QVQ-Max — 2025-05-15 is a dated entry in the QVQ-Max visual-reasoning line. The manufacturer describes this family as combining visual input with reasoning and a text answer. Its task directions include mathematics, programming, visual analysis, creating material and general problem-solving. The purpose is to explain or solve a question about provided visual evidence, rather than to generate a new image or video.
The documented QVQ workflows combine a written question with images or video and return text. For a mathematical illustration, provide the entire condition, readable labels and the quantity to find. For a chart, identify the axes, unit of measurement and comparison you need. Ask the model to separate visible data from assumptions before giving a conclusion. The result can be a worked solution, a comparison of observations or an explanation of how particular details support an answer.
The manufacturer describes QVQ as combining visual input with reasoning and a text answer. Its service flow is streaming. In an application, keep intermediate reasoning distinguishable from the completed answer and assemble the returned fragments before using the result as a document or instruction. A reasoning model’s unfinished stream is not the same artifact as its final conclusion.
Prepare one connected task. For a process diagram, identify the starting condition, the decision points and the outcome to explain. For several related images, label each source and state their order or relationship. A useful request might compare two illustrated configurations, list the visible changes and explain which change affects the stated requirement. Preserve the original labels so each observation can be checked against the right image, and ask for clarification when a symbol or caption cannot be read.
For a video question, define the event and the part of the clip to examine. Ask for the sequence of observed actions or the visual evidence that supports a particular interpretation. The family’s documented video input is for understanding, not for producing an edited clip. If the task depends on a frame with small text, provide a readable still alongside the question. The expected output should name the relevant objects or stages and explain the conclusion in text rather than assume that a description establishes what a person intended.
The chat reference states that system messages have no effect for QVQ models. Put the task, role instructions and requested format into the user message. It also recommends leaving the QVQ sampling defaults unchanged. Define a final answer that can be inspected, such as observations followed by a conclusion, or a table linking each claim to a visible feature. A requested table or JSON-like arrangement should be validated by the application; it is not the same as an advertised constrained-output capability.
Keep the dated identifier with the source material and any processing settings needed to repeat a task. Other QVQ-Max snapshots and the changing family alias remain separate names. For a sizeable source, choose the relevant pages or frames, preserve their relationships and leave space for the answer. Media representation, task instructions and conversation history all affect the request. Preparation should follow the specification of the selected edition and interface rather than borrowing numerical settings from an unrelated visual model.
A practical analytical result contains the visible facts used, the explanation and the final answer, with missing or uncertain details identified. Check a calculation against the stated numbers and units; check a visual comparison against both original images; check a video interpretation against the relevant frames. QVQ-Max’s reasoning text does not itself execute an external tool, apply a program change or establish that information outside the supplied sources was searched. Use the model for the documented visual analysis and retain separate evidence for any subsequent action.
", "aboutText": "QVQ-Max — 2025-05-15 is a dated entry in the QVQ-Max visual-reasoning line. The manufacturer describes this family as combining visual input with reasoning and a text answer. Its task directions include mathematics, programming, visual analysis, creating material and general problem-solving. The purpose is to explain or solve a question about provided visual evidence, rather than to generate a new image or video.\n\nThe documented QVQ workflows combine a written question with images or video and return text. For a mathematical illustration, provide the entire condition, readable labels and the quantity to find. For a chart, identify the axes, unit of measurement and comparison you need. Ask the model to separate visible data from assumptions before giving a conclusion. The result can be a worked solution, a comparison of observations or an explanation of how particular details support an answer.\n\nThe manufacturer describes QVQ as combining visual input with reasoning and a text answer. Its service flow is streaming. In an application, keep intermediate reasoning distinguishable from the completed answer and assemble the returned fragments before using the result as a document or instruction. A reasoning model’s unfinished stream is not the same artifact as its final conclusion.\n\nPrepare one connected task. For a process diagram, identify the starting condition, the decision points and the outcome to explain. For several related images, label each source and state their order or relationship. A useful request might compare two illustrated configurations, list the visible changes and explain which change affects the stated requirement. Preserve the original labels so each observation can be checked against the right image, and ask for clarification when a symbol or caption cannot be read.\n\nFor a video question, define the event and the part of the clip to examine. Ask for the sequence of observed actions or the visual evidence that supports a particular interpretation. The family’s documented video input is for understanding, not for producing an edited clip. If the task depends on a frame with small text, provide a readable still alongside the question. The expected output should name the relevant objects or stages and explain the conclusion in text rather than assume that a description establishes what a person intended.\n\nThe chat reference states that system messages have no effect for QVQ models. Put the task, role instructions and requested format into the user message. It also recommends leaving the QVQ sampling defaults unchanged. Define a final answer that can be inspected, such as observations followed by a conclusion, or a table linking each claim to a visible feature. A requested table or JSON-like arrangement should be validated by the application; it is not the same as an advertised constrained-output capability.\n\nKeep the dated identifier with the source material and any processing settings needed to repeat a task. Other QVQ-Max snapshots and the changing family alias remain separate names. For a sizeable source, choose the relevant pages or frames, preserve their relationships and leave space for the answer. Media representation, task instructions and conversation history all affect the request. Preparation should follow the specification of the selected edition and interface rather than borrowing numerical settings from an unrelated visual model.\n\nA practical analytical result contains the visible facts used, the explanation and the final answer, with missing or uncertain details identified. Check a calculation against the stated numbers and units; check a visual comparison against both original images; check a video interpretation against the relevant frames. QVQ-Max’s reasoning text does not itself execute an external tool, apply a program change or establish that information outside the supplied sources was searched. Use the model for the documented visual analysis and retain separate evidence for any subsequent action.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Reason from transcribed chart values\n\nUse this text transcription of a chart, not an image: "Axis: liters per hour. Pump A: 18 at setting 1, 24 at setting 2. Pump B: 20 at setting 1, 21 at setting 2." Compare the increases and identify which pump gains more. Show the arithmetic, preserve units and avoid inferring power use.A small comparison table, two increase calculations and a conclusion restricted to flow rate.Check that increases are computed within each pump and no energy-efficiency claim is added.qvq-max-2025-05-15QVQ-Max — 2025-05-15 retains a separate dated identity in Qwen’s visual-reasoning line. Use its documented family approach for questions that connect images, diagrams or video observations with a written explanation, calculation or conclusion.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
QVQ-Max — 2025-05-15 is a dated entry in the QVQ-Max visual-reasoning line. The manufacturer describes this family as combining visual input with reasoning and a text answer. Its task directions include mathematics, programming, visual analysis, creating material and general problem-solving. The purpose is to explain or solve a question about provided visual evidence, rather than to generate a new image or video.
The documented QVQ workflows combine a written question with images or video and return text. For a mathematical illustration, provide the entire condition, readable labels and the quantity to find. For a chart, identify the axes, unit of measurement and comparison you need. Ask the model to separate visible data from assumptions before giving a conclusion. The result can be a worked solution, a comparison of observations or an explanation of how particular details support an answer.
The manufacturer describes QVQ as combining visual input with reasoning and a text answer. Its service flow is streaming. In an application, keep intermediate reasoning distinguishable from the completed answer and assemble the returned fragments before using the result as a document or instruction. A reasoning model’s unfinished stream is not the same artifact as its final conclusion.
Prepare one connected task. For a process diagram, identify the starting condition, the decision points and the outcome to explain. For several related images, label each source and state their order or relationship. A useful request might compare two illustrated configurations, list the visible changes and explain which change affects the stated requirement. Preserve the original labels so each observation can be checked against the right image, and ask for clarification when a symbol or caption cannot be read.
For a video question, define the event and the part of the clip to examine. Ask for the sequence of observed actions or the visual evidence that supports a particular interpretation. The family’s documented video input is for understanding, not for producing an edited clip. If the task depends on a frame with small text, provide a readable still alongside the question. The expected output should name the relevant objects or stages and explain the conclusion in text rather than assume that a description establishes what a person intended.
The chat reference states that system messages have no effect for QVQ models. Put the task, role instructions and requested format into the user message. It also recommends leaving the QVQ sampling defaults unchanged. Define a final answer that can be inspected, such as observations followed by a conclusion, or a table linking each claim to a visible feature. A requested table or JSON-like arrangement should be validated by the application; it is not the same as an advertised constrained-output capability.
Keep the dated identifier with the source material and any processing settings needed to repeat a task. Other QVQ-Max snapshots and the changing family alias remain separate names. For a sizeable source, choose the relevant pages or frames, preserve their relationships and leave space for the answer. Media representation, task instructions and conversation history all affect the request. Preparation should follow the specification of the selected edition and interface rather than borrowing numerical settings from an unrelated visual model.
A practical analytical result contains the visible facts used, the explanation and the final answer, with missing or uncertain details identified. Check a calculation against the stated numbers and units; check a visual comparison against both original images; check a video interpretation against the relevant frames. QVQ-Max’s reasoning text does not itself execute an external tool, apply a program change or establish that information outside the supplied sources was searched. Use the model for the documented visual analysis and retain separate evidence for any subsequent action.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qvq-max-2025-05-15 | 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 $0.0023 / 1K tokens Output · Output tokens $0.00916 / 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": "qvq-max-2025-05-15", "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='qvq-max-2025-05-15',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='qvq-max-2025-05-15',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 qvq-max-2025-05-15
Use the method paths shown above.
qvq-max-2025-05-15QVQ-Max — 2025-05-15 retains a separate dated identity in Qwen’s visual-reasoning line. Use its documented family approach for questions that connect images, diagrams or video observations with a written explanation, calculation or conclusion.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
QVQ-Max — 2025-05-15 is a dated entry in the QVQ-Max visual-reasoning line. The manufacturer describes this family as combining visual input with reasoning and a text answer. Its task directions include mathematics, programming, visual analysis, creating material and general problem-solving. The purpose is to explain or solve a question about provided visual evidence, rather than to generate a new image or video.
The documented QVQ workflows combine a written question with images or video and return text. For a mathematical illustration, provide the entire condition, readable labels and the quantity to find. For a chart, identify the axes, unit of measurement and comparison you need. Ask the model to separate visible data from assumptions before giving a conclusion. The result can be a worked solution, a comparison of observations or an explanation of how particular details support an answer.
The manufacturer describes QVQ as combining visual input with reasoning and a text answer. Its service flow is streaming. In an application, keep intermediate reasoning distinguishable from the completed answer and assemble the returned fragments before using the result as a document or instruction. A reasoning model’s unfinished stream is not the same artifact as its final conclusion.
Prepare one connected task. For a process diagram, identify the starting condition, the decision points and the outcome to explain. For several related images, label each source and state their order or relationship. A useful request might compare two illustrated configurations, list the visible changes and explain which change affects the stated requirement. Preserve the original labels so each observation can be checked against the right image, and ask for clarification when a symbol or caption cannot be read.
For a video question, define the event and the part of the clip to examine. Ask for the sequence of observed actions or the visual evidence that supports a particular interpretation. The family’s documented video input is for understanding, not for producing an edited clip. If the task depends on a frame with small text, provide a readable still alongside the question. The expected output should name the relevant objects or stages and explain the conclusion in text rather than assume that a description establishes what a person intended.
The chat reference states that system messages have no effect for QVQ models. Put the task, role instructions and requested format into the user message. It also recommends leaving the QVQ sampling defaults unchanged. Define a final answer that can be inspected, such as observations followed by a conclusion, or a table linking each claim to a visible feature. A requested table or JSON-like arrangement should be validated by the application; it is not the same as an advertised constrained-output capability.
Keep the dated identifier with the source material and any processing settings needed to repeat a task. Other QVQ-Max snapshots and the changing family alias remain separate names. For a sizeable source, choose the relevant pages or frames, preserve their relationships and leave space for the answer. Media representation, task instructions and conversation history all affect the request. Preparation should follow the specification of the selected edition and interface rather than borrowing numerical settings from an unrelated visual model.
A practical analytical result contains the visible facts used, the explanation and the final answer, with missing or uncertain details identified. Check a calculation against the stated numbers and units; check a visual comparison against both original images; check a video interpretation against the relevant frames. QVQ-Max’s reasoning text does not itself execute an external tool, apply a program change or establish that information outside the supplied sources was searched. Use the model for the documented visual analysis and retain separate evidence for any subsequent action.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qvq-max-2025-05-15 | 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 $0.0023 / 1K tokens Output · Output tokens $0.00916 / 1K tokens Input · Cache read $0 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "qvq-max-2025-05-15",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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': 'qvq-max-2025-05-15', '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': 'qvq-max-2025-05-15', '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 qvq-max-2025-05-15
Use the method paths shown above.
Technical example in English
Reason from transcribed chart values\n\nUse this text transcription of a chart, not an image: "Axis: liters per hour. Pump A: 18 at setting 1, 24 at setting 2. Pump B: 20 at setting 1, 21 at setting 2." Compare the increases and identify which pump gains more. Show the arithmetic, preserve units and avoid inferring power use.A small comparison table, two increase calculations and a conclusion restricted to flow rate.Check that increases are computed within each pump and no energy-efficiency claim is added.