The February 23 Flash release
Qwen3.5 Flash is a native vision-language model family. The maker’s release names the February 23, 2026 snapshot and describes a hybrid architecture combining linear attention with sparse mixture-of-experts computation. Its inputs are text, images and video and its result is text. The release focuses on balanced inference and task capability across text and multimodal work; it does not establish a fixed latency for a particular application.
Qwen’s open-model card describes managed Qwen3.5-Flash as corresponding to Qwen3.5-35B-A3B, with additional features such as a default one-million-token context and built-in tools. That is a manufacturer-described relationship between offerings, not a reason to collapse their exact names, configuration or interface features. The February 23 snapshot remains distinct from a moving Flash name and from later Qwen generations.
Text, visual and coding tasks
The Qwen3.5 family is trained with early text–vision fusion, supporting reasoning, coding, agents and visual understanding. For a coding task informed by a screenshot, provide the visual reference, relevant code and required behavior, then ask for an editable artifact with an explanation of the affected conditions. For a document or chart, preserve labels and units and request the specific fields or conclusions needed.
A useful visual answer can distinguish visible facts from inferred relationships and identify the source region or passage supporting each conclusion. For video, preserve the sequence and timing and state the event of interest. For document and video analysis, compare the returned fields and claims with the original labels, passages and timestamps. The model produces textual analysis or code; visual input does not imply generated images or video.
Thinking and direct responses
The maker’s mode guide identifies Qwen3.5 Flash as hybrid thinking, with thinking enabled by default. The documented hybrid workflow can disable thinking for a direct answer. Keep the final artifact separate from the reasoning when the chosen interface provides both. A concise response can suit straightforward extraction or rewriting, while a question connecting several conditions benefits from an explanation that remains traceable to the source.
Use the Flash edition’s documented controls rather than import sampling presets, historical reasoning options or prompt markers from another Qwen checkpoint. The open Qwen3.5-35B-A3B card has its own history and generation recipe; its settings are not automatically an exact hosted Flash interface contract.
Tools and application workflows
The manufacturer describes additional tools in the managed Flash offering. A connected workflow can supply retrieval, inspection or permitted execution and return the observations to the model. Define the available tools, allowed actions and observable condition for completion. Ask the final report to distinguish proposed work from results that an actual tool returned.
A model’s tool-oriented capability does not establish built-in access to current sources, files or a code environment through every interface. A request for a table or JSON-shaped text also does not by itself create an enforced output schema. Keep the artifact easy to inspect: code files, an evidence table or a short conclusion linked to the supplied material.
Context and edition-specific limits
Qwen describes a default one-million-token context for its managed Flash version. The corresponding open checkpoint has a different native context and an explicit extension procedure, so those numerical descriptions should remain scoped to their own offerings. Text, represented media, conversation history, reasoning and the answer need to fit the applicable configured sequence budget.
Select the relevant text, images or video segments, preserve document and code identifiers, and reserve room in the working sequence for the result.
Practical preparation and review
For an iterative coding task, supply actual error or review feedback with the next question so the model can update its proposed change. For document analysis, request supporting passages and identify missing evidence explicitly. Check extracted text, calculations and generated code against the source. Use this fixed release for text, image or video analysis that returns a concrete textual deliverable.
", "aboutText": "The February 23 Flash release\n\nQwen3.5 Flash is a native vision-language model family. The maker’s release names the February 23, 2026 snapshot and describes a hybrid architecture combining linear attention with sparse mixture-of-experts computation. Its inputs are text, images and video and its result is text. The release focuses on balanced inference and task capability across text and multimodal work; it does not establish a fixed latency for a particular application.\n\nQwen’s open-model card describes managed Qwen3.5-Flash as corresponding to Qwen3.5-35B-A3B, with additional features such as a default one-million-token context and built-in tools. That is a manufacturer-described relationship between offerings, not a reason to collapse their exact names, configuration or interface features. The February 23 snapshot remains distinct from a moving Flash name and from later Qwen generations.\n\nText, visual and coding tasks\n\nThe Qwen3.5 family is trained with early text–vision fusion, supporting reasoning, coding, agents and visual understanding. For a coding task informed by a screenshot, provide the visual reference, relevant code and required behavior, then ask for an editable artifact with an explanation of the affected conditions. For a document or chart, preserve labels and units and request the specific fields or conclusions needed.\n\nA useful visual answer can distinguish visible facts from inferred relationships and identify the source region or passage supporting each conclusion. For video, preserve the sequence and timing and state the event of interest. For document and video analysis, compare the returned fields and claims with the original labels, passages and timestamps. The model produces textual analysis or code; visual input does not imply generated images or video.\n\nThinking and direct responses\n\nThe maker’s mode guide identifies Qwen3.5 Flash as hybrid thinking, with thinking enabled by default. The documented hybrid workflow can disable thinking for a direct answer. Keep the final artifact separate from the reasoning when the chosen interface provides both. A concise response can suit straightforward extraction or rewriting, while a question connecting several conditions benefits from an explanation that remains traceable to the source.\n\nUse the Flash edition’s documented controls rather than import sampling presets, historical reasoning options or prompt markers from another Qwen checkpoint. The open Qwen3.5-35B-A3B card has its own history and generation recipe; its settings are not automatically an exact hosted Flash interface contract.\n\nTools and application workflows\n\nThe manufacturer describes additional tools in the managed Flash offering. A connected workflow can supply retrieval, inspection or permitted execution and return the observations to the model. Define the available tools, allowed actions and observable condition for completion. Ask the final report to distinguish proposed work from results that an actual tool returned.\n\nA model’s tool-oriented capability does not establish built-in access to current sources, files or a code environment through every interface. A request for a table or JSON-shaped text also does not by itself create an enforced output schema. Keep the artifact easy to inspect: code files, an evidence table or a short conclusion linked to the supplied material.\n\nContext and edition-specific limits\n\nQwen describes a default one-million-token context for its managed Flash version. The corresponding open checkpoint has a different native context and an explicit extension procedure, so those numerical descriptions should remain scoped to their own offerings. Text, represented media, conversation history, reasoning and the answer need to fit the applicable configured sequence budget.\n\nSelect the relevant text, images or video segments, preserve document and code identifiers, and reserve room in the working sequence for the result.\n\nPractical preparation and review\n\nFor an iterative coding task, supply actual error or review feedback with the next question so the model can update its proposed change. For document analysis, request supporting passages and identify missing evidence explicitly. Check extracted text, calculations and generated code against the source. Use this fixed release for text, image or video analysis that returns a concrete textual deliverable.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Refine a patch using test feedback\n\nA first patch changes deduplicate(values) to list(set(values)). The returned test observation is: input [3,1,3,2] expected [3,1,2], but order was not preserved. Propose a replacement that retains first occurrences and works on integers. Include a regression assertion and explain the one behavior the failed patch overlooked. Do not claim to run the test.A revised Python function, a regression assertion and a short explanation tied to the supplied test observation.The duplicate 3 is removed while the order 3,1,2 survives; test execution remains a proposed check.qwen/qwen3.5-flash-02-23The February 23 Qwen3.5 Flash release is a vision-language model for text, images and video, returning text. It combines hybrid attention and sparse experts with the Flash family’s thinking/direct-answer workflow, for coding, visual analysis and tool-assisted tasks.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
The February 23 Flash release
Qwen3.5 Flash is a native vision-language model family. The maker’s release names the February 23, 2026 snapshot and describes a hybrid architecture combining linear attention with sparse mixture-of-experts computation. Its inputs are text, images and video and its result is text. The release focuses on balanced inference and task capability across text and multimodal work; it does not establish a fixed latency for a particular application.
Qwen’s open-model card describes managed Qwen3.5-Flash as corresponding to Qwen3.5-35B-A3B, with additional features such as a default one-million-token context and built-in tools. That is a manufacturer-described relationship between offerings, not a reason to collapse their exact names, configuration or interface features. The February 23 snapshot remains distinct from a moving Flash name and from later Qwen generations.
Text, visual and coding tasks
The Qwen3.5 family is trained with early text–vision fusion, supporting reasoning, coding, agents and visual understanding. For a coding task informed by a screenshot, provide the visual reference, relevant code and required behavior, then ask for an editable artifact with an explanation of the affected conditions. For a document or chart, preserve labels and units and request the specific fields or conclusions needed.
A useful visual answer can distinguish visible facts from inferred relationships and identify the source region or passage supporting each conclusion. For video, preserve the sequence and timing and state the event of interest. For document and video analysis, compare the returned fields and claims with the original labels, passages and timestamps. The model produces textual analysis or code; visual input does not imply generated images or video.
Thinking and direct responses
The maker’s mode guide identifies Qwen3.5 Flash as hybrid thinking, with thinking enabled by default. The documented hybrid workflow can disable thinking for a direct answer. Keep the final artifact separate from the reasoning when the chosen interface provides both. A concise response can suit straightforward extraction or rewriting, while a question connecting several conditions benefits from an explanation that remains traceable to the source.
Use the Flash edition’s documented controls rather than import sampling presets, historical reasoning options or prompt markers from another Qwen checkpoint. The open Qwen3.5-35B-A3B card has its own history and generation recipe; its settings are not automatically an exact hosted Flash interface contract.
Tools and application workflows
The manufacturer describes additional tools in the managed Flash offering. A connected workflow can supply retrieval, inspection or permitted execution and return the observations to the model. Define the available tools, allowed actions and observable condition for completion. Ask the final report to distinguish proposed work from results that an actual tool returned.
A model’s tool-oriented capability does not establish built-in access to current sources, files or a code environment through every interface. A request for a table or JSON-shaped text also does not by itself create an enforced output schema. Keep the artifact easy to inspect: code files, an evidence table or a short conclusion linked to the supplied material.
Context and edition-specific limits
Qwen describes a default one-million-token context for its managed Flash version. The corresponding open checkpoint has a different native context and an explicit extension procedure, so those numerical descriptions should remain scoped to their own offerings. Text, represented media, conversation history, reasoning and the answer need to fit the applicable configured sequence budget.
Select the relevant text, images or video segments, preserve document and code identifiers, and reserve room in the working sequence for the result.
Practical preparation and review
For an iterative coding task, supply actual error or review feedback with the next question so the model can update its proposed change. For document analysis, request supporting passages and identify missing evidence explicitly. Check extracted text, calculations and generated code against the source. Use this fixed release for text, image or video analysis that returns a concrete textual deliverable.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qwen/qwen3.5-flash-02-23 | 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 $0.00013 / 1K tokens Output · Output tokens $0.00052 / 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 $0.00013 / 1K tokens Output · Output tokens $0.00052 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${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-flash-02-23", "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-flash-02-23',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-flash-02-23',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-flash-02-23
Use the method paths shown above.
qwen/qwen3.5-flash-02-23The February 23 Qwen3.5 Flash release is a vision-language model for text, images and video, returning text. It combines hybrid attention and sparse experts with the Flash family’s thinking/direct-answer workflow, for coding, visual analysis and tool-assisted tasks.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
The February 23 Flash release
Qwen3.5 Flash is a native vision-language model family. The maker’s release names the February 23, 2026 snapshot and describes a hybrid architecture combining linear attention with sparse mixture-of-experts computation. Its inputs are text, images and video and its result is text. The release focuses on balanced inference and task capability across text and multimodal work; it does not establish a fixed latency for a particular application.
Qwen’s open-model card describes managed Qwen3.5-Flash as corresponding to Qwen3.5-35B-A3B, with additional features such as a default one-million-token context and built-in tools. That is a manufacturer-described relationship between offerings, not a reason to collapse their exact names, configuration or interface features. The February 23 snapshot remains distinct from a moving Flash name and from later Qwen generations.
Text, visual and coding tasks
The Qwen3.5 family is trained with early text–vision fusion, supporting reasoning, coding, agents and visual understanding. For a coding task informed by a screenshot, provide the visual reference, relevant code and required behavior, then ask for an editable artifact with an explanation of the affected conditions. For a document or chart, preserve labels and units and request the specific fields or conclusions needed.
A useful visual answer can distinguish visible facts from inferred relationships and identify the source region or passage supporting each conclusion. For video, preserve the sequence and timing and state the event of interest. For document and video analysis, compare the returned fields and claims with the original labels, passages and timestamps. The model produces textual analysis or code; visual input does not imply generated images or video.
Thinking and direct responses
The maker’s mode guide identifies Qwen3.5 Flash as hybrid thinking, with thinking enabled by default. The documented hybrid workflow can disable thinking for a direct answer. Keep the final artifact separate from the reasoning when the chosen interface provides both. A concise response can suit straightforward extraction or rewriting, while a question connecting several conditions benefits from an explanation that remains traceable to the source.
Use the Flash edition’s documented controls rather than import sampling presets, historical reasoning options or prompt markers from another Qwen checkpoint. The open Qwen3.5-35B-A3B card has its own history and generation recipe; its settings are not automatically an exact hosted Flash interface contract.
Tools and application workflows
The manufacturer describes additional tools in the managed Flash offering. A connected workflow can supply retrieval, inspection or permitted execution and return the observations to the model. Define the available tools, allowed actions and observable condition for completion. Ask the final report to distinguish proposed work from results that an actual tool returned.
A model’s tool-oriented capability does not establish built-in access to current sources, files or a code environment through every interface. A request for a table or JSON-shaped text also does not by itself create an enforced output schema. Keep the artifact easy to inspect: code files, an evidence table or a short conclusion linked to the supplied material.
Context and edition-specific limits
Qwen describes a default one-million-token context for its managed Flash version. The corresponding open checkpoint has a different native context and an explicit extension procedure, so those numerical descriptions should remain scoped to their own offerings. Text, represented media, conversation history, reasoning and the answer need to fit the applicable configured sequence budget.
Select the relevant text, images or video segments, preserve document and code identifiers, and reserve room in the working sequence for the result.
Practical preparation and review
For an iterative coding task, supply actual error or review feedback with the next question so the model can update its proposed change. For document analysis, request supporting passages and identify missing evidence explicitly. Check extracted text, calculations and generated code against the source. Use this fixed release for text, image or video analysis that returns a concrete textual deliverable.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qwen/qwen3.5-flash-02-23 | 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 $0.00013 / 1K tokens Output · Output tokens $0.00052 / 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 $0.00013 / 1K tokens Output · Output tokens $0.00052 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "qwen/qwen3.5-flash-02-23",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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-flash-02-23', '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-flash-02-23', '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-flash-02-23
Use the method paths shown above.
Technical example in English
Refine a patch using test feedback\n\nA first patch changes deduplicate(values) to list(set(values)). The returned test observation is: input [3,1,3,2] expected [3,1,2], but order was not preserved. Propose a replacement that retains first occurrences and works on integers. Include a regression assertion and explain the one behavior the failed patch overlooked. Do not claim to run the test.A revised Python function, a regression assertion and a short explanation tied to the supplied test observation.The duplicate 3 is removed while the order 3,1,2 survives; test execution remains a proposed check.