Qwen3.5-Omni-Flash 2026-03-15 is Alibaba’s named March 15 multimodal snapshot for text creation, voice assistants and multimedia analysis. It accepts text, images, audio and video, including mixed input, and produces text or text with speech. Its dated identity is distinct from the undated Flash alias and from realtime models. A recorded task can keep this edition name together with the media and instructions being reviewed.
Its input can join a picture with a spoken question, or combine a video’s visuals and sound with written instructions. This makes it useful when a text-only summary would lose the connection between what is seen and what is heard. For a media brief, ask separately for the visible sequence, on-screen wording and spoken content, and request source-relative timestamps when the order of events matters. Sound effects and other non-speech audio can contribute to the analysis alongside speech.
For a voice response, specify the answer’s language, audience and delivery. Qwen’s guide documents instructions for volume, speaking rate and emotion. It lists 113 audio-input languages and dialects and 36 speech-output languages and dialects, including English, French, German and Russian. The voice catalogue identifies Tina as the default and includes options such as Serena and Ethan. Choose the voice and ask for a concise explanation at a measured pace rather than relying on the input voice to determine the output style.
The documented HTTP speech workflow returns streaming text and Base64-encoded audio chunks. Its WAV example uses 24 kHz, mono, 16-bit PCM; an application can collect the chunks into an audio file or decode them for playback as they arrive. This is streamed generation from a submitted request. Live turn detection, interruption handling and microphone conversation belong to separately named realtime models. Qwen3.5-Omni’s family table does not offer a deep-thinking mode.
This Flash snapshot lists web search and Function Calling, with Function Calling limited to Beijing Chat Completions and text output. Structured Outputs is marked unsupported: a request for chronological sections is a text-format instruction rather than a constrained JSON mode. Tool execution belongs to the surrounding application, which returns the tool result for the next model step. Prefix completion, context caching, batch inference and fine-tuning are also marked unsupported for this snapshot.
The published context window is 262,144 tokens, with maximum input of 196,608 tokens and maximum output of 65,536 tokens. Mixed media and text share the context budget. Alibaba’s HTTP guide allows up to three hours of audio or one hour of video for this series; it lists AMR, WAV, 3GP, 3GPP, AAC and MP3 audio and MP4, AVI, MKV, MOV, FLV and WMV video. URL-based audio or video files may be up to 2 GB, while Base64-encoded media must be smaller than 10 MB. These are the manufacturer’s file-workflow limits, distinct from the model introduction’s description of understanding over ten hours of audio or over 400 seconds of 720p video sampled at 1 FPS.
Images have their own preparation limits in that guide: up to 20 MB per URL-based image, dimensions greater than 10 pixels on each side and an aspect ratio no more extreme than 200:1. The guide allows up to 2,048 URL-based images or audio files and 512 URL-based video files; Base64 input allows up to 250 files. These transfer limits remain subject to the shared input-token budget. The series can combine several media types in one request. Choose the relevant excerpt, make small labels readable and explain how separate inputs relate. The documented file-count ceilings vary by modality and transfer method, while every input must still fit the shared token budget.
Custom voice cloning is not supported by the named March 15 snapshot in the Qwen3.5-Omni guide. Choose a documented catalogue voice for spoken output and describe the desired delivery in the written brief. Do not transfer the undated Flash alias’s separate voice-enrolment workflow into this edition. A catalogue voice identifies the speaker style, while instructions can shape volume, speaking rate and emotion.
For a repeatable media report, supply the relevant clip and ask for the events, visible wording and speech in distinct chronological sections, each tied to source timestamps. For an educational response, add a diagram and a learner’s recorded question: “Explain the labelled parts, answer the audio question in English and provide text plus calm speech.” Keep the input excerpt, edition name and prompt together, and specify whether the output should transcribe the source or explain it for a new audience.
", "aboutText": "Qwen3.5-Omni-Flash 2026-03-15 is Alibaba’s named March 15 multimodal snapshot for text creation, voice assistants and multimedia analysis. It accepts text, images, audio and video, including mixed input, and produces text or text with speech. Its dated identity is distinct from the undated Flash alias and from realtime models. A recorded task can keep this edition name together with the media and instructions being reviewed.\n\nIts input can join a picture with a spoken question, or combine a video’s visuals and sound with written instructions. This makes it useful when a text-only summary would lose the connection between what is seen and what is heard. For a media brief, ask separately for the visible sequence, on-screen wording and spoken content, and request source-relative timestamps when the order of events matters. Sound effects and other non-speech audio can contribute to the analysis alongside speech.\n\nFor a voice response, specify the answer’s language, audience and delivery. Qwen’s guide documents instructions for volume, speaking rate and emotion. It lists 113 audio-input languages and dialects and 36 speech-output languages and dialects, including English, French, German and Russian. The voice catalogue identifies Tina as the default and includes options such as Serena and Ethan. Choose the voice and ask for a concise explanation at a measured pace rather than relying on the input voice to determine the output style.\n\nThe documented HTTP speech workflow returns streaming text and Base64-encoded audio chunks. Its WAV example uses 24 kHz, mono, 16-bit PCM; an application can collect the chunks into an audio file or decode them for playback as they arrive. This is streamed generation from a submitted request. Live turn detection, interruption handling and microphone conversation belong to separately named realtime models. Qwen3.5-Omni’s family table does not offer a deep-thinking mode.\n\nThis Flash snapshot lists web search and Function Calling, with Function Calling limited to Beijing Chat Completions and text output. Structured Outputs is marked unsupported: a request for chronological sections is a text-format instruction rather than a constrained JSON mode. Tool execution belongs to the surrounding application, which returns the tool result for the next model step. Prefix completion, context caching, batch inference and fine-tuning are also marked unsupported for this snapshot.\n\nThe published context window is 262,144 tokens, with maximum input of 196,608 tokens and maximum output of 65,536 tokens. Mixed media and text share the context budget. Alibaba’s HTTP guide allows up to three hours of audio or one hour of video for this series; it lists AMR, WAV, 3GP, 3GPP, AAC and MP3 audio and MP4, AVI, MKV, MOV, FLV and WMV video. URL-based audio or video files may be up to 2 GB, while Base64-encoded media must be smaller than 10 MB. These are the manufacturer’s file-workflow limits, distinct from the model introduction’s description of understanding over ten hours of audio or over 400 seconds of 720p video sampled at 1 FPS.\n\nImages have their own preparation limits in that guide: up to 20 MB per URL-based image, dimensions greater than 10 pixels on each side and an aspect ratio no more extreme than 200:1. The guide allows up to 2,048 URL-based images or audio files and 512 URL-based video files; Base64 input allows up to 250 files. These transfer limits remain subject to the shared input-token budget. The series can combine several media types in one request. Choose the relevant excerpt, make small labels readable and explain how separate inputs relate. The documented file-count ceilings vary by modality and transfer method, while every input must still fit the shared token budget.\n\nCustom voice cloning is not supported by the named March 15 snapshot in the Qwen3.5-Omni guide. Choose a documented catalogue voice for spoken output and describe the desired delivery in the written brief. Do not transfer the undated Flash alias’s separate voice-enrolment workflow into this edition. A catalogue voice identifies the speaker style, while instructions can shape volume, speaking rate and emotion.\n\nFor a repeatable media report, supply the relevant clip and ask for the events, visible wording and speech in distinct chronological sections, each tied to source timestamps. For an educational response, add a diagram and a learner’s recorded question: “Explain the labelled parts, answer the audio question in English and provide text plus calm speech.” Keep the input excerpt, edition name and prompt together, and specify whether the output should transcribe the source or explain it for a new audience.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Separate speech from scene notes\n\nPrepare a chronological report from these transcribed media notes: 00:00 a green indicator is visible; 00:03 speaker says “Wait for the light”; 00:05 indicator turns amber; 00:08 speaker says “Now disconnect.” Separate described visuals from quoted speech and list the action instruction with its time. Return text only.A timeline with distinct visual and speech entries, followed by the timed instruction.Check that the instruction stays at 00:08 and that the indicator change is not described as something the speaker said.qwen3.5-omni-flash-2026-03-15Qwen3.5-Omni-Flash 2026-03-15 is a multimodal snapshot that accepts text, images, audio and video and returns text or speech. Use its separate edition for repeatable media briefs and spoken explanations, with documented input and output boundaries.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Qwen3.5-Omni-Flash 2026-03-15 is Alibaba’s named March 15 multimodal snapshot for text creation, voice assistants and multimedia analysis. It accepts text, images, audio and video, including mixed input, and produces text or text with speech. Its dated identity is distinct from the undated Flash alias and from realtime models. A recorded task can keep this edition name together with the media and instructions being reviewed.
Its input can join a picture with a spoken question, or combine a video’s visuals and sound with written instructions. This makes it useful when a text-only summary would lose the connection between what is seen and what is heard. For a media brief, ask separately for the visible sequence, on-screen wording and spoken content, and request source-relative timestamps when the order of events matters. Sound effects and other non-speech audio can contribute to the analysis alongside speech.
For a voice response, specify the answer’s language, audience and delivery. Qwen’s guide documents instructions for volume, speaking rate and emotion. It lists 113 audio-input languages and dialects and 36 speech-output languages and dialects, including English, French, German and Russian. The voice catalogue identifies Tina as the default and includes options such as Serena and Ethan. Choose the voice and ask for a concise explanation at a measured pace rather than relying on the input voice to determine the output style.
The documented HTTP speech workflow returns streaming text and Base64-encoded audio chunks. Its WAV example uses 24 kHz, mono, 16-bit PCM; an application can collect the chunks into an audio file or decode them for playback as they arrive. This is streamed generation from a submitted request. Live turn detection, interruption handling and microphone conversation belong to separately named realtime models. Qwen3.5-Omni’s family table does not offer a deep-thinking mode.
This Flash snapshot lists web search and Function Calling, with Function Calling limited to Beijing Chat Completions and text output. Structured Outputs is marked unsupported: a request for chronological sections is a text-format instruction rather than a constrained JSON mode. Tool execution belongs to the surrounding application, which returns the tool result for the next model step. Prefix completion, context caching, batch inference and fine-tuning are also marked unsupported for this snapshot.
The published context window is 262,144 tokens, with maximum input of 196,608 tokens and maximum output of 65,536 tokens. Mixed media and text share the context budget. Alibaba’s HTTP guide allows up to three hours of audio or one hour of video for this series; it lists AMR, WAV, 3GP, 3GPP, AAC and MP3 audio and MP4, AVI, MKV, MOV, FLV and WMV video. URL-based audio or video files may be up to 2 GB, while Base64-encoded media must be smaller than 10 MB. These are the manufacturer’s file-workflow limits, distinct from the model introduction’s description of understanding over ten hours of audio or over 400 seconds of 720p video sampled at 1 FPS.
Images have their own preparation limits in that guide: up to 20 MB per URL-based image, dimensions greater than 10 pixels on each side and an aspect ratio no more extreme than 200:1. The guide allows up to 2,048 URL-based images or audio files and 512 URL-based video files; Base64 input allows up to 250 files. These transfer limits remain subject to the shared input-token budget. The series can combine several media types in one request. Choose the relevant excerpt, make small labels readable and explain how separate inputs relate. The documented file-count ceilings vary by modality and transfer method, while every input must still fit the shared token budget.
Custom voice cloning is not supported by the named March 15 snapshot in the Qwen3.5-Omni guide. Choose a documented catalogue voice for spoken output and describe the desired delivery in the written brief. Do not transfer the undated Flash alias’s separate voice-enrolment workflow into this edition. A catalogue voice identifies the speaker style, while instructions can shape volume, speaking rate and emotion.
For a repeatable media report, supply the relevant clip and ask for the events, visible wording and speech in distinct chronological sections, each tied to source timestamps. For an educational response, add a diagram and a learner’s recorded question: “Explain the labelled parts, answer the audio question in English and provide text plus calm speech.” Keep the input excerpt, edition name and prompt together, and specify whether the output should transcribe the source or explain it for a new audience.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qwen3.5-omni-flash-2026-03-15 | 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.
| Configuration | Rate schedule | Charge |
|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Charge Input · Input tokens $0.00069 / 1K tokens Output · Output tokens $0.00418 / 1K tokens Input · Cache read $0 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "qwen3.5-omni-flash-2026-03-15", "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='qwen3.5-omni-flash-2026-03-15',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='qwen3.5-omni-flash-2026-03-15',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 qwen3.5-omni-flash-2026-03-15
Use the method paths shown above.
qwen3.5-omni-flash-2026-03-15Qwen3.5-Omni-Flash 2026-03-15 is a multimodal snapshot that accepts text, images, audio and video and returns text or speech. Use its separate edition for repeatable media briefs and spoken explanations, with documented input and output boundaries.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Qwen3.5-Omni-Flash 2026-03-15 is Alibaba’s named March 15 multimodal snapshot for text creation, voice assistants and multimedia analysis. It accepts text, images, audio and video, including mixed input, and produces text or text with speech. Its dated identity is distinct from the undated Flash alias and from realtime models. A recorded task can keep this edition name together with the media and instructions being reviewed.
Its input can join a picture with a spoken question, or combine a video’s visuals and sound with written instructions. This makes it useful when a text-only summary would lose the connection between what is seen and what is heard. For a media brief, ask separately for the visible sequence, on-screen wording and spoken content, and request source-relative timestamps when the order of events matters. Sound effects and other non-speech audio can contribute to the analysis alongside speech.
For a voice response, specify the answer’s language, audience and delivery. Qwen’s guide documents instructions for volume, speaking rate and emotion. It lists 113 audio-input languages and dialects and 36 speech-output languages and dialects, including English, French, German and Russian. The voice catalogue identifies Tina as the default and includes options such as Serena and Ethan. Choose the voice and ask for a concise explanation at a measured pace rather than relying on the input voice to determine the output style.
The documented HTTP speech workflow returns streaming text and Base64-encoded audio chunks. Its WAV example uses 24 kHz, mono, 16-bit PCM; an application can collect the chunks into an audio file or decode them for playback as they arrive. This is streamed generation from a submitted request. Live turn detection, interruption handling and microphone conversation belong to separately named realtime models. Qwen3.5-Omni’s family table does not offer a deep-thinking mode.
This Flash snapshot lists web search and Function Calling, with Function Calling limited to Beijing Chat Completions and text output. Structured Outputs is marked unsupported: a request for chronological sections is a text-format instruction rather than a constrained JSON mode. Tool execution belongs to the surrounding application, which returns the tool result for the next model step. Prefix completion, context caching, batch inference and fine-tuning are also marked unsupported for this snapshot.
The published context window is 262,144 tokens, with maximum input of 196,608 tokens and maximum output of 65,536 tokens. Mixed media and text share the context budget. Alibaba’s HTTP guide allows up to three hours of audio or one hour of video for this series; it lists AMR, WAV, 3GP, 3GPP, AAC and MP3 audio and MP4, AVI, MKV, MOV, FLV and WMV video. URL-based audio or video files may be up to 2 GB, while Base64-encoded media must be smaller than 10 MB. These are the manufacturer’s file-workflow limits, distinct from the model introduction’s description of understanding over ten hours of audio or over 400 seconds of 720p video sampled at 1 FPS.
Images have their own preparation limits in that guide: up to 20 MB per URL-based image, dimensions greater than 10 pixels on each side and an aspect ratio no more extreme than 200:1. The guide allows up to 2,048 URL-based images or audio files and 512 URL-based video files; Base64 input allows up to 250 files. These transfer limits remain subject to the shared input-token budget. The series can combine several media types in one request. Choose the relevant excerpt, make small labels readable and explain how separate inputs relate. The documented file-count ceilings vary by modality and transfer method, while every input must still fit the shared token budget.
Custom voice cloning is not supported by the named March 15 snapshot in the Qwen3.5-Omni guide. Choose a documented catalogue voice for spoken output and describe the desired delivery in the written brief. Do not transfer the undated Flash alias’s separate voice-enrolment workflow into this edition. A catalogue voice identifies the speaker style, while instructions can shape volume, speaking rate and emotion.
For a repeatable media report, supply the relevant clip and ask for the events, visible wording and speech in distinct chronological sections, each tied to source timestamps. For an educational response, add a diagram and a learner’s recorded question: “Explain the labelled parts, answer the audio question in English and provide text plus calm speech.” Keep the input excerpt, edition name and prompt together, and specify whether the output should transcribe the source or explain it for a new audience.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qwen3.5-omni-flash-2026-03-15 | 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.
| Configuration | Rate schedule | Charge |
|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Charge Input · Input tokens $0.00069 / 1K tokens Output · Output tokens $0.00418 / 1K tokens Input · Cache read $0 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "qwen3.5-omni-flash-2026-03-15",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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': 'qwen3.5-omni-flash-2026-03-15', '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': 'qwen3.5-omni-flash-2026-03-15', '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 qwen3.5-omni-flash-2026-03-15
Use the method paths shown above.
Technical example in English
Separate speech from scene notes\n\nPrepare a chronological report from these transcribed media notes: 00:00 a green indicator is visible; 00:03 speaker says “Wait for the light”; 00:05 indicator turns amber; 00:08 speaker says “Now disconnect.” Separate described visuals from quoted speech and list the action instruction with its time. Return text only.A timeline with distinct visual and speech entries, followed by the timed instruction.Check that the instruction stays at 00:08 and that the indicator change is not described as something the speaker said.