Qwen3-VL-8B-Thinking is the reasoning-focused 8B dense edition of Alibaba’s Qwen3-VL family. It combines text, images and video in a shared task and generates text. Qwen releases Thinking and Instruct editions separately; this card concerns the named Thinking model, whose purpose includes analysing visual evidence before producing an answer. Text-only work is also part of the model’s language capability.
The manufacturer presents visual agents first: the model can recognise desktop or mobile interface elements, interpret their functions and reason about the next interaction. In an application, screenshots supply the current state and tools carry out the selected actions. A useful brief gives the user’s goal, the visible screen and the permitted actions, then asks for the next step and the element that justifies it. The generated interpretation is distinct from an action executed by the surrounding application.
Visual coding connects reference images or video with textual code. Qwen documents Draw.io diagrams and HTML, CSS and JavaScript as example outputs. Supply a screenshot or sketch together with the required behaviour, content and target layout; request an editable code or diagram artifact. For spatial work, the family describes object position, viewpoint and occlusion, with 2D grounding and 3D grounding. State the coordinate convention if you need locations, so that a described position and a requested box use the same reference.
The native context is 256K tokens for text and interleaved visual material. The model card also describes expansion to one million tokens, which is a separate configured extension rather than the native context specification. Long-context applications include cross-referencing document pages and locating events in video. Preserve page order and video timestamps when preparing the input, and ask the answer to identify the page or moment used for each conclusion.
Multimodal reasoning covers mathematical and scientific tasks that require both the visible material and its written question. The family also supports broad visual recognition across objects, products, landmarks, plants and animals. Its OCR coverage spans 32 languages and includes challenging images with low light, blur or tilt, along with document-structure interpretation. For a scanned problem, ask for a transcription first and a solution second; this makes an incorrectly read sign or label visible before it changes the reasoning.
Three architecture updates support this visual and temporal work. Interleaved-MRoPE distributes positional information across time, width and height; DeepStack introduces visual features from several levels into the language model; explicit text timestamps represent the temporal position of video frame groups. Their practical relevance is preserving spatial detail and connecting an event description to a moment in the source. They do not turn a small or unreadable source detail into guaranteed recognition.
The exact Thinking model card gives generation recommendations separately for visual and text tasks. Both use sampling with temperature 1.0, top-p 0.95 and top-k 20; the visual example uses presence penalty 0.0, while the text example uses 1.5. Its example output-length settings are 40,960 for visual work and 32,768 for text, with 81,920 suggested for selected demanding text evaluations. These are tuning recommendations, not a universal maximum-output guarantee or parameters that a surrounding service necessarily exposes.
For a practical document task, supply ordered page images and ask: “Extract the section headings, explain the relationship between the diagram and the adjacent text, and attach a page reference to each finding.” For video, define the event you want located and request its timestamp plus a short visual explanation. For a visual reasoning question, state the required final artifact and the assumptions that may be used. The output remains a textual explanation, extracted content, code or proposed tool step; this edition’s visual input is not a video-generation or speech-generation workflow.
", "aboutText": "Qwen3-VL-8B-Thinking is the reasoning-focused 8B dense edition of Alibaba’s Qwen3-VL family. It combines text, images and video in a shared task and generates text. Qwen releases Thinking and Instruct editions separately; this card concerns the named Thinking model, whose purpose includes analysing visual evidence before producing an answer. Text-only work is also part of the model’s language capability.\n\nThe manufacturer presents visual agents first: the model can recognise desktop or mobile interface elements, interpret their functions and reason about the next interaction. In an application, screenshots supply the current state and tools carry out the selected actions. A useful brief gives the user’s goal, the visible screen and the permitted actions, then asks for the next step and the element that justifies it. The generated interpretation is distinct from an action executed by the surrounding application.\n\nVisual coding connects reference images or video with textual code. Qwen documents Draw.io diagrams and HTML, CSS and JavaScript as example outputs. Supply a screenshot or sketch together with the required behaviour, content and target layout; request an editable code or diagram artifact. For spatial work, the family describes object position, viewpoint and occlusion, with 2D grounding and 3D grounding. State the coordinate convention if you need locations, so that a described position and a requested box use the same reference.\n\nThe native context is 256K tokens for text and interleaved visual material. The model card also describes expansion to one million tokens, which is a separate configured extension rather than the native context specification. Long-context applications include cross-referencing document pages and locating events in video. Preserve page order and video timestamps when preparing the input, and ask the answer to identify the page or moment used for each conclusion.\n\nMultimodal reasoning covers mathematical and scientific tasks that require both the visible material and its written question. The family also supports broad visual recognition across objects, products, landmarks, plants and animals. Its OCR coverage spans 32 languages and includes challenging images with low light, blur or tilt, along with document-structure interpretation. For a scanned problem, ask for a transcription first and a solution second; this makes an incorrectly read sign or label visible before it changes the reasoning.\n\nThree architecture updates support this visual and temporal work. Interleaved-MRoPE distributes positional information across time, width and height; DeepStack introduces visual features from several levels into the language model; explicit text timestamps represent the temporal position of video frame groups. Their practical relevance is preserving spatial detail and connecting an event description to a moment in the source. They do not turn a small or unreadable source detail into guaranteed recognition.\n\nThe exact Thinking model card gives generation recommendations separately for visual and text tasks. Both use sampling with temperature 1.0, top-p 0.95 and top-k 20; the visual example uses presence penalty 0.0, while the text example uses 1.5. Its example output-length settings are 40,960 for visual work and 32,768 for text, with 81,920 suggested for selected demanding text evaluations. These are tuning recommendations, not a universal maximum-output guarantee or parameters that a surrounding service necessarily exposes.\n\nFor a practical document task, supply ordered page images and ask: “Extract the section headings, explain the relationship between the diagram and the adjacent text, and attach a page reference to each finding.” For video, define the event you want located and request its timestamp plus a short visual explanation. For a visual reasoning question, state the required final artifact and the assumptions that may be used. The output remains a textual explanation, extracted content, code or proposed tool step; this edition’s visual input is not a video-generation or speech-generation workflow.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Reason about a written interface layout\n\nUse this textual layout description: a dialog contains a title at the top, a long message in the middle and Cancel/Confirm buttons at the bottom. On a short screen, only the message area should scroll; both buttons must stay visible. Propose HTML and CSS structure and explain the height constraints. Do not assume an image was supplied.An editable HTML/CSS proposal and a short explanation of which region scrolls.Check the proposed structure limits message overflow while keeping both actions outside that scroll area.Qwen/Qwen3-VL-8B-ThinkingQwen3-VL-8B-Thinking is Qwen’s reasoning-focused 8B vision-language edition. It combines text, images and video for visual problem solving, document interpretation, spatial analysis and code generation from visual references.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Qwen3-VL-8B-Thinking is the reasoning-focused 8B dense edition of Alibaba’s Qwen3-VL family. It combines text, images and video in a shared task and generates text. Qwen releases Thinking and Instruct editions separately; this card concerns the named Thinking model, whose purpose includes analysing visual evidence before producing an answer. Text-only work is also part of the model’s language capability.
The manufacturer presents visual agents first: the model can recognise desktop or mobile interface elements, interpret their functions and reason about the next interaction. In an application, screenshots supply the current state and tools carry out the selected actions. A useful brief gives the user’s goal, the visible screen and the permitted actions, then asks for the next step and the element that justifies it. The generated interpretation is distinct from an action executed by the surrounding application.
Visual coding connects reference images or video with textual code. Qwen documents Draw.io diagrams and HTML, CSS and JavaScript as example outputs. Supply a screenshot or sketch together with the required behaviour, content and target layout; request an editable code or diagram artifact. For spatial work, the family describes object position, viewpoint and occlusion, with 2D grounding and 3D grounding. State the coordinate convention if you need locations, so that a described position and a requested box use the same reference.
The native context is 256K tokens for text and interleaved visual material. The model card also describes expansion to one million tokens, which is a separate configured extension rather than the native context specification. Long-context applications include cross-referencing document pages and locating events in video. Preserve page order and video timestamps when preparing the input, and ask the answer to identify the page or moment used for each conclusion.
Multimodal reasoning covers mathematical and scientific tasks that require both the visible material and its written question. The family also supports broad visual recognition across objects, products, landmarks, plants and animals. Its OCR coverage spans 32 languages and includes challenging images with low light, blur or tilt, along with document-structure interpretation. For a scanned problem, ask for a transcription first and a solution second; this makes an incorrectly read sign or label visible before it changes the reasoning.
Three architecture updates support this visual and temporal work. Interleaved-MRoPE distributes positional information across time, width and height; DeepStack introduces visual features from several levels into the language model; explicit text timestamps represent the temporal position of video frame groups. Their practical relevance is preserving spatial detail and connecting an event description to a moment in the source. They do not turn a small or unreadable source detail into guaranteed recognition.
The exact Thinking model card gives generation recommendations separately for visual and text tasks. Both use sampling with temperature 1.0, top-p 0.95 and top-k 20; the visual example uses presence penalty 0.0, while the text example uses 1.5. Its example output-length settings are 40,960 for visual work and 32,768 for text, with 81,920 suggested for selected demanding text evaluations. These are tuning recommendations, not a universal maximum-output guarantee or parameters that a surrounding service necessarily exposes.
For a practical document task, supply ordered page images and ask: “Extract the section headings, explain the relationship between the diagram and the adjacent text, and attach a page reference to each finding.” For video, define the event you want located and request its timestamp plus a short visual explanation. For a visual reasoning question, state the required final artifact and the assumptions that may be used. The output remains a textual explanation, extracted content, code or proposed tool step; this edition’s visual input is not a video-generation or speech-generation workflow.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits Qwen/Qwen3-VL-8B-Thinking | 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 $0.000144 / 1K tokens Output · Output tokens $0.00143 / 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/Qwen3-VL-8B-Thinking", "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/Qwen3-VL-8B-Thinking',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/Qwen3-VL-8B-Thinking',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/Qwen3-VL-8B-Thinking
Use the method paths shown above.
Qwen/Qwen3-VL-8B-ThinkingQwen3-VL-8B-Thinking is Qwen’s reasoning-focused 8B vision-language edition. It combines text, images and video for visual problem solving, document interpretation, spatial analysis and code generation from visual references.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Qwen3-VL-8B-Thinking is the reasoning-focused 8B dense edition of Alibaba’s Qwen3-VL family. It combines text, images and video in a shared task and generates text. Qwen releases Thinking and Instruct editions separately; this card concerns the named Thinking model, whose purpose includes analysing visual evidence before producing an answer. Text-only work is also part of the model’s language capability.
The manufacturer presents visual agents first: the model can recognise desktop or mobile interface elements, interpret their functions and reason about the next interaction. In an application, screenshots supply the current state and tools carry out the selected actions. A useful brief gives the user’s goal, the visible screen and the permitted actions, then asks for the next step and the element that justifies it. The generated interpretation is distinct from an action executed by the surrounding application.
Visual coding connects reference images or video with textual code. Qwen documents Draw.io diagrams and HTML, CSS and JavaScript as example outputs. Supply a screenshot or sketch together with the required behaviour, content and target layout; request an editable code or diagram artifact. For spatial work, the family describes object position, viewpoint and occlusion, with 2D grounding and 3D grounding. State the coordinate convention if you need locations, so that a described position and a requested box use the same reference.
The native context is 256K tokens for text and interleaved visual material. The model card also describes expansion to one million tokens, which is a separate configured extension rather than the native context specification. Long-context applications include cross-referencing document pages and locating events in video. Preserve page order and video timestamps when preparing the input, and ask the answer to identify the page or moment used for each conclusion.
Multimodal reasoning covers mathematical and scientific tasks that require both the visible material and its written question. The family also supports broad visual recognition across objects, products, landmarks, plants and animals. Its OCR coverage spans 32 languages and includes challenging images with low light, blur or tilt, along with document-structure interpretation. For a scanned problem, ask for a transcription first and a solution second; this makes an incorrectly read sign or label visible before it changes the reasoning.
Three architecture updates support this visual and temporal work. Interleaved-MRoPE distributes positional information across time, width and height; DeepStack introduces visual features from several levels into the language model; explicit text timestamps represent the temporal position of video frame groups. Their practical relevance is preserving spatial detail and connecting an event description to a moment in the source. They do not turn a small or unreadable source detail into guaranteed recognition.
The exact Thinking model card gives generation recommendations separately for visual and text tasks. Both use sampling with temperature 1.0, top-p 0.95 and top-k 20; the visual example uses presence penalty 0.0, while the text example uses 1.5. Its example output-length settings are 40,960 for visual work and 32,768 for text, with 81,920 suggested for selected demanding text evaluations. These are tuning recommendations, not a universal maximum-output guarantee or parameters that a surrounding service necessarily exposes.
For a practical document task, supply ordered page images and ask: “Extract the section headings, explain the relationship between the diagram and the adjacent text, and attach a page reference to each finding.” For video, define the event you want located and request its timestamp plus a short visual explanation. For a visual reasoning question, state the required final artifact and the assumptions that may be used. The output remains a textual explanation, extracted content, code or proposed tool step; this edition’s visual input is not a video-generation or speech-generation workflow.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits Qwen/Qwen3-VL-8B-Thinking | 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 $0.000144 / 1K tokens Output · Output tokens $0.00143 / 1K tokens Input · Cache read $0 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "Qwen/Qwen3-VL-8B-Thinking",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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/Qwen3-VL-8B-Thinking', '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/Qwen3-VL-8B-Thinking', '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/Qwen3-VL-8B-Thinking
Use the method paths shown above.
Technical example in English
Reason about a written interface layout\n\nUse this textual layout description: a dialog contains a title at the top, a long message in the middle and Cancel/Confirm buttons at the bottom. On a short screen, only the message area should scroll; both buttons must stay visible. Propose HTML and CSS structure and explain the height constraints. Do not assume an image was supplied.An editable HTML/CSS proposal and a short explanation of which region scrolls.Check the proposed structure limits message overflow while keeping both actions outside that scroll area.