Qwen-VL-Plus is the Qwen visual-language line with a particular focus on detail recognition and text inside images. The maker describes support for images above one million pixels and different aspect ratios. This makes the model relevant when the answer depends on a small label, a field on a page or the relationship between textual and visual elements, rather than only the subject of a photograph.
The current producer card describes the unversioned qwen-vl-plus name as functionally equivalent to qwen-vl-plus-2025-08-15. Preserve the exact edition name in a repeatable task. A Plus label, a Latest alias and another dated snapshot are separate choices; matching the family name does not make their specifications interchangeable.
Model capabilities
The maker lists text, images and video as input, with text as output. A text instruction can direct the model to read a section of a document, describe objects, explain a layout or answer a question about a scene. Recognition and explanation are related tasks but need different output requirements: a transcription should preserve the visible wording, while an explanation should say how the visible details relate to the question.
For document extraction, supply a readable page and identify the fields to return. A form can call for its field labels and values; a table can call for the requested row together with its column headings. If a value is not visible, define an explicit representation for a missing value. This illustrative output design helps the application distinguish extracted text from a guessed completion.
For a layout review, ask about the elements that matter: where a label is located, which object it belongs to, and how two versions differ. Give each image a role and keep the comparison criteria the same. For a screenshot-based explanation, state the user's goal and ask for a short instruction based on the visible controls. The answer is text about the interface, not a performed action.
The producer tables include response-prefix continuation and context caching. Structured output, batch submission and fine-tuning are not exposed identically across producer configurations; they should be treated as interface options rather than an unconditional consequence of choosing the Plus name. Function calling and web search are not listed as supported on this card. A request to format extracted fields is distinct from a request to execute a function or obtain new information from the web.
Context limits
The published card gives a 131,072-token context window, a maximum input of 129,024 tokens and a maximum output of 8,192 tokens. The image or video representation uses input capacity alongside the question and supporting text. Plan the visual material and the answer separately: a long or detailed input can still require only a short list of fields or observations.
Input preparation
The maker's emphasis on detail and varied proportions does not remove the need for readable material. Keep the area containing the requested text clear. When cropping a table, retain the headings and units needed to interpret its values; when using several pages, indicate their order and the section to examine. State whether you want the original wording, a summary, or an interpretation so that those results are not mixed.
For video, define the event or visible detail to describe and the desired structure of the response. A practical task might ask for the sequence of actions in a demonstration and the objects involved in each step. The documented output is text; the card does not list audio as input or speech as output. This visual route therefore should not be used as evidence that a spoken transcript has been understood.
A useful repeatable workflow is to give the same extraction fields to several document images, keep the image identifiers beside the results, and then compare the resulting records in the application. Another is to pair a screenshot with a written requirement and ask for the visible matches, differences and unresolved details. In either case, keep the source image associated with each returned value so that the result can be inspected.
", "aboutText": "Qwen-VL-Plus is the Qwen visual-language line with a particular focus on detail recognition and text inside images. The maker describes support for images above one million pixels and different aspect ratios. This makes the model relevant when the answer depends on a small label, a field on a page or the relationship between textual and visual elements, rather than only the subject of a photograph.\n\nThe current producer card describes the unversioned qwen-vl-plus name as functionally equivalent to qwen-vl-plus-2025-08-15. Preserve the exact edition name in a repeatable task. A Plus label, a Latest alias and another dated snapshot are separate choices; matching the family name does not make their specifications interchangeable.\n\nModel capabilities\n\nThe maker lists text, images and video as input, with text as output. A text instruction can direct the model to read a section of a document, describe objects, explain a layout or answer a question about a scene. Recognition and explanation are related tasks but need different output requirements: a transcription should preserve the visible wording, while an explanation should say how the visible details relate to the question.\n\nFor document extraction, supply a readable page and identify the fields to return. A form can call for its field labels and values; a table can call for the requested row together with its column headings. If a value is not visible, define an explicit representation for a missing value. This illustrative output design helps the application distinguish extracted text from a guessed completion.\n\nFor a layout review, ask about the elements that matter: where a label is located, which object it belongs to, and how two versions differ. Give each image a role and keep the comparison criteria the same. For a screenshot-based explanation, state the user's goal and ask for a short instruction based on the visible controls. The answer is text about the interface, not a performed action.\n\nThe producer tables include response-prefix continuation and context caching. Structured output, batch submission and fine-tuning are not exposed identically across producer configurations; they should be treated as interface options rather than an unconditional consequence of choosing the Plus name. Function calling and web search are not listed as supported on this card. A request to format extracted fields is distinct from a request to execute a function or obtain new information from the web.\n\nContext limits\n\nThe published card gives a 131,072-token context window, a maximum input of 129,024 tokens and a maximum output of 8,192 tokens. The image or video representation uses input capacity alongside the question and supporting text. Plan the visual material and the answer separately: a long or detailed input can still require only a short list of fields or observations.\n\nInput preparation\n\nThe maker's emphasis on detail and varied proportions does not remove the need for readable material. Keep the area containing the requested text clear. When cropping a table, retain the headings and units needed to interpret its values; when using several pages, indicate their order and the section to examine. State whether you want the original wording, a summary, or an interpretation so that those results are not mixed.\n\nFor video, define the event or visible detail to describe and the desired structure of the response. A practical task might ask for the sequence of actions in a demonstration and the objects involved in each step. The documented output is text; the card does not list audio as input or speech as output. This visual route therefore should not be used as evidence that a spoken transcript has been understood.\n\nA useful repeatable workflow is to give the same extraction fields to several document images, keep the image identifiers beside the results, and then compare the resulting records in the application. Another is to pair a screenshot with a written requirement and ask for the visible matches, differences and unresolved details. In either case, keep the source image associated with each returned value so that the result can be inspected.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Compare transcribed package labels\n\nCompare these package-label transcriptions using the same fields. Label A: Oat drink; 1 L; ingredients: water, oats, salt. Label B: Oat drink; 750 mL; ingredients: water, oats, sunflower oil, salt. Return product name, volume and ingredient differences. Preserve original units and do not infer nutrition values or visual layout.A label comparison table plus a short list of explicit wording and quantity differences.Check that sunflower oil is attributed only to Label B and the original L/mL units are retained.qwen-vl-plusQwen-VL-Plus reads text and details in images and combines them with a written question. Its maker documents image and video input, text output, high-resolution images and varied aspect ratios for document extraction, visual comparison and scene explanation.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Qwen-VL-Plus is the Qwen visual-language line with a particular focus on detail recognition and text inside images. The maker describes support for images above one million pixels and different aspect ratios. This makes the model relevant when the answer depends on a small label, a field on a page or the relationship between textual and visual elements, rather than only the subject of a photograph.
The current producer card describes the unversioned qwen-vl-plus name as functionally equivalent to qwen-vl-plus-2025-08-15. Preserve the exact edition name in a repeatable task. A Plus label, a Latest alias and another dated snapshot are separate choices; matching the family name does not make their specifications interchangeable.
Model capabilities
The maker lists text, images and video as input, with text as output. A text instruction can direct the model to read a section of a document, describe objects, explain a layout or answer a question about a scene. Recognition and explanation are related tasks but need different output requirements: a transcription should preserve the visible wording, while an explanation should say how the visible details relate to the question.
For document extraction, supply a readable page and identify the fields to return. A form can call for its field labels and values; a table can call for the requested row together with its column headings. If a value is not visible, define an explicit representation for a missing value. This illustrative output design helps the application distinguish extracted text from a guessed completion.
For a layout review, ask about the elements that matter: where a label is located, which object it belongs to, and how two versions differ. Give each image a role and keep the comparison criteria the same. For a screenshot-based explanation, state the user's goal and ask for a short instruction based on the visible controls. The answer is text about the interface, not a performed action.
The producer tables include response-prefix continuation and context caching. Structured output, batch submission and fine-tuning are not exposed identically across producer configurations; they should be treated as interface options rather than an unconditional consequence of choosing the Plus name. Function calling and web search are not listed as supported on this card. A request to format extracted fields is distinct from a request to execute a function or obtain new information from the web.
Context limits
The published card gives a 131,072-token context window, a maximum input of 129,024 tokens and a maximum output of 8,192 tokens. The image or video representation uses input capacity alongside the question and supporting text. Plan the visual material and the answer separately: a long or detailed input can still require only a short list of fields or observations.
Input preparation
The maker's emphasis on detail and varied proportions does not remove the need for readable material. Keep the area containing the requested text clear. When cropping a table, retain the headings and units needed to interpret its values; when using several pages, indicate their order and the section to examine. State whether you want the original wording, a summary, or an interpretation so that those results are not mixed.
For video, define the event or visible detail to describe and the desired structure of the response. A practical task might ask for the sequence of actions in a demonstration and the objects involved in each step. The documented output is text; the card does not list audio as input or speech as output. This visual route therefore should not be used as evidence that a spoken transcript has been understood.
A useful repeatable workflow is to give the same extraction fields to several document images, keep the image identifiers beside the results, and then compare the resulting records in the application. Another is to pair a screenshot with a written requirement and ask for the visible matches, differences and unresolved details. In either case, keep the source image associated with each returned value so that the result can be inspected.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qwen-vl-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 $0.00024 / 1K tokens Output · Output tokens $0.000572 / 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": "qwen-vl-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='qwen-vl-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='qwen-vl-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 qwen-vl-plus
Use the method paths shown above.
qwen-vl-plusQwen-VL-Plus reads text and details in images and combines them with a written question. Its maker documents image and video input, text output, high-resolution images and varied aspect ratios for document extraction, visual comparison and scene explanation.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Qwen-VL-Plus is the Qwen visual-language line with a particular focus on detail recognition and text inside images. The maker describes support for images above one million pixels and different aspect ratios. This makes the model relevant when the answer depends on a small label, a field on a page or the relationship between textual and visual elements, rather than only the subject of a photograph.
The current producer card describes the unversioned qwen-vl-plus name as functionally equivalent to qwen-vl-plus-2025-08-15. Preserve the exact edition name in a repeatable task. A Plus label, a Latest alias and another dated snapshot are separate choices; matching the family name does not make their specifications interchangeable.
Model capabilities
The maker lists text, images and video as input, with text as output. A text instruction can direct the model to read a section of a document, describe objects, explain a layout or answer a question about a scene. Recognition and explanation are related tasks but need different output requirements: a transcription should preserve the visible wording, while an explanation should say how the visible details relate to the question.
For document extraction, supply a readable page and identify the fields to return. A form can call for its field labels and values; a table can call for the requested row together with its column headings. If a value is not visible, define an explicit representation for a missing value. This illustrative output design helps the application distinguish extracted text from a guessed completion.
For a layout review, ask about the elements that matter: where a label is located, which object it belongs to, and how two versions differ. Give each image a role and keep the comparison criteria the same. For a screenshot-based explanation, state the user's goal and ask for a short instruction based on the visible controls. The answer is text about the interface, not a performed action.
The producer tables include response-prefix continuation and context caching. Structured output, batch submission and fine-tuning are not exposed identically across producer configurations; they should be treated as interface options rather than an unconditional consequence of choosing the Plus name. Function calling and web search are not listed as supported on this card. A request to format extracted fields is distinct from a request to execute a function or obtain new information from the web.
Context limits
The published card gives a 131,072-token context window, a maximum input of 129,024 tokens and a maximum output of 8,192 tokens. The image or video representation uses input capacity alongside the question and supporting text. Plan the visual material and the answer separately: a long or detailed input can still require only a short list of fields or observations.
Input preparation
The maker's emphasis on detail and varied proportions does not remove the need for readable material. Keep the area containing the requested text clear. When cropping a table, retain the headings and units needed to interpret its values; when using several pages, indicate their order and the section to examine. State whether you want the original wording, a summary, or an interpretation so that those results are not mixed.
For video, define the event or visible detail to describe and the desired structure of the response. A practical task might ask for the sequence of actions in a demonstration and the objects involved in each step. The documented output is text; the card does not list audio as input or speech as output. This visual route therefore should not be used as evidence that a spoken transcript has been understood.
A useful repeatable workflow is to give the same extraction fields to several document images, keep the image identifiers beside the results, and then compare the resulting records in the application. Another is to pair a screenshot with a written requirement and ask for the visible matches, differences and unresolved details. In either case, keep the source image associated with each returned value so that the result can be inspected.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qwen-vl-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 $0.00024 / 1K tokens Output · Output tokens $0.000572 / 1K tokens Input · Cache read $0 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "qwen-vl-plus",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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': 'qwen-vl-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': 'qwen-vl-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 qwen-vl-plus
Use the method paths shown above.
Technical example in English
Compare transcribed package labels\n\nCompare these package-label transcriptions using the same fields. Label A: Oat drink; 1 L; ingredients: water, oats, salt. Label B: Oat drink; 750 mL; ingredients: water, oats, sunflower oil, salt. Return product name, volume and ingredient differences. Preserve original units and do not infer nutrition values or visual layout.A label comparison table plus a short list of explicit wording and quantity differences.Check that sunflower oil is attributed only to Label B and the original L/mL units are retained.