Overview: reasoning grounded in visual input
QVQ-Max is Qwen’s visual reasoning model. The maker describes chain-of-thought output and stronger capabilities in mathematics, programming, visual analysis, creative work and general tasks. Its dedicated capability page lists text, image and video input with text output. Choose it for a question where the visual material is part of the reasoning problem, such as a diagram, a chart or a sequence of observed events.
The exact model edition
The producer currently describes qvq-max as functionally equivalent to the qvq-max-2025-03-25 snapshot. That statement identifies a manufacturer-described edition relationship; it does not change the exact IDs preserved by an application. QVQ-Max should not inherit the weight identity, parameter count or generation controls of QVQ-72B-Preview, QVQ-Plus or a newer Qwen visual model merely because they share a reasoning theme. A latest-suffixed supplier name also does not by itself establish a fixed checkpoint.
Preparing a visual reasoning question
Provide the relevant image together with the complete question. For a mathematical diagram, preserve labels, dimensions and the accompanying statement, then ask which relationships follow from the visible figure and which require an additional assumption. Request a clearly delimited final answer with the values and relationships used to obtain it. A useful explanation should connect each important inference to something in the supplied material.
For a chart, ask the model to identify the axes, units and series before interpreting a trend. For a diagram of an algorithm or interface, state the intended behavior and ask how the visible structure relates to that behavior. For a creative brief, distinguish a description of what is actually present from proposed changes or interpretations. These are authored applications of the maker’s documented mathematics, programming, analysis and creation capabilities, not demonstrations of a particular asset’s successful processing.
Video and multiple pieces of evidence
Video is explicitly listed as an input modality. For an event-analysis request, supply the relevant segment and ask for an ordered explanation of what changes, which scene supports the conclusion and what remains uncertain. If timing information is available in the input, state how the result should refer to it. The exact model page does not establish a universal video duration, frame count or timestamp precision, so those properties should not be borrowed from another Qwen family.
When the question uses several images or passages, label them and explain the relationship the model should examine. Ask for a result organized by those labels so a reviewer can see which evidence supports each point. A reasoning response should remain distinguishable from the final answer; an extended explanation is useful only when its claims can be checked against the source.
Context and answer limits
The specification lists a 131,072-token context window, a maximum input length of 106,496 tokens and a maximum output length of 8,192 tokens. Keep these separate values rather than deriving an undocumented reasoning-token allowance from their difference. Text, represented visual material and generated content must fit the applicable sequence and output bounds.
For a dense page or diagram, make the relevant details readable before submission and retain the complete statement needed for the inference. For a long source, select the material tied to the question and reserve enough answer space for a conclusion with supporting evidence. The token specification does not provide an unlimited visual-input allowance or a guarantee that every detail is recalled.
Tools, formatting and substantive limits
The exact capability matrix marks function calling, built-in web search and enforced structured outputs unsupported. QVQ-Max’s visual reasoning therefore should not be presented as automatic browser control, an external-code execution tool or a source of live information. A prompt may request a table or a JSON-shaped textual result, but that request does not create a schema-enforcement contract.
The dedicated model page does not publish a model-specific hybrid thinking switch or a parameter count. Preserve the documented visual-reasoning identity instead of importing controls or size claims from a different checkpoint. Check small labels, extracted numbers, inferred relationships and code suggestions against the source. The practical output is an explained visual conclusion or draft artifact, grounded in the material the user supplies.
", "aboutText": "Overview: reasoning grounded in visual input\n\nQVQ-Max is Qwen’s visual reasoning model. The maker describes chain-of-thought output and stronger capabilities in mathematics, programming, visual analysis, creative work and general tasks. Its dedicated capability page lists text, image and video input with text output. Choose it for a question where the visual material is part of the reasoning problem, such as a diagram, a chart or a sequence of observed events.\n\nThe exact model edition\n\nThe producer currently describes qvq-max as functionally equivalent to the qvq-max-2025-03-25 snapshot. That statement identifies a manufacturer-described edition relationship; it does not change the exact IDs preserved by an application. QVQ-Max should not inherit the weight identity, parameter count or generation controls of QVQ-72B-Preview, QVQ-Plus or a newer Qwen visual model merely because they share a reasoning theme. A latest-suffixed supplier name also does not by itself establish a fixed checkpoint.\n\nPreparing a visual reasoning question\n\nProvide the relevant image together with the complete question. For a mathematical diagram, preserve labels, dimensions and the accompanying statement, then ask which relationships follow from the visible figure and which require an additional assumption. Request a clearly delimited final answer with the values and relationships used to obtain it. A useful explanation should connect each important inference to something in the supplied material.\n\nFor a chart, ask the model to identify the axes, units and series before interpreting a trend. For a diagram of an algorithm or interface, state the intended behavior and ask how the visible structure relates to that behavior. For a creative brief, distinguish a description of what is actually present from proposed changes or interpretations. These are authored applications of the maker’s documented mathematics, programming, analysis and creation capabilities, not demonstrations of a particular asset’s successful processing.\n\nVideo and multiple pieces of evidence\n\nVideo is explicitly listed as an input modality. For an event-analysis request, supply the relevant segment and ask for an ordered explanation of what changes, which scene supports the conclusion and what remains uncertain. If timing information is available in the input, state how the result should refer to it. The exact model page does not establish a universal video duration, frame count or timestamp precision, so those properties should not be borrowed from another Qwen family.\n\nWhen the question uses several images or passages, label them and explain the relationship the model should examine. Ask for a result organized by those labels so a reviewer can see which evidence supports each point. A reasoning response should remain distinguishable from the final answer; an extended explanation is useful only when its claims can be checked against the source.\n\nContext and answer limits\n\nThe specification lists a 131,072-token context window, a maximum input length of 106,496 tokens and a maximum output length of 8,192 tokens. Keep these separate values rather than deriving an undocumented reasoning-token allowance from their difference. Text, represented visual material and generated content must fit the applicable sequence and output bounds.\n\nFor a dense page or diagram, make the relevant details readable before submission and retain the complete statement needed for the inference. For a long source, select the material tied to the question and reserve enough answer space for a conclusion with supporting evidence. The token specification does not provide an unlimited visual-input allowance or a guarantee that every detail is recalled.\n\nTools, formatting and substantive limits\n\nThe exact capability matrix marks function calling, built-in web search and enforced structured outputs unsupported. QVQ-Max’s visual reasoning therefore should not be presented as automatic browser control, an external-code execution tool or a source of live information. A prompt may request a table or a JSON-shaped textual result, but that request does not create a schema-enforcement contract.\n\nThe dedicated model page does not publish a model-specific hybrid thinking switch or a parameter count. Preserve the documented visual-reasoning identity instead of importing controls or size claims from a different checkpoint. Check small labels, extracted numbers, inferred relationships and code suggestions against the source. The practical output is an explained visual conclusion or draft artifact, grounded in the material the user supplies.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Reason from a written geometric diagram\n\nUse this textual description of a diagram: rectangle ABCD has adjacent sides AB=6 cm and BC=8 cm; diagonal AC is drawn. Find AC and the area of triangle ABC. Give the relationships and calculations supporting each result. Explain which stated geometric property makes the calculation valid; do not assume any extra marked lengths.A concise derivation, two clearly delimited results with units and the relevant rectangle property.Check the diagonal and triangle-area calculations use the stated right angle and correct units.qvq-maxQVQ-Max is Qwen’s visual reasoning model for text, images and video, returning text with an explained solution. Use it for mathematical diagrams, visual analysis, programming-related imagery and creative interpretation; its specification lists a 131,072-token context and 8,192-token output limit.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Overview: reasoning grounded in visual input
QVQ-Max is Qwen’s visual reasoning model. The maker describes chain-of-thought output and stronger capabilities in mathematics, programming, visual analysis, creative work and general tasks. Its dedicated capability page lists text, image and video input with text output. Choose it for a question where the visual material is part of the reasoning problem, such as a diagram, a chart or a sequence of observed events.
The exact model edition
The producer currently describes qvq-max as functionally equivalent to the qvq-max-2025-03-25 snapshot. That statement identifies a manufacturer-described edition relationship; it does not change the exact IDs preserved by an application. QVQ-Max should not inherit the weight identity, parameter count or generation controls of QVQ-72B-Preview, QVQ-Plus or a newer Qwen visual model merely because they share a reasoning theme. A latest-suffixed supplier name also does not by itself establish a fixed checkpoint.
Preparing a visual reasoning question
Provide the relevant image together with the complete question. For a mathematical diagram, preserve labels, dimensions and the accompanying statement, then ask which relationships follow from the visible figure and which require an additional assumption. Request a clearly delimited final answer with the values and relationships used to obtain it. A useful explanation should connect each important inference to something in the supplied material.
For a chart, ask the model to identify the axes, units and series before interpreting a trend. For a diagram of an algorithm or interface, state the intended behavior and ask how the visible structure relates to that behavior. For a creative brief, distinguish a description of what is actually present from proposed changes or interpretations. These are authored applications of the maker’s documented mathematics, programming, analysis and creation capabilities, not demonstrations of a particular asset’s successful processing.
Video and multiple pieces of evidence
Video is explicitly listed as an input modality. For an event-analysis request, supply the relevant segment and ask for an ordered explanation of what changes, which scene supports the conclusion and what remains uncertain. If timing information is available in the input, state how the result should refer to it. The exact model page does not establish a universal video duration, frame count or timestamp precision, so those properties should not be borrowed from another Qwen family.
When the question uses several images or passages, label them and explain the relationship the model should examine. Ask for a result organized by those labels so a reviewer can see which evidence supports each point. A reasoning response should remain distinguishable from the final answer; an extended explanation is useful only when its claims can be checked against the source.
Context and answer limits
The specification lists a 131,072-token context window, a maximum input length of 106,496 tokens and a maximum output length of 8,192 tokens. Keep these separate values rather than deriving an undocumented reasoning-token allowance from their difference. Text, represented visual material and generated content must fit the applicable sequence and output bounds.
For a dense page or diagram, make the relevant details readable before submission and retain the complete statement needed for the inference. For a long source, select the material tied to the question and reserve enough answer space for a conclusion with supporting evidence. The token specification does not provide an unlimited visual-input allowance or a guarantee that every detail is recalled.
Tools, formatting and substantive limits
The exact capability matrix marks function calling, built-in web search and enforced structured outputs unsupported. QVQ-Max’s visual reasoning therefore should not be presented as automatic browser control, an external-code execution tool or a source of live information. A prompt may request a table or a JSON-shaped textual result, but that request does not create a schema-enforcement contract.
The dedicated model page does not publish a model-specific hybrid thinking switch or a parameter count. Preserve the documented visual-reasoning identity instead of importing controls or size claims from a different checkpoint. Check small labels, extracted numbers, inferred relationships and code suggestions against the source. The practical output is an explained visual conclusion or draft artifact, grounded in the material the user supplies.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qvq-max | 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", "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',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',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
Use the method paths shown above.
qvq-maxQVQ-Max is Qwen’s visual reasoning model for text, images and video, returning text with an explained solution. Use it for mathematical diagrams, visual analysis, programming-related imagery and creative interpretation; its specification lists a 131,072-token context and 8,192-token output limit.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Overview: reasoning grounded in visual input
QVQ-Max is Qwen’s visual reasoning model. The maker describes chain-of-thought output and stronger capabilities in mathematics, programming, visual analysis, creative work and general tasks. Its dedicated capability page lists text, image and video input with text output. Choose it for a question where the visual material is part of the reasoning problem, such as a diagram, a chart or a sequence of observed events.
The exact model edition
The producer currently describes qvq-max as functionally equivalent to the qvq-max-2025-03-25 snapshot. That statement identifies a manufacturer-described edition relationship; it does not change the exact IDs preserved by an application. QVQ-Max should not inherit the weight identity, parameter count or generation controls of QVQ-72B-Preview, QVQ-Plus or a newer Qwen visual model merely because they share a reasoning theme. A latest-suffixed supplier name also does not by itself establish a fixed checkpoint.
Preparing a visual reasoning question
Provide the relevant image together with the complete question. For a mathematical diagram, preserve labels, dimensions and the accompanying statement, then ask which relationships follow from the visible figure and which require an additional assumption. Request a clearly delimited final answer with the values and relationships used to obtain it. A useful explanation should connect each important inference to something in the supplied material.
For a chart, ask the model to identify the axes, units and series before interpreting a trend. For a diagram of an algorithm or interface, state the intended behavior and ask how the visible structure relates to that behavior. For a creative brief, distinguish a description of what is actually present from proposed changes or interpretations. These are authored applications of the maker’s documented mathematics, programming, analysis and creation capabilities, not demonstrations of a particular asset’s successful processing.
Video and multiple pieces of evidence
Video is explicitly listed as an input modality. For an event-analysis request, supply the relevant segment and ask for an ordered explanation of what changes, which scene supports the conclusion and what remains uncertain. If timing information is available in the input, state how the result should refer to it. The exact model page does not establish a universal video duration, frame count or timestamp precision, so those properties should not be borrowed from another Qwen family.
When the question uses several images or passages, label them and explain the relationship the model should examine. Ask for a result organized by those labels so a reviewer can see which evidence supports each point. A reasoning response should remain distinguishable from the final answer; an extended explanation is useful only when its claims can be checked against the source.
Context and answer limits
The specification lists a 131,072-token context window, a maximum input length of 106,496 tokens and a maximum output length of 8,192 tokens. Keep these separate values rather than deriving an undocumented reasoning-token allowance from their difference. Text, represented visual material and generated content must fit the applicable sequence and output bounds.
For a dense page or diagram, make the relevant details readable before submission and retain the complete statement needed for the inference. For a long source, select the material tied to the question and reserve enough answer space for a conclusion with supporting evidence. The token specification does not provide an unlimited visual-input allowance or a guarantee that every detail is recalled.
Tools, formatting and substantive limits
The exact capability matrix marks function calling, built-in web search and enforced structured outputs unsupported. QVQ-Max’s visual reasoning therefore should not be presented as automatic browser control, an external-code execution tool or a source of live information. A prompt may request a table or a JSON-shaped textual result, but that request does not create a schema-enforcement contract.
The dedicated model page does not publish a model-specific hybrid thinking switch or a parameter count. Preserve the documented visual-reasoning identity instead of importing controls or size claims from a different checkpoint. Check small labels, extracted numbers, inferred relationships and code suggestions against the source. The practical output is an explained visual conclusion or draft artifact, grounded in the material the user supplies.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qvq-max | 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 $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "qvq-max",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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', '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', '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
Use the method paths shown above.
Technical example in English
Reason from a written geometric diagram\n\nUse this textual description of a diagram: rectangle ABCD has adjacent sides AB=6 cm and BC=8 cm; diagonal AC is drawn. Find AC and the area of triangle ABC. Give the relationships and calculations supporting each result. Explain which stated geometric property makes the calculation valid; do not assume any extra marked lengths.A concise derivation, two clearly delimited results with units and the relevant rectangle property.Check the diagonal and triangle-area calculations use the stated right angle and correct units.