The fixed April 20 Plus snapshot
Qwen3.5 Plus 2026-04-20 is the April 20, 2026 snapshot of Qwen’s native vision-language Plus family. The maker’s release notice identifies a substantial improvement in agentic coding compared with the February 15 snapshot, alongside stronger inference efficiency and retained knowledge, reasoning and long-context capabilities. Keep this dated edition distinct from a moving Plus name and from the open Qwen3.5-397B-A17B checkpoint.
The family accepts text with images or video and produces textual results. That scope supports a development task informed by a screenshot, a question about a technical diagram or a document-based explanation. The snapshot name does not by itself establish the open checkpoint’s parameter count, activated experts or exact architecture, so those figures are not assigned to this edition here.
Agentic coding
The release’s main change is more capable coding in an agent workflow. Supply the project requirements, relevant files or excerpts, existing behavior and the artifact expected at completion. For a screenshot-to-interface task, include the visual reference and functional constraints, then request editable source and an explanation of the intended behavior. For a repository change, identify the affected feature and the input demonstrating the issue, then ask for a patch and the checks needed to assess it.
A multi-step coding workflow benefits from actual feedback: inspection results, observed errors and review findings can be returned to the model as the work progresses. The application controls the tools and executes permitted actions. Ask for a report of what was proposed, what was observed and what remains unresolved.
Knowledge and reasoning
The maker says the snapshot retains strong knowledge and reasoning while improving agent work. For an analytical task, separate the source facts from assumptions and specify the conclusion being sought. Request supporting passages, values or code identifiers so the result can be checked. For a professional report, provide the relevant material and desired sections rather than rely on the model to know a private project’s missing context.
The Qwen3.5 Plus family is documented as hybrid thinking, with thinking enabled by default. Its family workflow can produce a direct response when thinking is disabled, while reasoning and final-answer content are treated separately. The exact April snapshot’s interface should use its own documented controls; a family mode description is not a promise that every application exposes a particular parameter.
Long-context work
Alibaba’s dedicated April 20 snapshot table gives a 1,000,000-token context, maximum input of 991,808 tokens for direct responses or 983,616 for thinking, and maximum output of 65,536 in either mode. Do not transfer the open Qwen3.5 checkpoint’s native or extended context numbers into a hard limit for this Plus snapshot. Prepare a long input with document boundaries, page identifiers, code paths and the definitions needed for the task.
A useful request can ask for a requirements-to-implementation table, a document comparison or a report identifying evidence for each conclusion. Keep unrelated material out of the prompt and leave room for the answer. A long-context capability helps place more evidence together; it is not a guarantee of complete recall or a substitute for a clear question.
Production-style task preparation
The manufacturer positions this edition for complex agents, coding workflows and throughput-oriented use. Define the task’s observable result: the files to produce, behavior to implement or findings to explain. Where tools are connected, distinguish their real returned results from the model’s text proposals. Set the final format so the artifact can move into a review or application workflow, while checking its syntax and content separately.
The dedicated snapshot table lists function calling, structured outputs, web search, prefix completion and context caching; batch inference and fine-tuning are unsupported. These are producer workflow features, and media-file limits remain a separate specification. A request for JSON-shaped text, code execution or source retrieval should therefore remain a requested workflow rather than an assumed native guarantee. The improvement described by the maker is qualitative; it should not become an unqualified latency or throughput promise.
Practical limits
Keep the exact dated Plus edition and source material with the result when comparing later revisions. Check generated code, calculations and extracted visual details against the supplied source and return unresolved evidence explicitly. The useful outcome is a concrete textual artifact tied to the task’s requirements, with the exact dated Plus identity and the documented producer input, output and tool limits kept explicit.
", "aboutText": "The fixed April 20 Plus snapshot\n\nQwen3.5 Plus 2026-04-20 is the April 20, 2026 snapshot of Qwen’s native vision-language Plus family. The maker’s release notice identifies a substantial improvement in agentic coding compared with the February 15 snapshot, alongside stronger inference efficiency and retained knowledge, reasoning and long-context capabilities. Keep this dated edition distinct from a moving Plus name and from the open Qwen3.5-397B-A17B checkpoint.\n\nThe family accepts text with images or video and produces textual results. That scope supports a development task informed by a screenshot, a question about a technical diagram or a document-based explanation. The snapshot name does not by itself establish the open checkpoint’s parameter count, activated experts or exact architecture, so those figures are not assigned to this edition here.\n\nAgentic coding\n\nThe release’s main change is more capable coding in an agent workflow. Supply the project requirements, relevant files or excerpts, existing behavior and the artifact expected at completion. For a screenshot-to-interface task, include the visual reference and functional constraints, then request editable source and an explanation of the intended behavior. For a repository change, identify the affected feature and the input demonstrating the issue, then ask for a patch and the checks needed to assess it.\n\nA multi-step coding workflow benefits from actual feedback: inspection results, observed errors and review findings can be returned to the model as the work progresses. The application controls the tools and executes permitted actions. Ask for a report of what was proposed, what was observed and what remains unresolved.\n\nKnowledge and reasoning\n\nThe maker says the snapshot retains strong knowledge and reasoning while improving agent work. For an analytical task, separate the source facts from assumptions and specify the conclusion being sought. Request supporting passages, values or code identifiers so the result can be checked. For a professional report, provide the relevant material and desired sections rather than rely on the model to know a private project’s missing context.\n\nThe Qwen3.5 Plus family is documented as hybrid thinking, with thinking enabled by default. Its family workflow can produce a direct response when thinking is disabled, while reasoning and final-answer content are treated separately. The exact April snapshot’s interface should use its own documented controls; a family mode description is not a promise that every application exposes a particular parameter.\n\nLong-context work\n\nAlibaba’s dedicated April 20 snapshot table gives a 1,000,000-token context, maximum input of 991,808 tokens for direct responses or 983,616 for thinking, and maximum output of 65,536 in either mode. Do not transfer the open Qwen3.5 checkpoint’s native or extended context numbers into a hard limit for this Plus snapshot. Prepare a long input with document boundaries, page identifiers, code paths and the definitions needed for the task.\n\nA useful request can ask for a requirements-to-implementation table, a document comparison or a report identifying evidence for each conclusion. Keep unrelated material out of the prompt and leave room for the answer. A long-context capability helps place more evidence together; it is not a guarantee of complete recall or a substitute for a clear question.\n\nProduction-style task preparation\n\nThe manufacturer positions this edition for complex agents, coding workflows and throughput-oriented use. Define the task’s observable result: the files to produce, behavior to implement or findings to explain. Where tools are connected, distinguish their real returned results from the model’s text proposals. Set the final format so the artifact can move into a review or application workflow, while checking its syntax and content separately.\n\nThe dedicated snapshot table lists function calling, structured outputs, web search, prefix completion and context caching; batch inference and fine-tuning are unsupported. These are producer workflow features, and media-file limits remain a separate specification. A request for JSON-shaped text, code execution or source retrieval should therefore remain a requested workflow rather than an assumed native guarantee. The improvement described by the maker is qualitative; it should not become an unqualified latency or throughput promise.\n\nPractical limits\n\nKeep the exact dated Plus edition and source material with the result when comparing later revisions. Check generated code, calculations and extracted visual details against the supplied source and return unresolved evidence explicitly. The useful outcome is a concrete textual artifact tied to the task’s requirements, with the exact dated Plus identity and the documented producer input, output and tool limits kept explicit.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Repair an asynchronous search race\n\nA search field calls fetchResults(query).then(render) after each keystroke. Results for an older query sometimes arrive after the latest query and overwrite the screen. Propose a focused JavaScript change that renders only the newest request's result. Preserve the existing fetchResults and render interfaces, handle request failures and describe a reversed-response-order test.A code proposal, a brief request-order explanation and a deterministic out-of-order response test.Check an older response cannot overwrite the latest result, including after a failed newer request.qwen/qwen3.5-plus-20260420Qwen3.5 Plus 2026-04-20 is the fixed April 20 snapshot of Qwen’s vision-language Plus model. The maker highlights improved agentic coding while retaining reasoning, knowledge and long-context work, for complex tasks that combine supplied text or visual material with a concrete deliverable.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
The fixed April 20 Plus snapshot
Qwen3.5 Plus 2026-04-20 is the April 20, 2026 snapshot of Qwen’s native vision-language Plus family. The maker’s release notice identifies a substantial improvement in agentic coding compared with the February 15 snapshot, alongside stronger inference efficiency and retained knowledge, reasoning and long-context capabilities. Keep this dated edition distinct from a moving Plus name and from the open Qwen3.5-397B-A17B checkpoint.
The family accepts text with images or video and produces textual results. That scope supports a development task informed by a screenshot, a question about a technical diagram or a document-based explanation. The snapshot name does not by itself establish the open checkpoint’s parameter count, activated experts or exact architecture, so those figures are not assigned to this edition here.
Agentic coding
The release’s main change is more capable coding in an agent workflow. Supply the project requirements, relevant files or excerpts, existing behavior and the artifact expected at completion. For a screenshot-to-interface task, include the visual reference and functional constraints, then request editable source and an explanation of the intended behavior. For a repository change, identify the affected feature and the input demonstrating the issue, then ask for a patch and the checks needed to assess it.
A multi-step coding workflow benefits from actual feedback: inspection results, observed errors and review findings can be returned to the model as the work progresses. The application controls the tools and executes permitted actions. Ask for a report of what was proposed, what was observed and what remains unresolved.
Knowledge and reasoning
The maker says the snapshot retains strong knowledge and reasoning while improving agent work. For an analytical task, separate the source facts from assumptions and specify the conclusion being sought. Request supporting passages, values or code identifiers so the result can be checked. For a professional report, provide the relevant material and desired sections rather than rely on the model to know a private project’s missing context.
The Qwen3.5 Plus family is documented as hybrid thinking, with thinking enabled by default. Its family workflow can produce a direct response when thinking is disabled, while reasoning and final-answer content are treated separately. The exact April snapshot’s interface should use its own documented controls; a family mode description is not a promise that every application exposes a particular parameter.
Long-context work
Alibaba’s dedicated April 20 snapshot table gives a 1,000,000-token context, maximum input of 991,808 tokens for direct responses or 983,616 for thinking, and maximum output of 65,536 in either mode. Do not transfer the open Qwen3.5 checkpoint’s native or extended context numbers into a hard limit for this Plus snapshot. Prepare a long input with document boundaries, page identifiers, code paths and the definitions needed for the task.
A useful request can ask for a requirements-to-implementation table, a document comparison or a report identifying evidence for each conclusion. Keep unrelated material out of the prompt and leave room for the answer. A long-context capability helps place more evidence together; it is not a guarantee of complete recall or a substitute for a clear question.
Production-style task preparation
The manufacturer positions this edition for complex agents, coding workflows and throughput-oriented use. Define the task’s observable result: the files to produce, behavior to implement or findings to explain. Where tools are connected, distinguish their real returned results from the model’s text proposals. Set the final format so the artifact can move into a review or application workflow, while checking its syntax and content separately.
The dedicated snapshot table lists function calling, structured outputs, web search, prefix completion and context caching; batch inference and fine-tuning are unsupported. These are producer workflow features, and media-file limits remain a separate specification. A request for JSON-shaped text, code execution or source retrieval should therefore remain a requested workflow rather than an assumed native guarantee. The improvement described by the maker is qualitative; it should not become an unqualified latency or throughput promise.
Practical limits
Keep the exact dated Plus edition and source material with the result when comparing later revisions. Check generated code, calculations and extracted visual details against the supplied source and return unresolved evidence explicitly. The useful outcome is a concrete textual artifact tied to the task’s requirements, with the exact dated Plus identity and the documented producer input, output and tool limits kept explicit.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qwen/qwen3.5-plus-20260420 | 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 $0.0006 / 1K tokens Output · Output tokens $0.0036 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write $0.00075 / 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 $0.0006 / 1K tokens Output · Output tokens $0.0036 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write $0.00075 / 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 $0.00075 / 1K tokens Output · Output tokens $0.0045 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write $0.0009375 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${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-20260420", "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-20260420',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-20260420',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-20260420
Use the method paths shown above.
qwen/qwen3.5-plus-20260420Qwen3.5 Plus 2026-04-20 is the fixed April 20 snapshot of Qwen’s vision-language Plus model. The maker highlights improved agentic coding while retaining reasoning, knowledge and long-context work, for complex tasks that combine supplied text or visual material with a concrete deliverable.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
The fixed April 20 Plus snapshot
Qwen3.5 Plus 2026-04-20 is the April 20, 2026 snapshot of Qwen’s native vision-language Plus family. The maker’s release notice identifies a substantial improvement in agentic coding compared with the February 15 snapshot, alongside stronger inference efficiency and retained knowledge, reasoning and long-context capabilities. Keep this dated edition distinct from a moving Plus name and from the open Qwen3.5-397B-A17B checkpoint.
The family accepts text with images or video and produces textual results. That scope supports a development task informed by a screenshot, a question about a technical diagram or a document-based explanation. The snapshot name does not by itself establish the open checkpoint’s parameter count, activated experts or exact architecture, so those figures are not assigned to this edition here.
Agentic coding
The release’s main change is more capable coding in an agent workflow. Supply the project requirements, relevant files or excerpts, existing behavior and the artifact expected at completion. For a screenshot-to-interface task, include the visual reference and functional constraints, then request editable source and an explanation of the intended behavior. For a repository change, identify the affected feature and the input demonstrating the issue, then ask for a patch and the checks needed to assess it.
A multi-step coding workflow benefits from actual feedback: inspection results, observed errors and review findings can be returned to the model as the work progresses. The application controls the tools and executes permitted actions. Ask for a report of what was proposed, what was observed and what remains unresolved.
Knowledge and reasoning
The maker says the snapshot retains strong knowledge and reasoning while improving agent work. For an analytical task, separate the source facts from assumptions and specify the conclusion being sought. Request supporting passages, values or code identifiers so the result can be checked. For a professional report, provide the relevant material and desired sections rather than rely on the model to know a private project’s missing context.
The Qwen3.5 Plus family is documented as hybrid thinking, with thinking enabled by default. Its family workflow can produce a direct response when thinking is disabled, while reasoning and final-answer content are treated separately. The exact April snapshot’s interface should use its own documented controls; a family mode description is not a promise that every application exposes a particular parameter.
Long-context work
Alibaba’s dedicated April 20 snapshot table gives a 1,000,000-token context, maximum input of 991,808 tokens for direct responses or 983,616 for thinking, and maximum output of 65,536 in either mode. Do not transfer the open Qwen3.5 checkpoint’s native or extended context numbers into a hard limit for this Plus snapshot. Prepare a long input with document boundaries, page identifiers, code paths and the definitions needed for the task.
A useful request can ask for a requirements-to-implementation table, a document comparison or a report identifying evidence for each conclusion. Keep unrelated material out of the prompt and leave room for the answer. A long-context capability helps place more evidence together; it is not a guarantee of complete recall or a substitute for a clear question.
Production-style task preparation
The manufacturer positions this edition for complex agents, coding workflows and throughput-oriented use. Define the task’s observable result: the files to produce, behavior to implement or findings to explain. Where tools are connected, distinguish their real returned results from the model’s text proposals. Set the final format so the artifact can move into a review or application workflow, while checking its syntax and content separately.
The dedicated snapshot table lists function calling, structured outputs, web search, prefix completion and context caching; batch inference and fine-tuning are unsupported. These are producer workflow features, and media-file limits remain a separate specification. A request for JSON-shaped text, code execution or source retrieval should therefore remain a requested workflow rather than an assumed native guarantee. The improvement described by the maker is qualitative; it should not become an unqualified latency or throughput promise.
Practical limits
Keep the exact dated Plus edition and source material with the result when comparing later revisions. Check generated code, calculations and extracted visual details against the supplied source and return unresolved evidence explicitly. The useful outcome is a concrete textual artifact tied to the task’s requirements, with the exact dated Plus identity and the documented producer input, output and tool limits kept explicit.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qwen/qwen3.5-plus-20260420 | 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 $0.0006 / 1K tokens Output · Output tokens $0.0036 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write $0.00075 / 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 $0.0006 / 1K tokens Output · Output tokens $0.0036 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write $0.00075 / 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 $0.00075 / 1K tokens Output · Output tokens $0.0045 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write $0.0009375 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "qwen/qwen3.5-plus-20260420",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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-20260420', '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-20260420', '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-20260420
Use the method paths shown above.
Technical example in English
Repair an asynchronous search race\n\nA search field calls fetchResults(query).then(render) after each keystroke. Results for an older query sometimes arrive after the latest query and overwrite the screen. Propose a focused JavaScript change that renders only the newest request's result. Preserve the existing fetchResults and render interfaces, handle request failures and describe a reversed-response-order test.A code proposal, a brief request-order explanation and a deterministic out-of-order response test.Check an older response cannot overwrite the latest result, including after a failed newer request.