The February 15 Plus snapshot
Qwen3.5 Plus 2026-02-15 is the fixed February 15, 2026 release of Qwen’s native vision-language Plus family. Its documented architecture combines linear attention with sparse mixture-of-experts computation, supporting both text and multimodal tasks. Inputs include text, images and video; the response is text, such as an explanation, code proposal or document artifact. The dated name gives this edition a specific identity within the Plus family.
The manufacturer describes managed Qwen3.5-Plus as corresponding to the open Qwen3.5-397B-A17B model, with additional features including a default one-million-token context, built-in tools and adaptive tool use. The two offerings retain separate names and interface contracts. The open checkpoint’s exact expert counts, numerical representation and native context should not be silently converted into a complete specification for this dated Plus release.
Unified text and visual work
The Qwen3.5 family develops reasoning, coding, agents and visual understanding through early text–vision fusion and reinforcement learning on progressively complex tasks. Its family description includes 201 languages and dialects. For multilingual work, state the target language, audience and terms to preserve; for visual work, retain the labels, table headings or diagram definitions needed for the question.
A useful document request can ask for a comparison organized by the same sections as the source, with supporting passages for each finding. A coding request can combine a screenshot, the relevant existing code and functional requirements, then ask for editable source and a separate behavior explanation. For video, identify the event or sequence that matters and preserve timing. Check the returned passages, visual details and proposed code against the supplied material.
Reasoning and direct responses
The maker’s mode guide lists the Qwen3.5 Plus family and February 15 snapshot as hybrid thinking, with thinking enabled by default. The documented hybrid workflow can disable thinking for a direct response. Keep the reasoning distinct from the final artifact when the chosen interface provides both. Define a clear final form, such as a table of findings, a delimited answer or code files, so the result is easy to inspect.
The open Qwen3.5 checkpoint has its own history and sampling guidance. Later Qwen generations also introduce different reasoning-preservation defaults and controls. Follow the exact Plus interface recipe instead of assuming that a prompt marker, parameter container or history behavior carries across every edition with the Qwen name.
Tools and adaptive work
The producer’s Plus reference describes built-in and adaptive tool use. A task can let a connected workflow retrieve evidence, inspect provided material or return results of permitted operations. State the available tools, allowed actions and observable completion condition. The model can use actual feedback to revise its analysis and select the next step; the application performs external actions and supplies their results.
For an agent task, ask the final report to show the resulting artifact, supporting evidence and unresolved conditions. Distinguish a proposed patch or retrieval query from a tool result that was actually returned. A request for JSON-shaped text does not by itself establish a schema-enforcement contract, and a request to run code does not independently create an execution environment.
Long-context preparation
Qwen’s managed Plus reference describes a default one-million-token context. Keep document boundaries, code identifiers and definitions visible in a large input, and reserve space for reasoning and the final answer. Use the managed Plus context allowance for this workflow; the open 397B checkpoint has its own native and extended limits.
For a long comparison, narrow the question to the required decisions or relationships and ask the model to cite the supporting section for each conclusion. The context allowance can place more evidence together, but a clear source structure is what makes the answer traceable. Retain the dated edition name when reproducibility matters.
Practical result and limits
Use this snapshot for a concrete textual deliverable grounded in supplied project or visual material: an implementation proposal, a document comparison or an explained answer. Check small visual labels, calculations, quoted text and code changes against the original evidence. The documented model scope is text and visual understanding with textual output; it does not imply generated images, video or speech. Exact tools, upload rules and output allowances should follow the selected interface rather than an assumed equivalence with another checkpoint.
", "aboutText": "The February 15 Plus snapshot\n\nQwen3.5 Plus 2026-02-15 is the fixed February 15, 2026 release of Qwen’s native vision-language Plus family. Its documented architecture combines linear attention with sparse mixture-of-experts computation, supporting both text and multimodal tasks. Inputs include text, images and video; the response is text, such as an explanation, code proposal or document artifact. The dated name gives this edition a specific identity within the Plus family.\n\nThe manufacturer describes managed Qwen3.5-Plus as corresponding to the open Qwen3.5-397B-A17B model, with additional features including a default one-million-token context, built-in tools and adaptive tool use. The two offerings retain separate names and interface contracts. The open checkpoint’s exact expert counts, numerical representation and native context should not be silently converted into a complete specification for this dated Plus release.\n\nUnified text and visual work\n\nThe Qwen3.5 family develops reasoning, coding, agents and visual understanding through early text–vision fusion and reinforcement learning on progressively complex tasks. Its family description includes 201 languages and dialects. For multilingual work, state the target language, audience and terms to preserve; for visual work, retain the labels, table headings or diagram definitions needed for the question.\n\nA useful document request can ask for a comparison organized by the same sections as the source, with supporting passages for each finding. A coding request can combine a screenshot, the relevant existing code and functional requirements, then ask for editable source and a separate behavior explanation. For video, identify the event or sequence that matters and preserve timing. Check the returned passages, visual details and proposed code against the supplied material.\n\nReasoning and direct responses\n\nThe maker’s mode guide lists the Qwen3.5 Plus family and February 15 snapshot as hybrid thinking, with thinking enabled by default. The documented hybrid workflow can disable thinking for a direct response. Keep the reasoning distinct from the final artifact when the chosen interface provides both. Define a clear final form, such as a table of findings, a delimited answer or code files, so the result is easy to inspect.\n\nThe open Qwen3.5 checkpoint has its own history and sampling guidance. Later Qwen generations also introduce different reasoning-preservation defaults and controls. Follow the exact Plus interface recipe instead of assuming that a prompt marker, parameter container or history behavior carries across every edition with the Qwen name.\n\nTools and adaptive work\n\nThe producer’s Plus reference describes built-in and adaptive tool use. A task can let a connected workflow retrieve evidence, inspect provided material or return results of permitted operations. State the available tools, allowed actions and observable completion condition. The model can use actual feedback to revise its analysis and select the next step; the application performs external actions and supplies their results.\n\nFor an agent task, ask the final report to show the resulting artifact, supporting evidence and unresolved conditions. Distinguish a proposed patch or retrieval query from a tool result that was actually returned. A request for JSON-shaped text does not by itself establish a schema-enforcement contract, and a request to run code does not independently create an execution environment.\n\nLong-context preparation\n\nQwen’s managed Plus reference describes a default one-million-token context. Keep document boundaries, code identifiers and definitions visible in a large input, and reserve space for reasoning and the final answer. Use the managed Plus context allowance for this workflow; the open 397B checkpoint has its own native and extended limits.\n\nFor a long comparison, narrow the question to the required decisions or relationships and ask the model to cite the supporting section for each conclusion. The context allowance can place more evidence together, but a clear source structure is what makes the answer traceable. Retain the dated edition name when reproducibility matters.\n\nPractical result and limits\n\nUse this snapshot for a concrete textual deliverable grounded in supplied project or visual material: an implementation proposal, a document comparison or an explained answer. Check small visual labels, calculations, quoted text and code changes against the original evidence. The documented model scope is text and visual understanding with textual output; it does not imply generated images, video or speech. Exact tools, upload rules and output allowances should follow the selected interface rather than an assumed equivalence with another checkpoint.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Compare document retention clauses\n\nCompare sections A and B. A: 'Keep delivery logs for 30 days; retain disputed deliveries until resolution.' B: 'Delete every delivery log after 30 days.' Return the shared rule, the conflict and a revised B that preserves A's dispute exception. Cite the section label beside each finding and leave other retention categories unspecified.A section-linked comparison and a revised clause preserving the dispute condition.The revised clause must not delete an unresolved disputed-delivery log merely because 30 days passed.qwen/qwen3.5-plus-02-15Qwen3.5 Plus 2026-02-15 is the fixed February 15 snapshot of Qwen’s native vision-language Plus model. It combines text, image and video understanding with reasoning, coding and agent-oriented workflows, returning textual answers or artifacts in the family’s hybrid thinking mode.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
The February 15 Plus snapshot
Qwen3.5 Plus 2026-02-15 is the fixed February 15, 2026 release of Qwen’s native vision-language Plus family. Its documented architecture combines linear attention with sparse mixture-of-experts computation, supporting both text and multimodal tasks. Inputs include text, images and video; the response is text, such as an explanation, code proposal or document artifact. The dated name gives this edition a specific identity within the Plus family.
The manufacturer describes managed Qwen3.5-Plus as corresponding to the open Qwen3.5-397B-A17B model, with additional features including a default one-million-token context, built-in tools and adaptive tool use. The two offerings retain separate names and interface contracts. The open checkpoint’s exact expert counts, numerical representation and native context should not be silently converted into a complete specification for this dated Plus release.
Unified text and visual work
The Qwen3.5 family develops reasoning, coding, agents and visual understanding through early text–vision fusion and reinforcement learning on progressively complex tasks. Its family description includes 201 languages and dialects. For multilingual work, state the target language, audience and terms to preserve; for visual work, retain the labels, table headings or diagram definitions needed for the question.
A useful document request can ask for a comparison organized by the same sections as the source, with supporting passages for each finding. A coding request can combine a screenshot, the relevant existing code and functional requirements, then ask for editable source and a separate behavior explanation. For video, identify the event or sequence that matters and preserve timing. Check the returned passages, visual details and proposed code against the supplied material.
Reasoning and direct responses
The maker’s mode guide lists the Qwen3.5 Plus family and February 15 snapshot as hybrid thinking, with thinking enabled by default. The documented hybrid workflow can disable thinking for a direct response. Keep the reasoning distinct from the final artifact when the chosen interface provides both. Define a clear final form, such as a table of findings, a delimited answer or code files, so the result is easy to inspect.
The open Qwen3.5 checkpoint has its own history and sampling guidance. Later Qwen generations also introduce different reasoning-preservation defaults and controls. Follow the exact Plus interface recipe instead of assuming that a prompt marker, parameter container or history behavior carries across every edition with the Qwen name.
Tools and adaptive work
The producer’s Plus reference describes built-in and adaptive tool use. A task can let a connected workflow retrieve evidence, inspect provided material or return results of permitted operations. State the available tools, allowed actions and observable completion condition. The model can use actual feedback to revise its analysis and select the next step; the application performs external actions and supplies their results.
For an agent task, ask the final report to show the resulting artifact, supporting evidence and unresolved conditions. Distinguish a proposed patch or retrieval query from a tool result that was actually returned. A request for JSON-shaped text does not by itself establish a schema-enforcement contract, and a request to run code does not independently create an execution environment.
Long-context preparation
Qwen’s managed Plus reference describes a default one-million-token context. Keep document boundaries, code identifiers and definitions visible in a large input, and reserve space for reasoning and the final answer. Use the managed Plus context allowance for this workflow; the open 397B checkpoint has its own native and extended limits.
For a long comparison, narrow the question to the required decisions or relationships and ask the model to cite the supporting section for each conclusion. The context allowance can place more evidence together, but a clear source structure is what makes the answer traceable. Retain the dated edition name when reproducibility matters.
Practical result and limits
Use this snapshot for a concrete textual deliverable grounded in supplied project or visual material: an implementation proposal, a document comparison or an explained answer. Check small visual labels, calculations, quoted text and code changes against the original evidence. The documented model scope is text and visual understanding with textual output; it does not imply generated images, video or speech. Exact tools, upload rules and output allowances should follow the selected interface rather than an assumed equivalence with another checkpoint.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qwen/qwen3.5-plus-02-15 | 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 $0.00052 / 1K tokens Output · Output tokens $0.00312 / 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 including256,000 | Charge Input · Input tokens $0.00052 / 1K tokens Output · Output tokens $0.00312 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationRequest-length tier 2 | Rate schedule— | Context tokens, more than256,000 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.00065 / 1K tokens Output · Output tokens $0.0039 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "qwen/qwen3.5-plus-02-15", "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/qwen3.5-plus-02-15',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/qwen3.5-plus-02-15',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/qwen3.5-plus-02-15
Use the method paths shown above.
qwen/qwen3.5-plus-02-15Qwen3.5 Plus 2026-02-15 is the fixed February 15 snapshot of Qwen’s native vision-language Plus model. It combines text, image and video understanding with reasoning, coding and agent-oriented workflows, returning textual answers or artifacts in the family’s hybrid thinking mode.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
The February 15 Plus snapshot
Qwen3.5 Plus 2026-02-15 is the fixed February 15, 2026 release of Qwen’s native vision-language Plus family. Its documented architecture combines linear attention with sparse mixture-of-experts computation, supporting both text and multimodal tasks. Inputs include text, images and video; the response is text, such as an explanation, code proposal or document artifact. The dated name gives this edition a specific identity within the Plus family.
The manufacturer describes managed Qwen3.5-Plus as corresponding to the open Qwen3.5-397B-A17B model, with additional features including a default one-million-token context, built-in tools and adaptive tool use. The two offerings retain separate names and interface contracts. The open checkpoint’s exact expert counts, numerical representation and native context should not be silently converted into a complete specification for this dated Plus release.
Unified text and visual work
The Qwen3.5 family develops reasoning, coding, agents and visual understanding through early text–vision fusion and reinforcement learning on progressively complex tasks. Its family description includes 201 languages and dialects. For multilingual work, state the target language, audience and terms to preserve; for visual work, retain the labels, table headings or diagram definitions needed for the question.
A useful document request can ask for a comparison organized by the same sections as the source, with supporting passages for each finding. A coding request can combine a screenshot, the relevant existing code and functional requirements, then ask for editable source and a separate behavior explanation. For video, identify the event or sequence that matters and preserve timing. Check the returned passages, visual details and proposed code against the supplied material.
Reasoning and direct responses
The maker’s mode guide lists the Qwen3.5 Plus family and February 15 snapshot as hybrid thinking, with thinking enabled by default. The documented hybrid workflow can disable thinking for a direct response. Keep the reasoning distinct from the final artifact when the chosen interface provides both. Define a clear final form, such as a table of findings, a delimited answer or code files, so the result is easy to inspect.
The open Qwen3.5 checkpoint has its own history and sampling guidance. Later Qwen generations also introduce different reasoning-preservation defaults and controls. Follow the exact Plus interface recipe instead of assuming that a prompt marker, parameter container or history behavior carries across every edition with the Qwen name.
Tools and adaptive work
The producer’s Plus reference describes built-in and adaptive tool use. A task can let a connected workflow retrieve evidence, inspect provided material or return results of permitted operations. State the available tools, allowed actions and observable completion condition. The model can use actual feedback to revise its analysis and select the next step; the application performs external actions and supplies their results.
For an agent task, ask the final report to show the resulting artifact, supporting evidence and unresolved conditions. Distinguish a proposed patch or retrieval query from a tool result that was actually returned. A request for JSON-shaped text does not by itself establish a schema-enforcement contract, and a request to run code does not independently create an execution environment.
Long-context preparation
Qwen’s managed Plus reference describes a default one-million-token context. Keep document boundaries, code identifiers and definitions visible in a large input, and reserve space for reasoning and the final answer. Use the managed Plus context allowance for this workflow; the open 397B checkpoint has its own native and extended limits.
For a long comparison, narrow the question to the required decisions or relationships and ask the model to cite the supporting section for each conclusion. The context allowance can place more evidence together, but a clear source structure is what makes the answer traceable. Retain the dated edition name when reproducibility matters.
Practical result and limits
Use this snapshot for a concrete textual deliverable grounded in supplied project or visual material: an implementation proposal, a document comparison or an explained answer. Check small visual labels, calculations, quoted text and code changes against the original evidence. The documented model scope is text and visual understanding with textual output; it does not imply generated images, video or speech. Exact tools, upload rules and output allowances should follow the selected interface rather than an assumed equivalence with another checkpoint.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qwen/qwen3.5-plus-02-15 | 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 $0.00052 / 1K tokens Output · Output tokens $0.00312 / 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 including256,000 | Charge Input · Input tokens $0.00052 / 1K tokens Output · Output tokens $0.00312 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationRequest-length tier 2 | Rate schedule— | Context tokens, more than256,000 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.00065 / 1K tokens Output · Output tokens $0.0039 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "qwen/qwen3.5-plus-02-15",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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/qwen3.5-plus-02-15', '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/qwen3.5-plus-02-15', '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/qwen3.5-plus-02-15
Use the method paths shown above.
Technical example in English
Compare document retention clauses\n\nCompare sections A and B. A: 'Keep delivery logs for 30 days; retain disputed deliveries until resolution.' B: 'Delete every delivery log after 30 days.' Return the shared rule, the conflict and a revised B that preserves A's dispute exception. Cite the section label beside each finding and leave other retention categories unspecified.A section-linked comparison and a revised clause preserving the dispute condition.The revised clause must not delete an unresolved disputed-delivery log merely because 30 days passed.