The 235B-A22B Instruct edition
Qwen3-VL-235B-A22B-Instruct is the instruction-focused mixture-of-experts member of Qwen3-VL. It accepts text, images and video and generates text, including code or a requested document artifact. Preserve the exact Instruct edition rather than assign it a Thinking checkpoint’s response contract or another size’s recipe. A useful task gives the model a concrete question and a result that can be compared with the supplied evidence.
Visual agents and coding
The maker describes visual-agent workflows that recognize interface elements, understand their functions and invoke tools for computer or mobile tasks. Provide a screenshot and a goal, then ask for the relevant control and the evidence supporting the choice. The connected application performs actions and supplies results; recognizing an interface does not itself control a device.
Visual coding includes diagram content and HTML, CSS or JavaScript produced from images or video. Supply the layout reference, functional constraints and required editable output. For a change to an existing page, include the relevant source and interaction states. Request the artifact separately from the explanation so it can be rendered and reviewed by a development workflow. Generated source remains a proposal, not proof of a working application.
Spatial perception and long material
Qwen documents judgments about positions, viewpoints and occlusions, including two-dimensional grounding and support for three-dimensional grounding. Identify the objects and relationship that matter, then ask which visible cues support the conclusion. An image-based relationship should not be treated as a calibrated physical measurement.
The native context is 262,144 tokens. The family describes books and hours-long video, with second-level event indexing and extension to approximately one million tokens through configuration. Preserve timing and source identifiers when requesting an event account. Representation and sampling determine what material enters the request; a large context is not a guarantee of perfect recall of every page or frame.
Reasoning, recognition and OCR
The family supports STEM, mathematical, causal and logical visual questions. Give the full statement and diagram labels, and ask the model to identify the values or relationships used before the conclusion. Text and vision are combined, so one question can connect a paragraph with its figure and the user’s instructions.
Recognition extends across people, products, landmarks, plants, animals and media characters. OCR covers 32 languages and targets low light, blur and tilt, including specialist vocabulary and long-document structure. Supply readable pages and request named fields, quotations or a table that can be checked against the image. These applications reflect the documented scope rather than guarantee exact identification, transcription or calculation.
Architecture updates
The published mixture-of-experts text configuration has 94 layers, 128 experts and eight experts selected per token. Interleaved-MRoPE represents time, width and height for video reasoning. DeepStack combines visual features from multiple encoder levels, and text–timestamp alignment grounds events in temporal references. Use this 235B-A22B Instruct edition consistently when preparing visual tasks and comparing their results.
Preparing visual inputs
The family examples cover text-only requests, single or multiple images and video. Label visual inputs and state how they relate. Image and video pixel budgets are separate, while explicit image dimensions are aligned to multiples of 32. The documented video default is two frames per second, with rate or frame-count controls where supported. Preserve video metadata and avoid resizing twice when the helper has already resized the material.
For several document pages, organize the answer by page label and ask for supporting fields or passages. For a clip, request the relevant event, interval and visible evidence. Compare the returned event interval and supporting details with the original clip and its timing.
Generation guidance and limits
The checkpoint generation file defaults to temperature 0.7, top_p 0.8, top_k 20 and repetition penalty 1.0. The family’s Instruct recipe additionally uses presence penalty 1.5 and a 32,768-token output allowance. That allowance is a producer recipe budget, not an independently established hard output ceiling. The 8B card’s task-specific allowances and the Thinking edition’s presets remain separate.
The family’s context extension uses YaRN and suggests a factor of two or three when moving its interleaved positional scheme from 256K to about 1M. Reserve answer space alongside text and represented visuals, and verify quotations, extracted numbers and generated code against the source. The useful result is a concrete textual artifact with its supporting visual evidence and exact Instruct identity preserved.
", "aboutText": "The 235B-A22B Instruct edition\n\nQwen3-VL-235B-A22B-Instruct is the instruction-focused mixture-of-experts member of Qwen3-VL. It accepts text, images and video and generates text, including code or a requested document artifact. Preserve the exact Instruct edition rather than assign it a Thinking checkpoint’s response contract or another size’s recipe. A useful task gives the model a concrete question and a result that can be compared with the supplied evidence.\n\nVisual agents and coding\n\nThe maker describes visual-agent workflows that recognize interface elements, understand their functions and invoke tools for computer or mobile tasks. Provide a screenshot and a goal, then ask for the relevant control and the evidence supporting the choice. The connected application performs actions and supplies results; recognizing an interface does not itself control a device.\n\nVisual coding includes diagram content and HTML, CSS or JavaScript produced from images or video. Supply the layout reference, functional constraints and required editable output. For a change to an existing page, include the relevant source and interaction states. Request the artifact separately from the explanation so it can be rendered and reviewed by a development workflow. Generated source remains a proposal, not proof of a working application.\n\nSpatial perception and long material\n\nQwen documents judgments about positions, viewpoints and occlusions, including two-dimensional grounding and support for three-dimensional grounding. Identify the objects and relationship that matter, then ask which visible cues support the conclusion. An image-based relationship should not be treated as a calibrated physical measurement.\n\nThe native context is 262,144 tokens. The family describes books and hours-long video, with second-level event indexing and extension to approximately one million tokens through configuration. Preserve timing and source identifiers when requesting an event account. Representation and sampling determine what material enters the request; a large context is not a guarantee of perfect recall of every page or frame.\n\nReasoning, recognition and OCR\n\nThe family supports STEM, mathematical, causal and logical visual questions. Give the full statement and diagram labels, and ask the model to identify the values or relationships used before the conclusion. Text and vision are combined, so one question can connect a paragraph with its figure and the user’s instructions.\n\nRecognition extends across people, products, landmarks, plants, animals and media characters. OCR covers 32 languages and targets low light, blur and tilt, including specialist vocabulary and long-document structure. Supply readable pages and request named fields, quotations or a table that can be checked against the image. These applications reflect the documented scope rather than guarantee exact identification, transcription or calculation.\n\nArchitecture updates\n\nThe published mixture-of-experts text configuration has 94 layers, 128 experts and eight experts selected per token. Interleaved-MRoPE represents time, width and height for video reasoning. DeepStack combines visual features from multiple encoder levels, and text–timestamp alignment grounds events in temporal references. Use this 235B-A22B Instruct edition consistently when preparing visual tasks and comparing their results.\n\nPreparing visual inputs\n\nThe family examples cover text-only requests, single or multiple images and video. Label visual inputs and state how they relate. Image and video pixel budgets are separate, while explicit image dimensions are aligned to multiples of 32. The documented video default is two frames per second, with rate or frame-count controls where supported. Preserve video metadata and avoid resizing twice when the helper has already resized the material.\n\nFor several document pages, organize the answer by page label and ask for supporting fields or passages. For a clip, request the relevant event, interval and visible evidence. Compare the returned event interval and supporting details with the original clip and its timing.\n\nGeneration guidance and limits\n\nThe checkpoint generation file defaults to temperature 0.7, top_p 0.8, top_k 20 and repetition penalty 1.0. The family’s Instruct recipe additionally uses presence penalty 1.5 and a 32,768-token output allowance. That allowance is a producer recipe budget, not an independently established hard output ceiling. The 8B card’s task-specific allowances and the Thinking edition’s presets remain separate.\n\nThe family’s context extension uses YaRN and suggests a factor of two or three when moving its interleaved positional scheme from 256K to about 1M. Reserve answer space alongside text and represented visuals, and verify quotations, extracted numbers and generated code against the source. The useful result is a concrete textual artifact with its supporting visual evidence and exact Instruct identity preserved.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Translate a layout description to HTML\n\nCreate a semantic HTML fragment from this text layout specification: a product section contains heading "Travel mug", a paragraph "350 ml, steel", and a list of features "Sealed lid" and "Hand wash". Return editable HTML only, with no scripts or styles. Preserve exact wording and use a heading, paragraph and unordered list.One semantic HTML fragment using the requested heading, paragraph and two-item list.Inspect the element hierarchy and exact text; do not add a product image or unprovided features.qwen/qwen3-vl-235b-a22b-instructQwen3-VL-235B-A22B-Instruct is Qwen’s instruction-focused mixture-of-experts vision-language edition for text, images and video. It returns text or code for visual workflows, documents, spatial questions and STEM tasks, with 32-language OCR and a native 262,144-token context.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
The 235B-A22B Instruct edition
Qwen3-VL-235B-A22B-Instruct is the instruction-focused mixture-of-experts member of Qwen3-VL. It accepts text, images and video and generates text, including code or a requested document artifact. Preserve the exact Instruct edition rather than assign it a Thinking checkpoint’s response contract or another size’s recipe. A useful task gives the model a concrete question and a result that can be compared with the supplied evidence.
Visual agents and coding
The maker describes visual-agent workflows that recognize interface elements, understand their functions and invoke tools for computer or mobile tasks. Provide a screenshot and a goal, then ask for the relevant control and the evidence supporting the choice. The connected application performs actions and supplies results; recognizing an interface does not itself control a device.
Visual coding includes diagram content and HTML, CSS or JavaScript produced from images or video. Supply the layout reference, functional constraints and required editable output. For a change to an existing page, include the relevant source and interaction states. Request the artifact separately from the explanation so it can be rendered and reviewed by a development workflow. Generated source remains a proposal, not proof of a working application.
Spatial perception and long material
Qwen documents judgments about positions, viewpoints and occlusions, including two-dimensional grounding and support for three-dimensional grounding. Identify the objects and relationship that matter, then ask which visible cues support the conclusion. An image-based relationship should not be treated as a calibrated physical measurement.
The native context is 262,144 tokens. The family describes books and hours-long video, with second-level event indexing and extension to approximately one million tokens through configuration. Preserve timing and source identifiers when requesting an event account. Representation and sampling determine what material enters the request; a large context is not a guarantee of perfect recall of every page or frame.
Reasoning, recognition and OCR
The family supports STEM, mathematical, causal and logical visual questions. Give the full statement and diagram labels, and ask the model to identify the values or relationships used before the conclusion. Text and vision are combined, so one question can connect a paragraph with its figure and the user’s instructions.
Recognition extends across people, products, landmarks, plants, animals and media characters. OCR covers 32 languages and targets low light, blur and tilt, including specialist vocabulary and long-document structure. Supply readable pages and request named fields, quotations or a table that can be checked against the image. These applications reflect the documented scope rather than guarantee exact identification, transcription or calculation.
Architecture updates
The published mixture-of-experts text configuration has 94 layers, 128 experts and eight experts selected per token. Interleaved-MRoPE represents time, width and height for video reasoning. DeepStack combines visual features from multiple encoder levels, and text–timestamp alignment grounds events in temporal references. Use this 235B-A22B Instruct edition consistently when preparing visual tasks and comparing their results.
Preparing visual inputs
The family examples cover text-only requests, single or multiple images and video. Label visual inputs and state how they relate. Image and video pixel budgets are separate, while explicit image dimensions are aligned to multiples of 32. The documented video default is two frames per second, with rate or frame-count controls where supported. Preserve video metadata and avoid resizing twice when the helper has already resized the material.
For several document pages, organize the answer by page label and ask for supporting fields or passages. For a clip, request the relevant event, interval and visible evidence. Compare the returned event interval and supporting details with the original clip and its timing.
Generation guidance and limits
The checkpoint generation file defaults to temperature 0.7, top_p 0.8, top_k 20 and repetition penalty 1.0. The family’s Instruct recipe additionally uses presence penalty 1.5 and a 32,768-token output allowance. That allowance is a producer recipe budget, not an independently established hard output ceiling. The 8B card’s task-specific allowances and the Thinking edition’s presets remain separate.
The family’s context extension uses YaRN and suggests a factor of two or three when moving its interleaved positional scheme from 256K to about 1M. Reserve answer space alongside text and represented visuals, and verify quotations, extracted numbers and generated code against the source. The useful result is a concrete textual artifact with its supporting visual evidence and exact Instruct identity preserved.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qwen/qwen3-vl-235b-a22b-instruct | 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.
Match each charge to the conditions shown. Use one rate for each set of alternative configurations.
| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
|---|---|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.000572 / 1K tokens Output · Output tokens $0.0038 / 1K tokens Input · Cache read $0.0002 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationRequest-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.000572 / 1K tokens Output · Output tokens $0.0038 / 1K tokens Input · Cache read $0.0002 / 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-235b-a22b-instruct", "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-235b-a22b-instruct',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-235b-a22b-instruct',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-235b-a22b-instruct
Use the method paths shown above.
qwen/qwen3-vl-235b-a22b-instructQwen3-VL-235B-A22B-Instruct is Qwen’s instruction-focused mixture-of-experts vision-language edition for text, images and video. It returns text or code for visual workflows, documents, spatial questions and STEM tasks, with 32-language OCR and a native 262,144-token context.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
The 235B-A22B Instruct edition
Qwen3-VL-235B-A22B-Instruct is the instruction-focused mixture-of-experts member of Qwen3-VL. It accepts text, images and video and generates text, including code or a requested document artifact. Preserve the exact Instruct edition rather than assign it a Thinking checkpoint’s response contract or another size’s recipe. A useful task gives the model a concrete question and a result that can be compared with the supplied evidence.
Visual agents and coding
The maker describes visual-agent workflows that recognize interface elements, understand their functions and invoke tools for computer or mobile tasks. Provide a screenshot and a goal, then ask for the relevant control and the evidence supporting the choice. The connected application performs actions and supplies results; recognizing an interface does not itself control a device.
Visual coding includes diagram content and HTML, CSS or JavaScript produced from images or video. Supply the layout reference, functional constraints and required editable output. For a change to an existing page, include the relevant source and interaction states. Request the artifact separately from the explanation so it can be rendered and reviewed by a development workflow. Generated source remains a proposal, not proof of a working application.
Spatial perception and long material
Qwen documents judgments about positions, viewpoints and occlusions, including two-dimensional grounding and support for three-dimensional grounding. Identify the objects and relationship that matter, then ask which visible cues support the conclusion. An image-based relationship should not be treated as a calibrated physical measurement.
The native context is 262,144 tokens. The family describes books and hours-long video, with second-level event indexing and extension to approximately one million tokens through configuration. Preserve timing and source identifiers when requesting an event account. Representation and sampling determine what material enters the request; a large context is not a guarantee of perfect recall of every page or frame.
Reasoning, recognition and OCR
The family supports STEM, mathematical, causal and logical visual questions. Give the full statement and diagram labels, and ask the model to identify the values or relationships used before the conclusion. Text and vision are combined, so one question can connect a paragraph with its figure and the user’s instructions.
Recognition extends across people, products, landmarks, plants, animals and media characters. OCR covers 32 languages and targets low light, blur and tilt, including specialist vocabulary and long-document structure. Supply readable pages and request named fields, quotations or a table that can be checked against the image. These applications reflect the documented scope rather than guarantee exact identification, transcription or calculation.
Architecture updates
The published mixture-of-experts text configuration has 94 layers, 128 experts and eight experts selected per token. Interleaved-MRoPE represents time, width and height for video reasoning. DeepStack combines visual features from multiple encoder levels, and text–timestamp alignment grounds events in temporal references. Use this 235B-A22B Instruct edition consistently when preparing visual tasks and comparing their results.
Preparing visual inputs
The family examples cover text-only requests, single or multiple images and video. Label visual inputs and state how they relate. Image and video pixel budgets are separate, while explicit image dimensions are aligned to multiples of 32. The documented video default is two frames per second, with rate or frame-count controls where supported. Preserve video metadata and avoid resizing twice when the helper has already resized the material.
For several document pages, organize the answer by page label and ask for supporting fields or passages. For a clip, request the relevant event, interval and visible evidence. Compare the returned event interval and supporting details with the original clip and its timing.
Generation guidance and limits
The checkpoint generation file defaults to temperature 0.7, top_p 0.8, top_k 20 and repetition penalty 1.0. The family’s Instruct recipe additionally uses presence penalty 1.5 and a 32,768-token output allowance. That allowance is a producer recipe budget, not an independently established hard output ceiling. The 8B card’s task-specific allowances and the Thinking edition’s presets remain separate.
The family’s context extension uses YaRN and suggests a factor of two or three when moving its interleaved positional scheme from 256K to about 1M. Reserve answer space alongside text and represented visuals, and verify quotations, extracted numbers and generated code against the source. The useful result is a concrete textual artifact with its supporting visual evidence and exact Instruct identity preserved.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qwen/qwen3-vl-235b-a22b-instruct | 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.
Match each charge to the conditions shown. Use one rate for each set of alternative configurations.
| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
|---|---|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.000572 / 1K tokens Output · Output tokens $0.0038 / 1K tokens Input · Cache read $0.0002 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationRequest-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.000572 / 1K tokens Output · Output tokens $0.0038 / 1K tokens Input · Cache read $0.0002 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "qwen/qwen3-vl-235b-a22b-instruct",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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-235b-a22b-instruct', '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-235b-a22b-instruct', '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-235b-a22b-instruct
Use the method paths shown above.
Technical example in English
Translate a layout description to HTML\n\nCreate a semantic HTML fragment from this text layout specification: a product section contains heading "Travel mug", a paragraph "350 ml, steel", and a list of features "Sealed lid" and "Hand wash". Return editable HTML only, with no scripts or styles. Preserve exact wording and use a heading, paragraph and unordered list.One semantic HTML fragment using the requested heading, paragraph and two-item list.Inspect the element hierarchy and exact text; do not add a product image or unprovided features.