QVQ-Plus is the Plus line of Qwen’s QVQ visual-reasoning models. The manufacturer highlights mathematics, programming, visual analysis, creative work and general tasks involving visual evidence. It accepts text, images and video and returns text, including a reasoning process and an answer. The Plus name is a family identity, not a substitute for a fixed QVQ-Max snapshot or an image-generation model.
The documented context window is 131,072 tokens, with a maximum input of 106,496 tokens and a maximum output of 8,192 tokens. Keep these limits distinct when planning a request. Include the written task, relevant visual material and necessary conversation history, then allow room for the explanation and final answer. A screenshot’s or video’s contribution is determined by its processed representation, so the number of typed characters alone is not a sufficient measure of the complete input.
The manufacturer describes QVQ as combining visual input with reasoning and a text answer. The documented QVQ service flow uses streaming. An application should distinguish intermediate reasoning from the final-answer fragments and assemble the text before presenting it as a completed explanation. A concise requested answer can still follow an internal reasoning process; asking for brevity does not change the model into a separate non-thinking edition.
For a chart or table, state the comparison to make and provide readable labels, units and headings. For example, ask whether two plotted series diverge over a selected range, then request the visible observations supporting the conclusion. If the answer needs numerical values, make sure they are present in the source and ask the model to identify uncertainty where only an approximate visual reading is possible. Preserve the original image so the result can be checked against the evidence.
For a document or interface screenshot, define the user’s goal and the part of the material to analyze. A useful request might ask which visible fields are required for a stated workflow, how the page is organized or what the diagram’s connectors imply. For a visual programming task, provide the screenshot and written requirements, then ask for a text explanation or proposed implementation consistent with the visible structure. Distinguish properties that can be observed from those that depend on hidden application behavior.
For video, identify the event, sequence or relationship you want explained. Keep the relevant segment and provide readable stills where small details matter. Label multiple inputs and explain their order so a comparison is not confused with unrelated scenes. The result is a textual account of the material and a conclusion about the stated question; it does not itself edit the source, create a new clip or verify something outside the observation.
The manufacturer’s Plus card does not advertise function calling, web search or constrained structured output. Organize the text answer with clear headings, a comparison table or a list of observations, and validate any machine-readable-looking result before an application uses it. The chat reference says system messages have no effect for QVQ models, so put role, task and formatting instructions in the user message. Retain the documented QVQ sampling defaults rather than importing a temperature or token-selection recipe from a different Qwen family.
For a useful analytical artifact, request the observed facts, the explanation and a clearly named final answer. Check calculations against visible numbers, labels and units, and check a document interpretation against the source section it refers to. Keep the chosen Plus identity and input materials with the result when a case must be revisited. Separate a reasoned proposal from any subsequent action: an application or person still has to perform a requested tool operation and return its outcome. This model is a source of visual reasoning and text, with the original material retained as the basis for review.
", "aboutText": "QVQ-Plus is the Plus line of Qwen’s QVQ visual-reasoning models. The manufacturer highlights mathematics, programming, visual analysis, creative work and general tasks involving visual evidence. It accepts text, images and video and returns text, including a reasoning process and an answer. The Plus name is a family identity, not a substitute for a fixed QVQ-Max snapshot or an image-generation model.\n\nThe documented context window is 131,072 tokens, with a maximum input of 106,496 tokens and a maximum output of 8,192 tokens. Keep these limits distinct when planning a request. Include the written task, relevant visual material and necessary conversation history, then allow room for the explanation and final answer. A screenshot’s or video’s contribution is determined by its processed representation, so the number of typed characters alone is not a sufficient measure of the complete input.\n\nThe manufacturer describes QVQ as combining visual input with reasoning and a text answer. The documented QVQ service flow uses streaming. An application should distinguish intermediate reasoning from the final-answer fragments and assemble the text before presenting it as a completed explanation. A concise requested answer can still follow an internal reasoning process; asking for brevity does not change the model into a separate non-thinking edition.\n\nFor a chart or table, state the comparison to make and provide readable labels, units and headings. For example, ask whether two plotted series diverge over a selected range, then request the visible observations supporting the conclusion. If the answer needs numerical values, make sure they are present in the source and ask the model to identify uncertainty where only an approximate visual reading is possible. Preserve the original image so the result can be checked against the evidence.\n\nFor a document or interface screenshot, define the user’s goal and the part of the material to analyze. A useful request might ask which visible fields are required for a stated workflow, how the page is organized or what the diagram’s connectors imply. For a visual programming task, provide the screenshot and written requirements, then ask for a text explanation or proposed implementation consistent with the visible structure. Distinguish properties that can be observed from those that depend on hidden application behavior.\n\nFor video, identify the event, sequence or relationship you want explained. Keep the relevant segment and provide readable stills where small details matter. Label multiple inputs and explain their order so a comparison is not confused with unrelated scenes. The result is a textual account of the material and a conclusion about the stated question; it does not itself edit the source, create a new clip or verify something outside the observation.\n\nThe manufacturer’s Plus card does not advertise function calling, web search or constrained structured output. Organize the text answer with clear headings, a comparison table or a list of observations, and validate any machine-readable-looking result before an application uses it. The chat reference says system messages have no effect for QVQ models, so put role, task and formatting instructions in the user message. Retain the documented QVQ sampling defaults rather than importing a temperature or token-selection recipe from a different Qwen family.\n\nFor a useful analytical artifact, request the observed facts, the explanation and a clearly named final answer. Check calculations against visible numbers, labels and units, and check a document interpretation against the source section it refers to. Keep the chosen Plus identity and input materials with the result when a case must be revisited. Separate a reasoned proposal from any subsequent action: an application or person still has to perform a requested tool operation and return its outcome. This model is a source of visual reasoning and text, with the original material retained as the basis for review.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Compare a transcribed chart trend\n\nAnalyze this chart transcription: week 1, signups 100 and activations 80; week 2, signups 150 and activations 90; week 3, signups 200 and activations 100. Calculate activation share each week and explain whether the signup and activation trends tell the same story. Use only these values and distinguish counts from rates.A three-row count-and-rate table followed by a concise trend comparison.Activation share uses activations divided by signups, and increasing counts are not confused with increasing share.qvq-plusQVQ-Plus combines a text question with images or video to produce a reasoned text answer. Use it for visual mathematics, chart and document analysis, or questions whose conclusion depends on several visible details; the Plus line retains its own identity.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
QVQ-Plus is the Plus line of Qwen’s QVQ visual-reasoning models. The manufacturer highlights mathematics, programming, visual analysis, creative work and general tasks involving visual evidence. It accepts text, images and video and returns text, including a reasoning process and an answer. The Plus name is a family identity, not a substitute for a fixed QVQ-Max snapshot or an image-generation model.
The documented context window is 131,072 tokens, with a maximum input of 106,496 tokens and a maximum output of 8,192 tokens. Keep these limits distinct when planning a request. Include the written task, relevant visual material and necessary conversation history, then allow room for the explanation and final answer. A screenshot’s or video’s contribution is determined by its processed representation, so the number of typed characters alone is not a sufficient measure of the complete input.
The manufacturer describes QVQ as combining visual input with reasoning and a text answer. The documented QVQ service flow uses streaming. An application should distinguish intermediate reasoning from the final-answer fragments and assemble the text before presenting it as a completed explanation. A concise requested answer can still follow an internal reasoning process; asking for brevity does not change the model into a separate non-thinking edition.
For a chart or table, state the comparison to make and provide readable labels, units and headings. For example, ask whether two plotted series diverge over a selected range, then request the visible observations supporting the conclusion. If the answer needs numerical values, make sure they are present in the source and ask the model to identify uncertainty where only an approximate visual reading is possible. Preserve the original image so the result can be checked against the evidence.
For a document or interface screenshot, define the user’s goal and the part of the material to analyze. A useful request might ask which visible fields are required for a stated workflow, how the page is organized or what the diagram’s connectors imply. For a visual programming task, provide the screenshot and written requirements, then ask for a text explanation or proposed implementation consistent with the visible structure. Distinguish properties that can be observed from those that depend on hidden application behavior.
For video, identify the event, sequence or relationship you want explained. Keep the relevant segment and provide readable stills where small details matter. Label multiple inputs and explain their order so a comparison is not confused with unrelated scenes. The result is a textual account of the material and a conclusion about the stated question; it does not itself edit the source, create a new clip or verify something outside the observation.
The manufacturer’s Plus card does not advertise function calling, web search or constrained structured output. Organize the text answer with clear headings, a comparison table or a list of observations, and validate any machine-readable-looking result before an application uses it. The chat reference says system messages have no effect for QVQ models, so put role, task and formatting instructions in the user message. Retain the documented QVQ sampling defaults rather than importing a temperature or token-selection recipe from a different Qwen family.
For a useful analytical artifact, request the observed facts, the explanation and a clearly named final answer. Check calculations against visible numbers, labels and units, and check a document interpretation against the source section it refers to. Keep the chosen Plus identity and input materials with the result when a case must be revisited. Separate a reasoned proposal from any subsequent action: an application or person still has to perform a requested tool operation and return its outcome. This model is a source of visual reasoning and text, with the original material retained as the basis for review.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qvq-plus | 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 $0.00058 / 1K tokens Output · Output tokens $0.00144 / 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-plus", "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-plus',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-plus',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-plus
Use the method paths shown above.
qvq-plusQVQ-Plus combines a text question with images or video to produce a reasoned text answer. Use it for visual mathematics, chart and document analysis, or questions whose conclusion depends on several visible details; the Plus line retains its own identity.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
QVQ-Plus is the Plus line of Qwen’s QVQ visual-reasoning models. The manufacturer highlights mathematics, programming, visual analysis, creative work and general tasks involving visual evidence. It accepts text, images and video and returns text, including a reasoning process and an answer. The Plus name is a family identity, not a substitute for a fixed QVQ-Max snapshot or an image-generation model.
The documented context window is 131,072 tokens, with a maximum input of 106,496 tokens and a maximum output of 8,192 tokens. Keep these limits distinct when planning a request. Include the written task, relevant visual material and necessary conversation history, then allow room for the explanation and final answer. A screenshot’s or video’s contribution is determined by its processed representation, so the number of typed characters alone is not a sufficient measure of the complete input.
The manufacturer describes QVQ as combining visual input with reasoning and a text answer. The documented QVQ service flow uses streaming. An application should distinguish intermediate reasoning from the final-answer fragments and assemble the text before presenting it as a completed explanation. A concise requested answer can still follow an internal reasoning process; asking for brevity does not change the model into a separate non-thinking edition.
For a chart or table, state the comparison to make and provide readable labels, units and headings. For example, ask whether two plotted series diverge over a selected range, then request the visible observations supporting the conclusion. If the answer needs numerical values, make sure they are present in the source and ask the model to identify uncertainty where only an approximate visual reading is possible. Preserve the original image so the result can be checked against the evidence.
For a document or interface screenshot, define the user’s goal and the part of the material to analyze. A useful request might ask which visible fields are required for a stated workflow, how the page is organized or what the diagram’s connectors imply. For a visual programming task, provide the screenshot and written requirements, then ask for a text explanation or proposed implementation consistent with the visible structure. Distinguish properties that can be observed from those that depend on hidden application behavior.
For video, identify the event, sequence or relationship you want explained. Keep the relevant segment and provide readable stills where small details matter. Label multiple inputs and explain their order so a comparison is not confused with unrelated scenes. The result is a textual account of the material and a conclusion about the stated question; it does not itself edit the source, create a new clip or verify something outside the observation.
The manufacturer’s Plus card does not advertise function calling, web search or constrained structured output. Organize the text answer with clear headings, a comparison table or a list of observations, and validate any machine-readable-looking result before an application uses it. The chat reference says system messages have no effect for QVQ models, so put role, task and formatting instructions in the user message. Retain the documented QVQ sampling defaults rather than importing a temperature or token-selection recipe from a different Qwen family.
For a useful analytical artifact, request the observed facts, the explanation and a clearly named final answer. Check calculations against visible numbers, labels and units, and check a document interpretation against the source section it refers to. Keep the chosen Plus identity and input materials with the result when a case must be revisited. Separate a reasoned proposal from any subsequent action: an application or person still has to perform a requested tool operation and return its outcome. This model is a source of visual reasoning and text, with the original material retained as the basis for review.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qvq-plus | 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 $0.00058 / 1K tokens Output · Output tokens $0.00144 / 1K tokens Input · Cache read $0 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "qvq-plus",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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-plus', '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-plus', '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-plus
Use the method paths shown above.
Technical example in English
Compare a transcribed chart trend\n\nAnalyze this chart transcription: week 1, signups 100 and activations 80; week 2, signups 150 and activations 90; week 3, signups 200 and activations 100. Calculate activation share each week and explain whether the signup and activation trends tell the same story. Use only these values and distinguish counts from rates.A three-row count-and-rate table followed by a concise trend comparison.Activation share uses activations divided by signups, and increasing counts are not confused with increasing share.