QVQ-Max — 2025-03-25 belongs to Qwen’s QVQ visual-reasoning line. The QVQ-Max family combines observation of images and video with analysis of that information. Its documented applications span mathematical problems, programming, visual analysis, creative work and everyday questions. The useful result is a text explanation or solution connected to the supplied visual evidence.
Detailed observation comes first. For a chart, provide readable axes, legends and data labels, then state whether to compare values, explain a trend or examine a particular claim. Ask for the observations supporting the conclusion. For several images, preserve their order and identify which image should support each answer. A good comparison names the visible differences and explains why they matter for the question, rather than treating a plausible interpretation as an observed fact.
Visual reasoning uses those observations to solve a problem. For a diagram-based calculation, provide the complete illustration and written question, retaining labels, units and stated conditions. Ask the model to identify the given information, explain the calculation and express the result in the requested form. For a technical diagram, name the process or relation to examine and request an explanation tied to specific visible elements. If a value or label is unclear, ask it to identify the ambiguity before attempting a calculation.
The family also supports creative and practical work based on visual material. A rough sketch can be the starting point for an illustration brief; a scene can inform a short video script; a photo can support a description or comparison. Give the intended audience, purpose and constraints, and ask for a written deliverable such as a revised concept, scene outline or explanation. These tasks produce text guidance from the visual source. Preserve the original image or clip so the proposed changes can be compared with the evidence that prompted them.
For video understanding, identify the interval or event and the question to answer. The documented QVQ interface accepts video material for analysis. If fine detail is important, attach a readable still from the relevant scene and explain its relationship to the clip. Ask for the sequence of visible actions and the observations supporting the conclusion, while distinguishing those observations from an interpretation of intent or a prediction about what happens next. Select the material around the particular evidence needed for the question, retaining its source order.
QVQ’s documented reasoning workflow combines a thinking process with the answer, and the producer’s QVQ service flow uses streaming output. Keep reasoning fragments separate from answer fragments and assemble the completed response before using it as a report, worked solution or user instruction. An interrupted response needs to be recognized as incomplete. Request a concise final section that states the result, the evidence used and any assumptions, so the conclusion remains easy to inspect after the reasoning has finished.
The manufacturer’s chat reference states that system messages have no effect for QVQ. Put the actual task, relevant conditions and requested answer format in the user message. It recommends retaining the QVQ sampling defaults rather than applying settings copied from another model family. A requested table can organize a text answer; if an application will process JSON-like output, validate its structure and values before using it. Keep the prompt focused on the visual question and the deliverable needed from the analysis.
For a practical result, retain the source image or clip with the completed answer. Check arithmetic against the original numbers and units, and compare visual explanations with the labels and objects actually present. Keep the exact dated model name in the task record when revisiting the same case. Ask the model to distinguish visible evidence, assumptions and conclusions: a confident interpretation of a blurry symbol or an unseen event can otherwise become the basis for a wrong calculation or decision.
", "aboutText": "QVQ-Max — 2025-03-25 belongs to Qwen’s QVQ visual-reasoning line. The QVQ-Max family combines observation of images and video with analysis of that information. Its documented applications span mathematical problems, programming, visual analysis, creative work and everyday questions. The useful result is a text explanation or solution connected to the supplied visual evidence.\n\nDetailed observation comes first. For a chart, provide readable axes, legends and data labels, then state whether to compare values, explain a trend or examine a particular claim. Ask for the observations supporting the conclusion. For several images, preserve their order and identify which image should support each answer. A good comparison names the visible differences and explains why they matter for the question, rather than treating a plausible interpretation as an observed fact.\n\nVisual reasoning uses those observations to solve a problem. For a diagram-based calculation, provide the complete illustration and written question, retaining labels, units and stated conditions. Ask the model to identify the given information, explain the calculation and express the result in the requested form. For a technical diagram, name the process or relation to examine and request an explanation tied to specific visible elements. If a value or label is unclear, ask it to identify the ambiguity before attempting a calculation.\n\nThe family also supports creative and practical work based on visual material. A rough sketch can be the starting point for an illustration brief; a scene can inform a short video script; a photo can support a description or comparison. Give the intended audience, purpose and constraints, and ask for a written deliverable such as a revised concept, scene outline or explanation. These tasks produce text guidance from the visual source. Preserve the original image or clip so the proposed changes can be compared with the evidence that prompted them.\n\nFor video understanding, identify the interval or event and the question to answer. The documented QVQ interface accepts video material for analysis. If fine detail is important, attach a readable still from the relevant scene and explain its relationship to the clip. Ask for the sequence of visible actions and the observations supporting the conclusion, while distinguishing those observations from an interpretation of intent or a prediction about what happens next. Select the material around the particular evidence needed for the question, retaining its source order.\n\nQVQ’s documented reasoning workflow combines a thinking process with the answer, and the producer’s QVQ service flow uses streaming output. Keep reasoning fragments separate from answer fragments and assemble the completed response before using it as a report, worked solution or user instruction. An interrupted response needs to be recognized as incomplete. Request a concise final section that states the result, the evidence used and any assumptions, so the conclusion remains easy to inspect after the reasoning has finished.\n\nThe manufacturer’s chat reference states that system messages have no effect for QVQ. Put the actual task, relevant conditions and requested answer format in the user message. It recommends retaining the QVQ sampling defaults rather than applying settings copied from another model family. A requested table can organize a text answer; if an application will process JSON-like output, validate its structure and values before using it. Keep the prompt focused on the visual question and the deliverable needed from the analysis.\n\nFor a practical result, retain the source image or clip with the completed answer. Check arithmetic against the original numbers and units, and compare visual explanations with the labels and objects actually present. Keep the exact dated model name in the task record when revisiting the same case. Ask the model to distinguish visible evidence, assumptions and conclusions: a confident interpretation of a blurry symbol or an unseen event can otherwise become the basis for a wrong calculation or decision.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Solve a described geometry problem\n\nA diagram is described in text: triangle ABC has base AB = 8 cm and perpendicular height from C to line AB = 3 cm. The foot of the height lies outside segment AB. Calculate the area, explain whether the outside foot changes the formula and state which given measurements are sufficient.A worked area calculation with units and a brief explanation of perpendicular height when its foot is outside the base segment.Check that the answer uses the perpendicular height, not an inferred side length, and reports square centimeters.qvq-max-2025-03-25QVQ-Max — 2025-03-25 belongs to Qwen’s visual-reasoning line. The QVQ-Max family analyzes images and video alongside text questions, combining visual observations with reasoning to produce explanations, worked solutions and creative guidance in text.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
QVQ-Max — 2025-03-25 belongs to Qwen’s QVQ visual-reasoning line. The QVQ-Max family combines observation of images and video with analysis of that information. Its documented applications span mathematical problems, programming, visual analysis, creative work and everyday questions. The useful result is a text explanation or solution connected to the supplied visual evidence.
Detailed observation comes first. For a chart, provide readable axes, legends and data labels, then state whether to compare values, explain a trend or examine a particular claim. Ask for the observations supporting the conclusion. For several images, preserve their order and identify which image should support each answer. A good comparison names the visible differences and explains why they matter for the question, rather than treating a plausible interpretation as an observed fact.
Visual reasoning uses those observations to solve a problem. For a diagram-based calculation, provide the complete illustration and written question, retaining labels, units and stated conditions. Ask the model to identify the given information, explain the calculation and express the result in the requested form. For a technical diagram, name the process or relation to examine and request an explanation tied to specific visible elements. If a value or label is unclear, ask it to identify the ambiguity before attempting a calculation.
The family also supports creative and practical work based on visual material. A rough sketch can be the starting point for an illustration brief; a scene can inform a short video script; a photo can support a description or comparison. Give the intended audience, purpose and constraints, and ask for a written deliverable such as a revised concept, scene outline or explanation. These tasks produce text guidance from the visual source. Preserve the original image or clip so the proposed changes can be compared with the evidence that prompted them.
For video understanding, identify the interval or event and the question to answer. The documented QVQ interface accepts video material for analysis. If fine detail is important, attach a readable still from the relevant scene and explain its relationship to the clip. Ask for the sequence of visible actions and the observations supporting the conclusion, while distinguishing those observations from an interpretation of intent or a prediction about what happens next. Select the material around the particular evidence needed for the question, retaining its source order.
QVQ’s documented reasoning workflow combines a thinking process with the answer, and the producer’s QVQ service flow uses streaming output. Keep reasoning fragments separate from answer fragments and assemble the completed response before using it as a report, worked solution or user instruction. An interrupted response needs to be recognized as incomplete. Request a concise final section that states the result, the evidence used and any assumptions, so the conclusion remains easy to inspect after the reasoning has finished.
The manufacturer’s chat reference states that system messages have no effect for QVQ. Put the actual task, relevant conditions and requested answer format in the user message. It recommends retaining the QVQ sampling defaults rather than applying settings copied from another model family. A requested table can organize a text answer; if an application will process JSON-like output, validate its structure and values before using it. Keep the prompt focused on the visual question and the deliverable needed from the analysis.
For a practical result, retain the source image or clip with the completed answer. Check arithmetic against the original numbers and units, and compare visual explanations with the labels and objects actually present. Keep the exact dated model name in the task record when revisiting the same case. Ask the model to distinguish visible evidence, assumptions and conclusions: a confident interpretation of a blurry symbol or an unseen event can otherwise become the basis for a wrong calculation or decision.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qvq-max-2025-03-25 | 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-2025-03-25", "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-2025-03-25',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-2025-03-25',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-2025-03-25
Use the method paths shown above.
qvq-max-2025-03-25QVQ-Max — 2025-03-25 belongs to Qwen’s visual-reasoning line. The QVQ-Max family analyzes images and video alongside text questions, combining visual observations with reasoning to produce explanations, worked solutions and creative guidance in text.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
QVQ-Max — 2025-03-25 belongs to Qwen’s QVQ visual-reasoning line. The QVQ-Max family combines observation of images and video with analysis of that information. Its documented applications span mathematical problems, programming, visual analysis, creative work and everyday questions. The useful result is a text explanation or solution connected to the supplied visual evidence.
Detailed observation comes first. For a chart, provide readable axes, legends and data labels, then state whether to compare values, explain a trend or examine a particular claim. Ask for the observations supporting the conclusion. For several images, preserve their order and identify which image should support each answer. A good comparison names the visible differences and explains why they matter for the question, rather than treating a plausible interpretation as an observed fact.
Visual reasoning uses those observations to solve a problem. For a diagram-based calculation, provide the complete illustration and written question, retaining labels, units and stated conditions. Ask the model to identify the given information, explain the calculation and express the result in the requested form. For a technical diagram, name the process or relation to examine and request an explanation tied to specific visible elements. If a value or label is unclear, ask it to identify the ambiguity before attempting a calculation.
The family also supports creative and practical work based on visual material. A rough sketch can be the starting point for an illustration brief; a scene can inform a short video script; a photo can support a description or comparison. Give the intended audience, purpose and constraints, and ask for a written deliverable such as a revised concept, scene outline or explanation. These tasks produce text guidance from the visual source. Preserve the original image or clip so the proposed changes can be compared with the evidence that prompted them.
For video understanding, identify the interval or event and the question to answer. The documented QVQ interface accepts video material for analysis. If fine detail is important, attach a readable still from the relevant scene and explain its relationship to the clip. Ask for the sequence of visible actions and the observations supporting the conclusion, while distinguishing those observations from an interpretation of intent or a prediction about what happens next. Select the material around the particular evidence needed for the question, retaining its source order.
QVQ’s documented reasoning workflow combines a thinking process with the answer, and the producer’s QVQ service flow uses streaming output. Keep reasoning fragments separate from answer fragments and assemble the completed response before using it as a report, worked solution or user instruction. An interrupted response needs to be recognized as incomplete. Request a concise final section that states the result, the evidence used and any assumptions, so the conclusion remains easy to inspect after the reasoning has finished.
The manufacturer’s chat reference states that system messages have no effect for QVQ. Put the actual task, relevant conditions and requested answer format in the user message. It recommends retaining the QVQ sampling defaults rather than applying settings copied from another model family. A requested table can organize a text answer; if an application will process JSON-like output, validate its structure and values before using it. Keep the prompt focused on the visual question and the deliverable needed from the analysis.
For a practical result, retain the source image or clip with the completed answer. Check arithmetic against the original numbers and units, and compare visual explanations with the labels and objects actually present. Keep the exact dated model name in the task record when revisiting the same case. Ask the model to distinguish visible evidence, assumptions and conclusions: a confident interpretation of a blurry symbol or an unseen event can otherwise become the basis for a wrong calculation or decision.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qvq-max-2025-03-25 | 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 $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "qvq-max-2025-03-25",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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-2025-03-25', '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-2025-03-25', '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-2025-03-25
Use the method paths shown above.
Technical example in English
Solve a described geometry problem\n\nA diagram is described in text: triangle ABC has base AB = 8 cm and perpendicular height from C to line AB = 3 cm. The foot of the height lies outside segment AB. Calculate the area, explain whether the outside foot changes the formula and state which given measurements are sufficient.A worked area calculation with units and a brief explanation of perpendicular height when its foot is outside the base segment.Check that the answer uses the perpendicular height, not an inferred side length, and reports square centimeters.