile table describes image/text conversation and output containing a reasoning process and a final answer. Its V6 family emphasizes mixed visual-language understanding, mathematical analysis and coding-related reasoning. Reasoner is distinct from the Pro and lightweight Turbo profiles.\n\n### Prepare the problem and its visual context\n\nSupply the question, the relevant values and the conditions that a solution must satisfy. If the task uses a chart, diagram or document image, make its labels and governing relationships clear. Keep given values separate from assumptions and identify missing information. A useful request can ask which interpretation is supported by the pictured evidence and what condition would change the conclusion.\n\nFor a mathematical problem, preserve the original expression or visible figure and the definitions it uses. For a document comparison, identify the pages and the rule that governs a disagreement. The final artifact should make the decisive result and its assumptions inspectable rather than simply producing a lengthy explanation around an underspecified task.\n\n### Reasoning material and the final answer\n\nThe manufacturer distinguishes the Reasoner’s thinking output from its final response. Keep those parts in their roles when reviewing the outcome. The final answer should clearly state the conclusion, the values or conditions that establish it and any unresolved case. Extended reasoning is useful when it connects the evidence to that result; its length is not independent proof that the conclusion is correct.\n\nCheck consequential calculations and source associations against the supplied material. A diagram can be interpreted incorrectly even when the explanation appears coherent. A code-related answer should retain the concrete input case and expected behavior that make its proposed logic assessable. Ask a follow-up about a specific unresolved condition instead of treating confidence as verification.\n\n### Multimodal family and edition boundaries\n\nThe V6 release describes a fused model series trained for text and multimodal reasoning, with long-thought and global-memory research. Its announcement also demonstrates ten-minute video analysis in the wider family and separately describes Omni real-time interaction. Those workflows are distinct from the image/text Reasoner profile table and should not be turned into an undocumented per-request media or output cap.\n\nThe family’s published long-reasoning training description is separate from a complete native API token-limit table. Preserve the selected Reasoner profile and the actual evidence returned by the producer interface rather than assuming that Pro, Turbo, Omni or later V6.5 releases have identical controls.\n\n### Produce a reviewable reasoning artifact\n\nA useful result can be a solution, a comparison or an explanation grounded in a document image. Keep the original question and source material with the final answer so the decisive inference can be checked or extended. Distinguish a value read from the source, a calculation based on it and an assumption the task did not establish. This makes the complex-thinking profile useful for a finite, traceable reasoning task.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Separate a reading from a conclusion\n\nAnalyze these source readings: [TABLE] Device A: 20 tasks in 5 minutes; Device B: 30 tasks in 10 minutes. [NOTE] The tasks may differ in complexity. Calculate the observed tasks-per-minute rates, then assess the claim 'A is inherently faster.' Separate computed values, supported comparison and the missing condition needed for that broader claim.A rate table and a concise final assessment separating observations, calculations and an unresolved comparability condition.Check the answer does not turn unequal task sets into proof of an inherent device advantage.SenseNova-V6-ReasonerSenseNova V6 Reasoner applies complex thinking to image-and-text questions. Its producer profile returns reasoning material and a final text answer for mathematical, analytical and document-understanding tasks, with the result checked against the original evidence.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
SenseNova V6 Reasoner is SenseTime’s multimodal profile for complex, deliberate reasoning over written questions and images. The producer’s profile table describes image/text conversation and output containing a reasoning process and a final answer. Its V6 family emphasizes mixed visual-language understanding, mathematical analysis and coding-related reasoning. Reasoner is distinct from the Pro and lightweight Turbo profiles.
Supply the question, the relevant values and the conditions that a solution must satisfy. If the task uses a chart, diagram or document image, make its labels and governing relationships clear. Keep given values separate from assumptions and identify missing information. A useful request can ask which interpretation is supported by the pictured evidence and what condition would change the conclusion.
For a mathematical problem, preserve the original expression or visible figure and the definitions it uses. For a document comparison, identify the pages and the rule that governs a disagreement. The final artifact should make the decisive result and its assumptions inspectable rather than simply producing a lengthy explanation around an underspecified task.
The manufacturer distinguishes the Reasoner’s thinking output from its final response. Keep those parts in their roles when reviewing the outcome. The final answer should clearly state the conclusion, the values or conditions that establish it and any unresolved case. Extended reasoning is useful when it connects the evidence to that result; its length is not independent proof that the conclusion is correct.
Check consequential calculations and source associations against the supplied material. A diagram can be interpreted incorrectly even when the explanation appears coherent. A code-related answer should retain the concrete input case and expected behavior that make its proposed logic assessable. Ask a follow-up about a specific unresolved condition instead of treating confidence as verification.
The V6 release describes a fused model series trained for text and multimodal reasoning, with long-thought and global-memory research. Its announcement also demonstrates ten-minute video analysis in the wider family and separately describes Omni real-time interaction. Those workflows are distinct from the image/text Reasoner profile table and should not be turned into an undocumented per-request media or output cap.
The family’s published long-reasoning training description is separate from a complete native API token-limit table. Preserve the selected Reasoner profile and the actual evidence returned by the producer interface rather than assuming that Pro, Turbo, Omni or later V6.5 releases have identical controls.
A useful result can be a solution, a comparison or an explanation grounded in a document image. Keep the original question and source material with the final answer so the decisive inference can be checked or extended. Distinguish a value read from the source, a calculation based on it and an assumption the task did not establish. This makes the complex-thinking profile useful for a finite, traceable reasoning task.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits SenseNova-V6-Reasoner | Default— |
Fieldmessages | Typemessage[] | RequirementRequired | Values & limits Minimum items: 1 | Default— |
Fieldmessages[].role | Typestring | RequirementRequired | Values & limits Examples: system, user, assistant, tool, function Conditions: The supported role set depends on the selected model. 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 | ContractRead your actual UTF-8 document and insert its text into messages[].content. |
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 $0.00132 / 1K tokens Output · Output tokens $0.00506 / 1K tokens Input · Cache read $0 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "SenseNova-V6-Reasoner",\n "messages": [\n {\n "role": "user",\n "content": "Hello!"\n }\n ]\n}set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source document}"\nexport AILOOT_TEXT_FILE AILOOT_STREAM\npython3 - <<'PY_REQUEST'\nimport json, os\nfrom pathlib import Path\n\nmaterial_path = Path(os.environ['AILOOT_TEXT_FILE'])\nif not material_path.is_file():\n raise SystemExit('Choose your actual UTF-8 document')\ntext = material_path.read_text(encoding='utf-8')\nif not text.strip():\n raise SystemExit('The document must contain text')\nstream = os.environ.get('AILOOT_STREAM', '0') == '1'\npayload = {'model': 'SenseNova-V6-Reasoner', 'messages': [{'role': 'user', 'content': 'Hello!'}]}\npayload['messages'][0]['content'] = 'Summarize this material and quote supporting passages.\\n\\n' + text\npayload['stream'] = stream\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/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-body.bin\npython3 - <<'PY_RESULT'\nimport json, os\nfrom pathlib import Path\n\nraw = Path('result-body.bin').read_bytes()\nif os.environ.get('AILOOT_STREAM', '0') == '1':\n Path('result.sse').write_bytes(raw)\n print(raw.decode('utf-8'))\nelse:\n Path('result.json').write_bytes(raw)\n result = json.loads(raw)\n print(json.dumps(result, ensure_ascii=False, indent=2))\n for choice in result.get('choices', []):\n print('Choice', choice.get('index'), json.dumps(choice, ensure_ascii=False))\nPY_RESULT\nimport json, os\nfrom pathlib import Path\n\nmaterial_path = Path(os.environ['AILOOT_TEXT_FILE'])\nif not material_path.is_file():\n raise SystemExit('Choose your actual UTF-8 document')\ntext = material_path.read_text(encoding='utf-8')\nif not text.strip():\n raise SystemExit('The document must contain text')\nstream = os.environ.get('AILOOT_STREAM', '0') == '1'\npayload = {'model': 'SenseNova-V6-Reasoner', 'messages': [{'role': 'user', 'content': 'Hello!'}]}\npayload['messages'][0]['content'] = 'Summarize this material and quote supporting passages.\\n\\n' + text\npayload['stream'] = stream\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')\nrequest = Request('https://api.ailoot.ai/v1/chat/completions', data=json.dumps(payload, ensure_ascii=False).encode('utf-8'), headers={'Authorization': 'Bearer ' + api_key, 'Content-Type': 'application/json'}, 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-body.bin').write_bytes(error.read())\n Path('response-headers.txt').write_text(str(error.headers), encoding='utf-8')\n raise\nPath('result-body.bin').write_bytes(raw)\nimport json, os\nfrom pathlib import Path\n\nraw = Path('result-body.bin').read_bytes()\nif os.environ.get('AILOOT_STREAM', '0') == '1':\n Path('result.sse').write_bytes(raw)\n print(raw.decode('utf-8'))\nelse:\n Path('result.json').write_bytes(raw)\n result = json.loads(raw)\n print(json.dumps(result, ensure_ascii=False, indent=2))\n for choice in result.get('choices', []):\n print('Choice', choice.get('index'), json.dumps(choice, ensure_ascii=False))\nimport { readFileSync, writeFileSync } from 'node:fs';\n\nconst apiKey = process.env.AILOOT_API_KEY;\nif (!apiKey?.trim()) throw new Error('Set AILOOT_API_KEY');\nif (!process.env.AILOOT_TEXT_FILE) throw new Error('Choose your actual UTF-8 document');\nconst text = readFileSync(process.env.AILOOT_TEXT_FILE, 'utf8');\nif (!text.trim()) throw new Error('The document must contain text');\nconst stream = process.env.AILOOT_STREAM === '1';\nconst payload = {"model": "SenseNova-V6-Reasoner", "messages": [{"role": "user", "content": "Hello!"}]};\npayload.messages[0].content = 'Summarize this material and quote supporting passages.\\n\\n' + text;\npayload.stream = stream;\nconst response = await fetch('https://api.ailoot.ai/v1/chat/completions', { method: 'POST', headers: { 'Authorization': 'Bearer ' + apiKey, 'Content-Type': 'application/json' }, body: JSON.stringify(payload) });\nconst raw = Buffer.from(await response.arrayBuffer());\nwriteFileSync('result-body.bin', raw);\nwriteFileSync('response-headers.txt', [...response.headers].map(([key, value]) => key + ': ' + value).join('\\n'));\nif (!response.ok) throw new Error('HTTP ' + response.status + '; original response saved in result-body.bin');\nif (stream) {\n writeFileSync('result.sse', raw);\n process.stdout.write(raw);\n} else {\n writeFileSync('result.json', raw);\n const result = JSON.parse(raw.toString('utf8'));\n console.log(JSON.stringify(result, null, 2));\n for (const choice of result.choices ?? []) console.log('Choice', choice.index, JSON.stringify(choice));\n}\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 SenseNova-V6-Reasoner, sensetime/sensenova-v6-reasoner
Use the method paths shown above.
SenseNova-V6-ReasonerSenseNova V6 Reasoner applies complex thinking to image-and-text questions. Its producer profile returns reasoning material and a final text answer for mathematical, analytical and document-understanding tasks, with the result checked against the original evidence.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
SenseNova V6 Reasoner is SenseTime’s multimodal profile for complex, deliberate reasoning over written questions and images. The producer’s profile table describes image/text conversation and output containing a reasoning process and a final answer. Its V6 family emphasizes mixed visual-language understanding, mathematical analysis and coding-related reasoning. Reasoner is distinct from the Pro and lightweight Turbo profiles.
Supply the question, the relevant values and the conditions that a solution must satisfy. If the task uses a chart, diagram or document image, make its labels and governing relationships clear. Keep given values separate from assumptions and identify missing information. A useful request can ask which interpretation is supported by the pictured evidence and what condition would change the conclusion.
For a mathematical problem, preserve the original expression or visible figure and the definitions it uses. For a document comparison, identify the pages and the rule that governs a disagreement. The final artifact should make the decisive result and its assumptions inspectable rather than simply producing a lengthy explanation around an underspecified task.
The manufacturer distinguishes the Reasoner’s thinking output from its final response. Keep those parts in their roles when reviewing the outcome. The final answer should clearly state the conclusion, the values or conditions that establish it and any unresolved case. Extended reasoning is useful when it connects the evidence to that result; its length is not independent proof that the conclusion is correct.
Check consequential calculations and source associations against the supplied material. A diagram can be interpreted incorrectly even when the explanation appears coherent. A code-related answer should retain the concrete input case and expected behavior that make its proposed logic assessable. Ask a follow-up about a specific unresolved condition instead of treating confidence as verification.
The V6 release describes a fused model series trained for text and multimodal reasoning, with long-thought and global-memory research. Its announcement also demonstrates ten-minute video analysis in the wider family and separately describes Omni real-time interaction. Those workflows are distinct from the image/text Reasoner profile table and should not be turned into an undocumented per-request media or output cap.
The family’s published long-reasoning training description is separate from a complete native API token-limit table. Preserve the selected Reasoner profile and the actual evidence returned by the producer interface rather than assuming that Pro, Turbo, Omni or later V6.5 releases have identical controls.
A useful result can be a solution, a comparison or an explanation grounded in a document image. Keep the original question and source material with the final answer so the decisive inference can be checked or extended. Distinguish a value read from the source, a calculation based on it and an assumption the task did not establish. This makes the complex-thinking profile useful for a finite, traceable reasoning task.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits SenseNova-V6-Reasoner | 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 $0.00132 / 1K tokens Output · Output tokens $0.00506 / 1K tokens Input · Cache read $0 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "SenseNova-V6-Reasoner",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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': 'SenseNova-V6-Reasoner', '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': 'SenseNova-V6-Reasoner', '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 SenseNova-V6-Reasoner, sensetime/sensenova-v6-reasoner
Use the method paths shown above.
sensetime/sensenova-v6-reasonerSenseNova V6 Reasoner applies complex thinking to image-and-text questions. Its producer profile returns reasoning material and a final text answer for mathematical, analytical and document-understanding tasks, with the result checked against the original evidence.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
SenseNova V6 Reasoner is SenseTime’s multimodal profile for complex, deliberate reasoning over written questions and images. The producer’s profile table describes image/text conversation and output containing a reasoning process and a final answer. Its V6 family emphasizes mixed visual-language understanding, mathematical analysis and coding-related reasoning. Reasoner is distinct from the Pro and lightweight Turbo profiles.
Supply the question, the relevant values and the conditions that a solution must satisfy. If the task uses a chart, diagram or document image, make its labels and governing relationships clear. Keep given values separate from assumptions and identify missing information. A useful request can ask which interpretation is supported by the pictured evidence and what condition would change the conclusion.
For a mathematical problem, preserve the original expression or visible figure and the definitions it uses. For a document comparison, identify the pages and the rule that governs a disagreement. The final artifact should make the decisive result and its assumptions inspectable rather than simply producing a lengthy explanation around an underspecified task.
The manufacturer distinguishes the Reasoner’s thinking output from its final response. Keep those parts in their roles when reviewing the outcome. The final answer should clearly state the conclusion, the values or conditions that establish it and any unresolved case. Extended reasoning is useful when it connects the evidence to that result; its length is not independent proof that the conclusion is correct.
Check consequential calculations and source associations against the supplied material. A diagram can be interpreted incorrectly even when the explanation appears coherent. A code-related answer should retain the concrete input case and expected behavior that make its proposed logic assessable. Ask a follow-up about a specific unresolved condition instead of treating confidence as verification.
The V6 release describes a fused model series trained for text and multimodal reasoning, with long-thought and global-memory research. Its announcement also demonstrates ten-minute video analysis in the wider family and separately describes Omni real-time interaction. Those workflows are distinct from the image/text Reasoner profile table and should not be turned into an undocumented per-request media or output cap.
The family’s published long-reasoning training description is separate from a complete native API token-limit table. Preserve the selected Reasoner profile and the actual evidence returned by the producer interface rather than assuming that Pro, Turbo, Omni or later V6.5 releases have identical controls.
A useful result can be a solution, a comparison or an explanation grounded in a document image. Keep the original question and source material with the final answer so the decisive inference can be checked or extended. Distinguish a value read from the source, a calculation based on it and an assumption the task did not establish. This makes the complex-thinking profile useful for a finite, traceable reasoning task.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits sensetime/sensenova-v6-reasoner | 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 $0.00132 / 1K tokens Output · Output tokens $0.00506 / 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": "sensetime/sensenova-v6-reasoner", "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='sensetime/sensenova-v6-reasoner',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='sensetime/sensenova-v6-reasoner',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 SenseNova-V6-Reasoner, sensetime/sensenova-v6-reasoner
Use the method paths shown above.
sensetime/sensenova-v6-reasonerSenseNova V6 Reasoner applies complex thinking to image-and-text questions. Its producer profile returns reasoning material and a final text answer for mathematical, analytical and document-understanding tasks, with the result checked against the original evidence.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
SenseNova V6 Reasoner is SenseTime’s multimodal profile for complex, deliberate reasoning over written questions and images. The producer’s profile table describes image/text conversation and output containing a reasoning process and a final answer. Its V6 family emphasizes mixed visual-language understanding, mathematical analysis and coding-related reasoning. Reasoner is distinct from the Pro and lightweight Turbo profiles.
Supply the question, the relevant values and the conditions that a solution must satisfy. If the task uses a chart, diagram or document image, make its labels and governing relationships clear. Keep given values separate from assumptions and identify missing information. A useful request can ask which interpretation is supported by the pictured evidence and what condition would change the conclusion.
For a mathematical problem, preserve the original expression or visible figure and the definitions it uses. For a document comparison, identify the pages and the rule that governs a disagreement. The final artifact should make the decisive result and its assumptions inspectable rather than simply producing a lengthy explanation around an underspecified task.
The manufacturer distinguishes the Reasoner’s thinking output from its final response. Keep those parts in their roles when reviewing the outcome. The final answer should clearly state the conclusion, the values or conditions that establish it and any unresolved case. Extended reasoning is useful when it connects the evidence to that result; its length is not independent proof that the conclusion is correct.
Check consequential calculations and source associations against the supplied material. A diagram can be interpreted incorrectly even when the explanation appears coherent. A code-related answer should retain the concrete input case and expected behavior that make its proposed logic assessable. Ask a follow-up about a specific unresolved condition instead of treating confidence as verification.
The V6 release describes a fused model series trained for text and multimodal reasoning, with long-thought and global-memory research. Its announcement also demonstrates ten-minute video analysis in the wider family and separately describes Omni real-time interaction. Those workflows are distinct from the image/text Reasoner profile table and should not be turned into an undocumented per-request media or output cap.
The family’s published long-reasoning training description is separate from a complete native API token-limit table. Preserve the selected Reasoner profile and the actual evidence returned by the producer interface rather than assuming that Pro, Turbo, Omni or later V6.5 releases have identical controls.
A useful result can be a solution, a comparison or an explanation grounded in a document image. Keep the original question and source material with the final answer so the decisive inference can be checked or extended. Distinguish a value read from the source, a calculation based on it and an assumption the task did not establish. This makes the complex-thinking profile useful for a finite, traceable reasoning task.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits sensetime/sensenova-v6-reasoner | 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 $0.00132 / 1K tokens Output · Output tokens $0.00506 / 1K tokens Input · Cache read $0 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "sensetime/sensenova-v6-reasoner",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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': 'sensetime/sensenova-v6-reasoner', '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': 'sensetime/sensenova-v6-reasoner', '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 SenseNova-V6-Reasoner, sensetime/sensenova-v6-reasoner
Use the method paths shown above.
Technical example in English
Separate a reading from a conclusion\n\nAnalyze these source readings: [TABLE] Device A: 20 tasks in 5 minutes; Device B: 30 tasks in 10 minutes. [NOTE] The tasks may differ in complexity. Calculate the observed tasks-per-minute rates, then assess the claim 'A is inherently faster.' Separate computed values, supported comparison and the missing condition needed for that broader claim.A rate table and a concise final assessment separating observations, calculations and an unresolved comparability condition.Check the answer does not turn unequal task sets into proof of an inherent device advantage.