Qwen3.6 highlights in a dense 27B model
Qwen3.6-27B is a dense vision-language model developed from Qwen3.5-27B. The maker highlights stronger coding agents and STEM reasoning, with improvements in spatial understanding, object localization and detection, document OCR, video understanding and visual agents. It accepts text, images and video and generates text. This exact dense edition is distinct from the Qwen3.6-35B-A3B mixture-of-experts model, even though they share a generation and task focus.
For a STEM diagram, provide the complete statement and preserve labels and units. Ask the model to separate directly visible facts from assumptions, then return an explanation with a clear final answer. For a document, specify the fields or claims to extract and request supporting page references. For a coding agent, provide the relevant modules, desired behavior and actual feedback from the connected workflow. These examples apply the documented capabilities; they are not claims of exact extraction or successful execution.
Model overview
The model has 27 billion parameters and 64 language-model layers. Its hybrid layout repeats three Gated DeltaNet layers followed by one gated-attention layer, using dense feed-forward networks rather than sparse experts. A vision encoder provides image and video understanding, and multi-token prediction is part of training. These architecture facts identify the checkpoint without ranking every application’s quality or response time.
The native context is 262,144 tokens and can be extended to 1,010,000 through configuration. Qwen advises maintaining at least a 128K context where possible for complex reasoning, while recognizing that memory pressure may require a smaller setting. Represented images and video, text, historical messages, thinking and the answer all consume space in the configured sequence.
Inputs and modes
The maker shows text, image and video questions. Thinking is enabled by default, with a reasoning block before the final response. enable_thinking can disable that behavior for a direct answer. Qwen3.6 does not officially support the older /think and /nothink prompt switches. Keep the required result easy to identify after the explanation, such as a computed value, a table of extracted fields or an editable code patch.
The video example uses two frames per second by default in its supported workflow. For hour-scale video, the maker recommends increasing the processor budget to allow higher-rate sampling, giving an example corresponding to roughly 224K video tokens. More visual detail needs more of the context and processing budget. Those settings do not establish an unconditional video duration or exact event-timestamp accuracy for every interface.
Historical thinking
The default template retains thinking associated with the latest user message. The preserve_thinking option can additionally retain reasoning from historical messages; the maker’s explicit example enables it with true. This can support iterative development where earlier decisions remain relevant after new tool feedback. It differs from Qwen3.8’s documented default preservation behavior and from Qwen3.5’s final-answer-only history guidance. Follow the exact checkpoint format rather than silently substitute another generation’s history rules.
Agentic usage
Qwen documents tool calling and recommends Qwen-Agent with configured or MCP-connected tools, alongside Qwen Code for coding-agent work. State the permitted actions and observable completion criteria. A tool can inspect supplied material or return a real check result, after which the model can revise its analysis. The model does not gain access to a filesystem, current sources or an execution environment simply from its agent specialization.
Ultra-long input
The extension recipe uses YaRN with this model’s interleaved positional settings. A factor of four targets the roughly one-million-token workflow; a factor of two is suggested for 524,288-token workloads. Static scaling can lower shorter-text performance, so it should follow the actual need for long context. Keep pages, functions and document boundaries labeled, then request conclusions that identify the supporting evidence.
Generation recommendations and limits
The card’s Best Practices recommend temperature 1.0, top_p 0.95, top_k 20, min_p 0, presence penalty 0 and repetition penalty 1.0 for general thinking. For precise coding, temperature becomes 0.6. For direct responses, temperature is 0.7, top_p 0.8 and presence penalty 1.5, with the other values unchanged. The maker warns that larger presence penalties can mix languages or slightly reduce quality.
Recommended generation allowances are 32,768 tokens for most questions and 81,920 for unusually difficult math or programming work. They are not separately established hard ceilings. Define a final-answer format and check extracted text, spatial conclusions, calculations and proposed code against the source. A large context and retained reasoning help carry evidence through the task; the reviewable artifact remains the useful result.
", "aboutText": "Qwen3.6 highlights in a dense 27B model\n\nQwen3.6-27B is a dense vision-language model developed from Qwen3.5-27B. The maker highlights stronger coding agents and STEM reasoning, with improvements in spatial understanding, object localization and detection, document OCR, video understanding and visual agents. It accepts text, images and video and generates text. This exact dense edition is distinct from the Qwen3.6-35B-A3B mixture-of-experts model, even though they share a generation and task focus.\n\nFor a STEM diagram, provide the complete statement and preserve labels and units. Ask the model to separate directly visible facts from assumptions, then return an explanation with a clear final answer. For a document, specify the fields or claims to extract and request supporting page references. For a coding agent, provide the relevant modules, desired behavior and actual feedback from the connected workflow. These examples apply the documented capabilities; they are not claims of exact extraction or successful execution.\n\nModel overview\n\nThe model has 27 billion parameters and 64 language-model layers. Its hybrid layout repeats three Gated DeltaNet layers followed by one gated-attention layer, using dense feed-forward networks rather than sparse experts. A vision encoder provides image and video understanding, and multi-token prediction is part of training. These architecture facts identify the checkpoint without ranking every application’s quality or response time.\n\nThe native context is 262,144 tokens and can be extended to 1,010,000 through configuration. Qwen advises maintaining at least a 128K context where possible for complex reasoning, while recognizing that memory pressure may require a smaller setting. Represented images and video, text, historical messages, thinking and the answer all consume space in the configured sequence.\n\nInputs and modes\n\nThe maker shows text, image and video questions. Thinking is enabled by default, with a reasoning block before the final response. enable_thinking can disable that behavior for a direct answer. Qwen3.6 does not officially support the older /think and /nothink prompt switches. Keep the required result easy to identify after the explanation, such as a computed value, a table of extracted fields or an editable code patch.\n\nThe video example uses two frames per second by default in its supported workflow. For hour-scale video, the maker recommends increasing the processor budget to allow higher-rate sampling, giving an example corresponding to roughly 224K video tokens. More visual detail needs more of the context and processing budget. Those settings do not establish an unconditional video duration or exact event-timestamp accuracy for every interface.\n\nHistorical thinking\n\nThe default template retains thinking associated with the latest user message. The preserve_thinking option can additionally retain reasoning from historical messages; the maker’s explicit example enables it with true. This can support iterative development where earlier decisions remain relevant after new tool feedback. It differs from Qwen3.8’s documented default preservation behavior and from Qwen3.5’s final-answer-only history guidance. Follow the exact checkpoint format rather than silently substitute another generation’s history rules.\n\nAgentic usage\n\nQwen documents tool calling and recommends Qwen-Agent with configured or MCP-connected tools, alongside Qwen Code for coding-agent work. State the permitted actions and observable completion criteria. A tool can inspect supplied material or return a real check result, after which the model can revise its analysis. The model does not gain access to a filesystem, current sources or an execution environment simply from its agent specialization.\n\nUltra-long input\n\nThe extension recipe uses YaRN with this model’s interleaved positional settings. A factor of four targets the roughly one-million-token workflow; a factor of two is suggested for 524,288-token workloads. Static scaling can lower shorter-text performance, so it should follow the actual need for long context. Keep pages, functions and document boundaries labeled, then request conclusions that identify the supporting evidence.\n\nGeneration recommendations and limits\n\nThe card’s Best Practices recommend temperature 1.0, top_p 0.95, top_k 20, min_p 0, presence penalty 0 and repetition penalty 1.0 for general thinking. For precise coding, temperature becomes 0.6. For direct responses, temperature is 0.7, top_p 0.8 and presence penalty 1.5, with the other values unchanged. The maker warns that larger presence penalties can mix languages or slightly reduce quality.\n\nRecommended generation allowances are 32,768 tokens for most questions and 81,920 for unusually difficult math or programming work. They are not separately established hard ceilings. Define a final-answer format and check extracted text, spatial conclusions, calculations and proposed code against the source. A large context and retained reasoning help carry evidence through the task; the reviewable artifact remains the useful result.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Calculate a series-circuit result\n\nA circuit is described in text: an ideal 12 V source is connected to two resistors, 3 Ω and 5 Ω, in series. Wires have zero resistance. Calculate total resistance, current and voltage across each resistor. Show formulas with units and check that the two voltage drops equal the source voltage.A worked solution with total resistance, shared current, both voltage drops and a voltage-sum check.Check that the same current flows through both series resistors and the computed voltage drops sum to 12 V.qwen/qwen3.6-27bQwen3.6-27B is Qwen’s dense vision-language model for coding, STEM reasoning and visual analysis. It accepts text, images and video and returns text, with selectable thinking, optional historical reasoning preservation 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.
Qwen3.6 highlights in a dense 27B model
Qwen3.6-27B is a dense vision-language model developed from Qwen3.5-27B. The maker highlights stronger coding agents and STEM reasoning, with improvements in spatial understanding, object localization and detection, document OCR, video understanding and visual agents. It accepts text, images and video and generates text. This exact dense edition is distinct from the Qwen3.6-35B-A3B mixture-of-experts model, even though they share a generation and task focus.
For a STEM diagram, provide the complete statement and preserve labels and units. Ask the model to separate directly visible facts from assumptions, then return an explanation with a clear final answer. For a document, specify the fields or claims to extract and request supporting page references. For a coding agent, provide the relevant modules, desired behavior and actual feedback from the connected workflow. These examples apply the documented capabilities; they are not claims of exact extraction or successful execution.
Model overview
The model has 27 billion parameters and 64 language-model layers. Its hybrid layout repeats three Gated DeltaNet layers followed by one gated-attention layer, using dense feed-forward networks rather than sparse experts. A vision encoder provides image and video understanding, and multi-token prediction is part of training. These architecture facts identify the checkpoint without ranking every application’s quality or response time.
The native context is 262,144 tokens and can be extended to 1,010,000 through configuration. Qwen advises maintaining at least a 128K context where possible for complex reasoning, while recognizing that memory pressure may require a smaller setting. Represented images and video, text, historical messages, thinking and the answer all consume space in the configured sequence.
Inputs and modes
The maker shows text, image and video questions. Thinking is enabled by default, with a reasoning block before the final response. enable_thinking can disable that behavior for a direct answer. Qwen3.6 does not officially support the older /think and /nothink prompt switches. Keep the required result easy to identify after the explanation, such as a computed value, a table of extracted fields or an editable code patch.
The video example uses two frames per second by default in its supported workflow. For hour-scale video, the maker recommends increasing the processor budget to allow higher-rate sampling, giving an example corresponding to roughly 224K video tokens. More visual detail needs more of the context and processing budget. Those settings do not establish an unconditional video duration or exact event-timestamp accuracy for every interface.
Historical thinking
The default template retains thinking associated with the latest user message. The preserve_thinking option can additionally retain reasoning from historical messages; the maker’s explicit example enables it with true. This can support iterative development where earlier decisions remain relevant after new tool feedback. It differs from Qwen3.8’s documented default preservation behavior and from Qwen3.5’s final-answer-only history guidance. Follow the exact checkpoint format rather than silently substitute another generation’s history rules.
Agentic usage
Qwen documents tool calling and recommends Qwen-Agent with configured or MCP-connected tools, alongside Qwen Code for coding-agent work. State the permitted actions and observable completion criteria. A tool can inspect supplied material or return a real check result, after which the model can revise its analysis. The model does not gain access to a filesystem, current sources or an execution environment simply from its agent specialization.
Ultra-long input
The extension recipe uses YaRN with this model’s interleaved positional settings. A factor of four targets the roughly one-million-token workflow; a factor of two is suggested for 524,288-token workloads. Static scaling can lower shorter-text performance, so it should follow the actual need for long context. Keep pages, functions and document boundaries labeled, then request conclusions that identify the supporting evidence.
Generation recommendations and limits
The card’s Best Practices recommend temperature 1.0, top_p 0.95, top_k 20, min_p 0, presence penalty 0 and repetition penalty 1.0 for general thinking. For precise coding, temperature becomes 0.6. For direct responses, temperature is 0.7, top_p 0.8 and presence penalty 1.5, with the other values unchanged. The maker warns that larger presence penalties can mix languages or slightly reduce quality.
Recommended generation allowances are 32,768 tokens for most questions and 81,920 for unusually difficult math or programming work. They are not separately established hard ceilings. Define a final-answer format and check extracted text, spatial conclusions, calculations and proposed code against the source. A large context and retained reasoning help carry evidence through the task; the reviewable artifact remains the useful result.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qwen/qwen3.6-27b | 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 $0.0009 / 1K tokens Output · Output tokens $0.0054 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 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 $0.0009 / 1K tokens Output · Output tokens $0.0054 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "qwen/qwen3.6-27b", "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/qwen3.6-27b',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/qwen3.6-27b',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/qwen3.6-27b
Use the method paths shown above.
qwen/qwen3.6-27bQwen3.6-27B is Qwen’s dense vision-language model for coding, STEM reasoning and visual analysis. It accepts text, images and video and returns text, with selectable thinking, optional historical reasoning preservation 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.
Qwen3.6 highlights in a dense 27B model
Qwen3.6-27B is a dense vision-language model developed from Qwen3.5-27B. The maker highlights stronger coding agents and STEM reasoning, with improvements in spatial understanding, object localization and detection, document OCR, video understanding and visual agents. It accepts text, images and video and generates text. This exact dense edition is distinct from the Qwen3.6-35B-A3B mixture-of-experts model, even though they share a generation and task focus.
For a STEM diagram, provide the complete statement and preserve labels and units. Ask the model to separate directly visible facts from assumptions, then return an explanation with a clear final answer. For a document, specify the fields or claims to extract and request supporting page references. For a coding agent, provide the relevant modules, desired behavior and actual feedback from the connected workflow. These examples apply the documented capabilities; they are not claims of exact extraction or successful execution.
Model overview
The model has 27 billion parameters and 64 language-model layers. Its hybrid layout repeats three Gated DeltaNet layers followed by one gated-attention layer, using dense feed-forward networks rather than sparse experts. A vision encoder provides image and video understanding, and multi-token prediction is part of training. These architecture facts identify the checkpoint without ranking every application’s quality or response time.
The native context is 262,144 tokens and can be extended to 1,010,000 through configuration. Qwen advises maintaining at least a 128K context where possible for complex reasoning, while recognizing that memory pressure may require a smaller setting. Represented images and video, text, historical messages, thinking and the answer all consume space in the configured sequence.
Inputs and modes
The maker shows text, image and video questions. Thinking is enabled by default, with a reasoning block before the final response. enable_thinking can disable that behavior for a direct answer. Qwen3.6 does not officially support the older /think and /nothink prompt switches. Keep the required result easy to identify after the explanation, such as a computed value, a table of extracted fields or an editable code patch.
The video example uses two frames per second by default in its supported workflow. For hour-scale video, the maker recommends increasing the processor budget to allow higher-rate sampling, giving an example corresponding to roughly 224K video tokens. More visual detail needs more of the context and processing budget. Those settings do not establish an unconditional video duration or exact event-timestamp accuracy for every interface.
Historical thinking
The default template retains thinking associated with the latest user message. The preserve_thinking option can additionally retain reasoning from historical messages; the maker’s explicit example enables it with true. This can support iterative development where earlier decisions remain relevant after new tool feedback. It differs from Qwen3.8’s documented default preservation behavior and from Qwen3.5’s final-answer-only history guidance. Follow the exact checkpoint format rather than silently substitute another generation’s history rules.
Agentic usage
Qwen documents tool calling and recommends Qwen-Agent with configured or MCP-connected tools, alongside Qwen Code for coding-agent work. State the permitted actions and observable completion criteria. A tool can inspect supplied material or return a real check result, after which the model can revise its analysis. The model does not gain access to a filesystem, current sources or an execution environment simply from its agent specialization.
Ultra-long input
The extension recipe uses YaRN with this model’s interleaved positional settings. A factor of four targets the roughly one-million-token workflow; a factor of two is suggested for 524,288-token workloads. Static scaling can lower shorter-text performance, so it should follow the actual need for long context. Keep pages, functions and document boundaries labeled, then request conclusions that identify the supporting evidence.
Generation recommendations and limits
The card’s Best Practices recommend temperature 1.0, top_p 0.95, top_k 20, min_p 0, presence penalty 0 and repetition penalty 1.0 for general thinking. For precise coding, temperature becomes 0.6. For direct responses, temperature is 0.7, top_p 0.8 and presence penalty 1.5, with the other values unchanged. The maker warns that larger presence penalties can mix languages or slightly reduce quality.
Recommended generation allowances are 32,768 tokens for most questions and 81,920 for unusually difficult math or programming work. They are not separately established hard ceilings. Define a final-answer format and check extracted text, spatial conclusions, calculations and proposed code against the source. A large context and retained reasoning help carry evidence through the task; the reviewable artifact remains the useful result.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qwen/qwen3.6-27b | 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 $0.0009 / 1K tokens Output · Output tokens $0.0054 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 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 $0.0009 / 1K tokens Output · Output tokens $0.0054 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "qwen/qwen3.6-27b",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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/qwen3.6-27b', '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/qwen3.6-27b', '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/qwen3.6-27b
Use the method paths shown above.
Technical example in English
Calculate a series-circuit result\n\nA circuit is described in text: an ideal 12 V source is connected to two resistors, 3 Ω and 5 Ω, in series. Wires have zero resistance. Calculate total resistance, current and voltage across each resistor. Show formulas with units and check that the two voltage drops equal the source voltage.A worked solution with total resistance, shared current, both voltage drops and a voltage-sum check.Check that the same current flows through both series resistors and the computed voltage drops sum to 12 V.