Model selection: multimedia analysis with text output
Qwen3.8 Omni Flash is Qwen’s model for audio and video understanding, meeting summaries and content analysis. Its inputs are text, images, audio and video; its output is text. A response can describe a recording, answer a question about visual and audible evidence or prepare a written summary. The maker explicitly distinguishes this edition from Omni models that generate speech. Do not assume that the Omni name gives this checkpoint a spoken-output mode.
The context is one million tokens, and audio input covers 113 languages and dialects. That language count describes audio understanding, not a guarantee of identical recognition quality for every accent, recording condition or technical vocabulary. For a meeting, supply the agenda or terms that matter and request decisions, unresolved questions and next actions. For an audiovisual clip, ask the model to separate what is visible from what is said before combining the evidence in a conclusion.
Preparing multimodal material
The documented examples combine media with a text question. State the intended result rather than submit an unexplained recording: a thematic summary, an event account or an answer to a specific question. Label separate assets and retain their source time ranges outside the request so the result can be traced back to the original. When several participants or scenes matter, name the distinctions the report should preserve.
Media limits in the maker’s file workflow
For video files, the maker documents up to 64 files, a two-hour duration limit and files up to 2 GB when supplied by an accessible file location. The documented video formats are MP4, AVI, MKV, MOV, FLV and WMV. For ordered images used as a video, the documented range is two to 2,048 images. Preserve order and timing rather than treat an arbitrary picture collection as a known temporal sequence.
For audio, the guide documents up to three hours, file-location input up to 2 GB, and AMR, WAV, 3GP, 3GPP, AAC or MP3. Its audio-file count is up to 2,048 when supplied by file locations and up to 250 with Base64 encoding. Encoded Base64 payloads must be smaller than 10 MB. These are producer workflow limits, not promises about an application’s upload interface, nor evidence that all maximum-sized inputs fit the token budget together.
For images, the guide lists up to 2,048 image locations or 250 encoded images. A file supplied by an accessible image location may be up to 20 MB; both dimensions must exceed ten pixels and the aspect ratio must stay within 200:1 or 1:200. Retain enough resolution for the particular question. A text field that becomes illegible during preparation cannot be recovered simply by requesting a confident answer.
Spatial audio
This model supports two-channel stereo and four-channel first-order ambisonic audio in WYZX channel order. The maker’s use_multichannel control defaults to false, interpreting audio as mono. With the control enabled and the supported channel layout present, spatial information can participate in understanding. Preserve the channel layout when the task asks about the audible spatial scene; do not infer calibrated coordinates of a sound source from a general description.
Tools and current information
The maker supports function calling and web search. In its documented Responses workflow, web_search is the only supported built-in tool for this edition. A tool-aware task can ask the model to connect retrieved current information with the supplied recording, while keeping the origin of each claim clear. External actions and tool results still depend on the application’s configured interface. Tool support should not be expanded into an unqualified code-interpreter or file-system claim. The producer also lists context caching for recurring input; reuse concerns shared request prefixes and does not establish a cache hit for a particular request.
Thinking modes
Thinking is enabled by default, with reasoning_effort set to xhigh. The primary thinking-effort levels are low, medium and xhigh; the none setting disables thinking. For compatibility, minimal maps to low, while high and max map to xhigh. The maker rejects requests that set reasoning_effort and thinking_budget together. These controls describe the producer interface and do not establish that every application exposes them.
Choose a direct response for a straightforward summary and deeper reasoning for a question that requires connecting several pieces of evidence. Keep the final report separate from the reasoning and check speech quotations, event order and the evidence behind conclusions. The guide establishes media and context limits but does not publish a separate hard maximum text-output length in the sections used here. A clear question and a traceable written result are more useful than treating the largest possible upload as a guarantee of complete recall.
", "aboutText": "Model selection: multimedia analysis with text output\n\nQwen3.8 Omni Flash is Qwen’s model for audio and video understanding, meeting summaries and content analysis. Its inputs are text, images, audio and video; its output is text. A response can describe a recording, answer a question about visual and audible evidence or prepare a written summary. The maker explicitly distinguishes this edition from Omni models that generate speech. Do not assume that the Omni name gives this checkpoint a spoken-output mode.\n\nThe context is one million tokens, and audio input covers 113 languages and dialects. That language count describes audio understanding, not a guarantee of identical recognition quality for every accent, recording condition or technical vocabulary. For a meeting, supply the agenda or terms that matter and request decisions, unresolved questions and next actions. For an audiovisual clip, ask the model to separate what is visible from what is said before combining the evidence in a conclusion.\n\nPreparing multimodal material\n\nThe documented examples combine media with a text question. State the intended result rather than submit an unexplained recording: a thematic summary, an event account or an answer to a specific question. Label separate assets and retain their source time ranges outside the request so the result can be traced back to the original. When several participants or scenes matter, name the distinctions the report should preserve.\n\nMedia limits in the maker’s file workflow\n\nFor video files, the maker documents up to 64 files, a two-hour duration limit and files up to 2 GB when supplied by an accessible file location. The documented video formats are MP4, AVI, MKV, MOV, FLV and WMV. For ordered images used as a video, the documented range is two to 2,048 images. Preserve order and timing rather than treat an arbitrary picture collection as a known temporal sequence.\n\nFor audio, the guide documents up to three hours, file-location input up to 2 GB, and AMR, WAV, 3GP, 3GPP, AAC or MP3. Its audio-file count is up to 2,048 when supplied by file locations and up to 250 with Base64 encoding. Encoded Base64 payloads must be smaller than 10 MB. These are producer workflow limits, not promises about an application’s upload interface, nor evidence that all maximum-sized inputs fit the token budget together.\n\nFor images, the guide lists up to 2,048 image locations or 250 encoded images. A file supplied by an accessible image location may be up to 20 MB; both dimensions must exceed ten pixels and the aspect ratio must stay within 200:1 or 1:200. Retain enough resolution for the particular question. A text field that becomes illegible during preparation cannot be recovered simply by requesting a confident answer.\n\nSpatial audio\n\nThis model supports two-channel stereo and four-channel first-order ambisonic audio in WYZX channel order. The maker’s use_multichannel control defaults to false, interpreting audio as mono. With the control enabled and the supported channel layout present, spatial information can participate in understanding. Preserve the channel layout when the task asks about the audible spatial scene; do not infer calibrated coordinates of a sound source from a general description.\n\nTools and current information\n\nThe maker supports function calling and web search. In its documented Responses workflow, web_search is the only supported built-in tool for this edition. A tool-aware task can ask the model to connect retrieved current information with the supplied recording, while keeping the origin of each claim clear. External actions and tool results still depend on the application’s configured interface. Tool support should not be expanded into an unqualified code-interpreter or file-system claim. The producer also lists context caching for recurring input; reuse concerns shared request prefixes and does not establish a cache hit for a particular request.\n\nThinking modes\n\nThinking is enabled by default, with reasoning_effort set to xhigh. The primary thinking-effort levels are low, medium and xhigh; the none setting disables thinking. For compatibility, minimal maps to low, while high and max map to xhigh. The maker rejects requests that set reasoning_effort and thinking_budget together. These controls describe the producer interface and do not establish that every application exposes them.\n\nChoose a direct response for a straightforward summary and deeper reasoning for a question that requires connecting several pieces of evidence. Keep the final report separate from the reasoning and check speech quotations, event order and the evidence behind conclusions. The guide establishes media and context limits but does not publish a separate hard maximum text-output length in the sections used here. A clear question and a traceable written result are more useful than treating the largest possible upload as a guarantee of complete recall.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Extract decisions from meeting text\n\nUse this meeting transcript. Lena: We agree to pilot the new checklist with Team A. Omar: I will prepare the draft by Thursday. Lena: We still need someone to review the results; no reviewer is assigned. Return decisions, named actions and unresolved questions. Preserve who said what and do not turn the pilot into a full rollout.A meeting summary with decision, action-owner-deadline rows and an open reviewer-assignment question.Check that Omar owns the draft, Thursday is its deadline and the reviewer remains unassigned.qwen/qwen3.8-omni-flashQwen3.8 Omni Flash analyzes text, images, audio and video and returns text. It supports meeting summaries, multimedia questions, 113 audio languages and dialects, selectable reasoning effort and spatial audio, with a producer-documented one-million-token context.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Model selection: multimedia analysis with text output
Qwen3.8 Omni Flash is Qwen’s model for audio and video understanding, meeting summaries and content analysis. Its inputs are text, images, audio and video; its output is text. A response can describe a recording, answer a question about visual and audible evidence or prepare a written summary. The maker explicitly distinguishes this edition from Omni models that generate speech. Do not assume that the Omni name gives this checkpoint a spoken-output mode.
The context is one million tokens, and audio input covers 113 languages and dialects. That language count describes audio understanding, not a guarantee of identical recognition quality for every accent, recording condition or technical vocabulary. For a meeting, supply the agenda or terms that matter and request decisions, unresolved questions and next actions. For an audiovisual clip, ask the model to separate what is visible from what is said before combining the evidence in a conclusion.
Preparing multimodal material
The documented examples combine media with a text question. State the intended result rather than submit an unexplained recording: a thematic summary, an event account or an answer to a specific question. Label separate assets and retain their source time ranges outside the request so the result can be traced back to the original. When several participants or scenes matter, name the distinctions the report should preserve.
Media limits in the maker’s file workflow
For video files, the maker documents up to 64 files, a two-hour duration limit and files up to 2 GB when supplied by an accessible file location. The documented video formats are MP4, AVI, MKV, MOV, FLV and WMV. For ordered images used as a video, the documented range is two to 2,048 images. Preserve order and timing rather than treat an arbitrary picture collection as a known temporal sequence.
For audio, the guide documents up to three hours, file-location input up to 2 GB, and AMR, WAV, 3GP, 3GPP, AAC or MP3. Its audio-file count is up to 2,048 when supplied by file locations and up to 250 with Base64 encoding. Encoded Base64 payloads must be smaller than 10 MB. These are producer workflow limits, not promises about an application’s upload interface, nor evidence that all maximum-sized inputs fit the token budget together.
For images, the guide lists up to 2,048 image locations or 250 encoded images. A file supplied by an accessible image location may be up to 20 MB; both dimensions must exceed ten pixels and the aspect ratio must stay within 200:1 or 1:200. Retain enough resolution for the particular question. A text field that becomes illegible during preparation cannot be recovered simply by requesting a confident answer.
Spatial audio
This model supports two-channel stereo and four-channel first-order ambisonic audio in WYZX channel order. The maker’s use_multichannel control defaults to false, interpreting audio as mono. With the control enabled and the supported channel layout present, spatial information can participate in understanding. Preserve the channel layout when the task asks about the audible spatial scene; do not infer calibrated coordinates of a sound source from a general description.
Tools and current information
The maker supports function calling and web search. In its documented Responses workflow, web_search is the only supported built-in tool for this edition. A tool-aware task can ask the model to connect retrieved current information with the supplied recording, while keeping the origin of each claim clear. External actions and tool results still depend on the application’s configured interface. Tool support should not be expanded into an unqualified code-interpreter or file-system claim. The producer also lists context caching for recurring input; reuse concerns shared request prefixes and does not establish a cache hit for a particular request.
Thinking modes
Thinking is enabled by default, with reasoning_effort set to xhigh. The primary thinking-effort levels are low, medium and xhigh; the none setting disables thinking. For compatibility, minimal maps to low, while high and max map to xhigh. The maker rejects requests that set reasoning_effort and thinking_budget together. These controls describe the producer interface and do not establish that every application exposes them.
Choose a direct response for a straightforward summary and deeper reasoning for a question that requires connecting several pieces of evidence. Keep the final report separate from the reasoning and check speech quotations, event order and the evidence behind conclusions. The guide establishes media and context limits but does not publish a separate hard maximum text-output length in the sections used here. A clear question and a traceable written result are more useful than treating the largest possible upload as a guarantee of complete recall.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qwen/qwen3.8-omni-flash | 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 $0.0003 / 1K tokens Output · Output tokens $0.00094 / 1K tokens Input · Cache read $0.000032 / 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 $0.0003 / 1K tokens Output · Output tokens $0.00094 / 1K tokens Input · Cache read $0.000032 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "qwen/qwen3.8-omni-flash", "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/qwen3.8-omni-flash',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/qwen3.8-omni-flash',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/qwen3.8-omni-flash
Use the method paths shown above.
qwen/qwen3.8-omni-flashQwen3.8 Omni Flash analyzes text, images, audio and video and returns text. It supports meeting summaries, multimedia questions, 113 audio languages and dialects, selectable reasoning effort and spatial audio, with a producer-documented one-million-token context.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Model selection: multimedia analysis with text output
Qwen3.8 Omni Flash is Qwen’s model for audio and video understanding, meeting summaries and content analysis. Its inputs are text, images, audio and video; its output is text. A response can describe a recording, answer a question about visual and audible evidence or prepare a written summary. The maker explicitly distinguishes this edition from Omni models that generate speech. Do not assume that the Omni name gives this checkpoint a spoken-output mode.
The context is one million tokens, and audio input covers 113 languages and dialects. That language count describes audio understanding, not a guarantee of identical recognition quality for every accent, recording condition or technical vocabulary. For a meeting, supply the agenda or terms that matter and request decisions, unresolved questions and next actions. For an audiovisual clip, ask the model to separate what is visible from what is said before combining the evidence in a conclusion.
Preparing multimodal material
The documented examples combine media with a text question. State the intended result rather than submit an unexplained recording: a thematic summary, an event account or an answer to a specific question. Label separate assets and retain their source time ranges outside the request so the result can be traced back to the original. When several participants or scenes matter, name the distinctions the report should preserve.
Media limits in the maker’s file workflow
For video files, the maker documents up to 64 files, a two-hour duration limit and files up to 2 GB when supplied by an accessible file location. The documented video formats are MP4, AVI, MKV, MOV, FLV and WMV. For ordered images used as a video, the documented range is two to 2,048 images. Preserve order and timing rather than treat an arbitrary picture collection as a known temporal sequence.
For audio, the guide documents up to three hours, file-location input up to 2 GB, and AMR, WAV, 3GP, 3GPP, AAC or MP3. Its audio-file count is up to 2,048 when supplied by file locations and up to 250 with Base64 encoding. Encoded Base64 payloads must be smaller than 10 MB. These are producer workflow limits, not promises about an application’s upload interface, nor evidence that all maximum-sized inputs fit the token budget together.
For images, the guide lists up to 2,048 image locations or 250 encoded images. A file supplied by an accessible image location may be up to 20 MB; both dimensions must exceed ten pixels and the aspect ratio must stay within 200:1 or 1:200. Retain enough resolution for the particular question. A text field that becomes illegible during preparation cannot be recovered simply by requesting a confident answer.
Spatial audio
This model supports two-channel stereo and four-channel first-order ambisonic audio in WYZX channel order. The maker’s use_multichannel control defaults to false, interpreting audio as mono. With the control enabled and the supported channel layout present, spatial information can participate in understanding. Preserve the channel layout when the task asks about the audible spatial scene; do not infer calibrated coordinates of a sound source from a general description.
Tools and current information
The maker supports function calling and web search. In its documented Responses workflow, web_search is the only supported built-in tool for this edition. A tool-aware task can ask the model to connect retrieved current information with the supplied recording, while keeping the origin of each claim clear. External actions and tool results still depend on the application’s configured interface. Tool support should not be expanded into an unqualified code-interpreter or file-system claim. The producer also lists context caching for recurring input; reuse concerns shared request prefixes and does not establish a cache hit for a particular request.
Thinking modes
Thinking is enabled by default, with reasoning_effort set to xhigh. The primary thinking-effort levels are low, medium and xhigh; the none setting disables thinking. For compatibility, minimal maps to low, while high and max map to xhigh. The maker rejects requests that set reasoning_effort and thinking_budget together. These controls describe the producer interface and do not establish that every application exposes them.
Choose a direct response for a straightforward summary and deeper reasoning for a question that requires connecting several pieces of evidence. Keep the final report separate from the reasoning and check speech quotations, event order and the evidence behind conclusions. The guide establishes media and context limits but does not publish a separate hard maximum text-output length in the sections used here. A clear question and a traceable written result are more useful than treating the largest possible upload as a guarantee of complete recall.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qwen/qwen3.8-omni-flash | 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 $0.0003 / 1K tokens Output · Output tokens $0.00094 / 1K tokens Input · Cache read $0.000032 / 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 $0.0003 / 1K tokens Output · Output tokens $0.00094 / 1K tokens Input · Cache read $0.000032 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "qwen/qwen3.8-omni-flash",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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/qwen3.8-omni-flash', '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/qwen3.8-omni-flash', '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/qwen3.8-omni-flash
Use the method paths shown above.
Technical example in English
Extract decisions from meeting text\n\nUse this meeting transcript. Lena: We agree to pilot the new checklist with Team A. Omar: I will prepare the draft by Thursday. Lena: We still need someone to review the results; no reviewer is assigned. Return decisions, named actions and unresolved questions. Preserve who said what and do not turn the pilot into a full rollout.A meeting summary with decision, action-owner-deadline rows and an open reviewer-assignment question.Check that Omar owns the draft, Thursday is its deadline and the reviewer remains unassigned.