Overview: mixed-media understanding and spoken answers
Qwen-Omni-Turbo is Qwen’s multimodal understanding and generation model. It accepts text, images, speech and video, including combinations of those inputs, and produces text or text with natural speech. The maker describes simultaneous streaming of text and speech, with four natural conversational voice options. This makes the model relevant to a task where the question and its evidence arrive in different forms, such as a spoken question about a photograph or an explanation of an audiovisual scene.
The exact name and its editions
The producer’s current model page describes qwen-omni-turbo as functionally equivalent to the qwen-omni-turbo-2025-03-26 snapshot. It separately lists qwen-omni-turbo-latest as a dynamically updated name and keeps the earlier qwen-omni-turbo-2025-01-19 snapshot distinct. The March snapshot is described as improving visual capabilities over January. These are the manufacturer’s edition relationships, not proof that every similarly named application route uses identical weights or settings. Keep a dated snapshot name when the task requires an exact version.
The Turbo name does not identify the separate real-time edition, a newer Qwen-Omni generation or the open Qwen2.5-Omni-7B checkpoint. Their input rules, voices and interfaces need their own documentation. In particular, the four voice options described for Omni-Turbo should not be copied into the two-voice open checkpoint’s description.
Preparing a mixed-media task
State what the model should connect across the inputs. For a spoken question about a diagram, provide the diagram and the question together, then request an explanation of the visible element being discussed. For a video with speech, specify whether the desired result is a summary of what is seen, what is said, or how the two relate. A useful output can separate visual observations from audio observations before the conclusion.
For a multimedia review, supply the relevant short excerpt rather than several unrelated assets. Label images and explain their role if there is more than one. Preserve the audio and timing information that matter to the question. Ask for a focused deliverable, such as a spoken explanation for a listener or a concise textual list of scene details. These are authored applications of the documented mixed-input capabilities, not claims that a particular clip has already been analyzed.
Text and speech output
The maker’s model description supports text responses and simultaneous streamed text and speech. A spoken explanation can make sense for conversational assistance, while text is easier to inspect, search and compare with source material. The chosen output mode and voice controls depend on the interface exposing the model. Streaming describes delivery in successive pieces; it is not a guaranteed response time or evidence that a separate real-time conversation protocol is available.
Context and output limits
The dedicated specification lists a 32,768-token context window, a maximum input length of 30,720 tokens and a maximum output length of 2,048 tokens. Prepare the source material and desired answer with those separate limits in mind. Multimodal input must fit its representation budget rather than only a count of typed characters. A request for a lengthy narration should be narrowed to a brief explanation that fits the output allowance.
Those token limits do not establish a universal duration in minutes or a universal count of images. Media preprocessing and the selected edition affect how much material fits. The model page does not publish a checkpoint architecture or parameter count, so the Turbo label should not be used to invent a size or to borrow the architecture of another Omni model.
Tools and substantive limitations
The exact model’s capability matrix does not support function calling, built-in web search or enforced structured outputs. It lists batch inference in some manufacturer configurations and context caching in another. Asking for a list or a JSON-shaped answer is a text-format request, not a schema-enforcement guarantee. The model’s ability to understand a visual or spoken task also does not grant access to current information or external systems.
Check whether the answer distinguishes visible evidence, audible content and interpretation. Speech quotations, small visual labels and inferred relationships should be compared with the supplied material. For a spoken result, keep the accompanying text when available so a reviewer can inspect the explanation. The practical advantage is connecting several modalities in one response, with a concise output sized for the documented edition.
", "aboutText": "Overview: mixed-media understanding and spoken answers\n\nQwen-Omni-Turbo is Qwen’s multimodal understanding and generation model. It accepts text, images, speech and video, including combinations of those inputs, and produces text or text with natural speech. The maker describes simultaneous streaming of text and speech, with four natural conversational voice options. This makes the model relevant to a task where the question and its evidence arrive in different forms, such as a spoken question about a photograph or an explanation of an audiovisual scene.\n\nThe exact name and its editions\n\nThe producer’s current model page describes qwen-omni-turbo as functionally equivalent to the qwen-omni-turbo-2025-03-26 snapshot. It separately lists qwen-omni-turbo-latest as a dynamically updated name and keeps the earlier qwen-omni-turbo-2025-01-19 snapshot distinct. The March snapshot is described as improving visual capabilities over January. These are the manufacturer’s edition relationships, not proof that every similarly named application route uses identical weights or settings. Keep a dated snapshot name when the task requires an exact version.\n\nThe Turbo name does not identify the separate real-time edition, a newer Qwen-Omni generation or the open Qwen2.5-Omni-7B checkpoint. Their input rules, voices and interfaces need their own documentation. In particular, the four voice options described for Omni-Turbo should not be copied into the two-voice open checkpoint’s description.\n\nPreparing a mixed-media task\n\nState what the model should connect across the inputs. For a spoken question about a diagram, provide the diagram and the question together, then request an explanation of the visible element being discussed. For a video with speech, specify whether the desired result is a summary of what is seen, what is said, or how the two relate. A useful output can separate visual observations from audio observations before the conclusion.\n\nFor a multimedia review, supply the relevant short excerpt rather than several unrelated assets. Label images and explain their role if there is more than one. Preserve the audio and timing information that matter to the question. Ask for a focused deliverable, such as a spoken explanation for a listener or a concise textual list of scene details. These are authored applications of the documented mixed-input capabilities, not claims that a particular clip has already been analyzed.\n\nText and speech output\n\nThe maker’s model description supports text responses and simultaneous streamed text and speech. A spoken explanation can make sense for conversational assistance, while text is easier to inspect, search and compare with source material. The chosen output mode and voice controls depend on the interface exposing the model. Streaming describes delivery in successive pieces; it is not a guaranteed response time or evidence that a separate real-time conversation protocol is available.\n\nContext and output limits\n\nThe dedicated specification lists a 32,768-token context window, a maximum input length of 30,720 tokens and a maximum output length of 2,048 tokens. Prepare the source material and desired answer with those separate limits in mind. Multimodal input must fit its representation budget rather than only a count of typed characters. A request for a lengthy narration should be narrowed to a brief explanation that fits the output allowance.\n\nThose token limits do not establish a universal duration in minutes or a universal count of images. Media preprocessing and the selected edition affect how much material fits. The model page does not publish a checkpoint architecture or parameter count, so the Turbo label should not be used to invent a size or to borrow the architecture of another Omni model.\n\nTools and substantive limitations\n\nThe exact model’s capability matrix does not support function calling, built-in web search or enforced structured outputs. It lists batch inference in some manufacturer configurations and context caching in another. Asking for a list or a JSON-shaped answer is a text-format request, not a schema-enforcement guarantee. The model’s ability to understand a visual or spoken task also does not grant access to current information or external systems.\n\nCheck whether the answer distinguishes visible evidence, audible content and interpretation. Speech quotations, small visual labels and inferred relationships should be compared with the supplied material. For a spoken result, keep the accompanying text when available so a reviewer can inspect the explanation. The practical advantage is connecting several modalities in one response, with a concise output sized for the documented edition.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Reconcile written scene and speech notes\n\nCompare these text notes from a training clip. [Visible note] The operator places a red tag on the empty bin. [Speech transcript] "Use a yellow tag when cleaning is due." Summarize the discrepancy and draft one clarification question for the trainer. Use only the supplied notes; do not claim to hear audio or view video.A concise discrepancy statement and one question, with visible-note and speech-transcript evidence kept separate.Check that neither color is silently corrected and the response makes no claim of media access.qwen-omni-turboQwen-Omni-Turbo combines text, images, audio and video in one multimodal task and can stream text with spoken responses. Use it to connect a spoken question with visual evidence or explain an audiovisual clip, within the producer’s 32,768-token context and 2,048-token output limit.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Overview: mixed-media understanding and spoken answers
Qwen-Omni-Turbo is Qwen’s multimodal understanding and generation model. It accepts text, images, speech and video, including combinations of those inputs, and produces text or text with natural speech. The maker describes simultaneous streaming of text and speech, with four natural conversational voice options. This makes the model relevant to a task where the question and its evidence arrive in different forms, such as a spoken question about a photograph or an explanation of an audiovisual scene.
The exact name and its editions
The producer’s current model page describes qwen-omni-turbo as functionally equivalent to the qwen-omni-turbo-2025-03-26 snapshot. It separately lists qwen-omni-turbo-latest as a dynamically updated name and keeps the earlier qwen-omni-turbo-2025-01-19 snapshot distinct. The March snapshot is described as improving visual capabilities over January. These are the manufacturer’s edition relationships, not proof that every similarly named application route uses identical weights or settings. Keep a dated snapshot name when the task requires an exact version.
The Turbo name does not identify the separate real-time edition, a newer Qwen-Omni generation or the open Qwen2.5-Omni-7B checkpoint. Their input rules, voices and interfaces need their own documentation. In particular, the four voice options described for Omni-Turbo should not be copied into the two-voice open checkpoint’s description.
Preparing a mixed-media task
State what the model should connect across the inputs. For a spoken question about a diagram, provide the diagram and the question together, then request an explanation of the visible element being discussed. For a video with speech, specify whether the desired result is a summary of what is seen, what is said, or how the two relate. A useful output can separate visual observations from audio observations before the conclusion.
For a multimedia review, supply the relevant short excerpt rather than several unrelated assets. Label images and explain their role if there is more than one. Preserve the audio and timing information that matter to the question. Ask for a focused deliverable, such as a spoken explanation for a listener or a concise textual list of scene details. These are authored applications of the documented mixed-input capabilities, not claims that a particular clip has already been analyzed.
Text and speech output
The maker’s model description supports text responses and simultaneous streamed text and speech. A spoken explanation can make sense for conversational assistance, while text is easier to inspect, search and compare with source material. The chosen output mode and voice controls depend on the interface exposing the model. Streaming describes delivery in successive pieces; it is not a guaranteed response time or evidence that a separate real-time conversation protocol is available.
Context and output limits
The dedicated specification lists a 32,768-token context window, a maximum input length of 30,720 tokens and a maximum output length of 2,048 tokens. Prepare the source material and desired answer with those separate limits in mind. Multimodal input must fit its representation budget rather than only a count of typed characters. A request for a lengthy narration should be narrowed to a brief explanation that fits the output allowance.
Those token limits do not establish a universal duration in minutes or a universal count of images. Media preprocessing and the selected edition affect how much material fits. The model page does not publish a checkpoint architecture or parameter count, so the Turbo label should not be used to invent a size or to borrow the architecture of another Omni model.
Tools and substantive limitations
The exact model’s capability matrix does not support function calling, built-in web search or enforced structured outputs. It lists batch inference in some manufacturer configurations and context caching in another. Asking for a list or a JSON-shaped answer is a text-format request, not a schema-enforcement guarantee. The model’s ability to understand a visual or spoken task also does not grant access to current information or external systems.
Check whether the answer distinguishes visible evidence, audible content and interpretation. Speech quotations, small visual labels and inferred relationships should be compared with the supplied material. For a spoken result, keep the accompanying text when available so a reviewer can inspect the explanation. The practical advantage is connecting several modalities in one response, with a concise output sized for the documented edition.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qwen-omni-turbo | 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 $0.0046 / 1K tokens Output · Output tokens $0.0138 / 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": "qwen-omni-turbo", "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-omni-turbo',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-omni-turbo',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-omni-turbo
Use the method paths shown above.
qwen-omni-turboQwen-Omni-Turbo combines text, images, audio and video in one multimodal task and can stream text with spoken responses. Use it to connect a spoken question with visual evidence or explain an audiovisual clip, within the producer’s 32,768-token context and 2,048-token output limit.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Overview: mixed-media understanding and spoken answers
Qwen-Omni-Turbo is Qwen’s multimodal understanding and generation model. It accepts text, images, speech and video, including combinations of those inputs, and produces text or text with natural speech. The maker describes simultaneous streaming of text and speech, with four natural conversational voice options. This makes the model relevant to a task where the question and its evidence arrive in different forms, such as a spoken question about a photograph or an explanation of an audiovisual scene.
The exact name and its editions
The producer’s current model page describes qwen-omni-turbo as functionally equivalent to the qwen-omni-turbo-2025-03-26 snapshot. It separately lists qwen-omni-turbo-latest as a dynamically updated name and keeps the earlier qwen-omni-turbo-2025-01-19 snapshot distinct. The March snapshot is described as improving visual capabilities over January. These are the manufacturer’s edition relationships, not proof that every similarly named application route uses identical weights or settings. Keep a dated snapshot name when the task requires an exact version.
The Turbo name does not identify the separate real-time edition, a newer Qwen-Omni generation or the open Qwen2.5-Omni-7B checkpoint. Their input rules, voices and interfaces need their own documentation. In particular, the four voice options described for Omni-Turbo should not be copied into the two-voice open checkpoint’s description.
Preparing a mixed-media task
State what the model should connect across the inputs. For a spoken question about a diagram, provide the diagram and the question together, then request an explanation of the visible element being discussed. For a video with speech, specify whether the desired result is a summary of what is seen, what is said, or how the two relate. A useful output can separate visual observations from audio observations before the conclusion.
For a multimedia review, supply the relevant short excerpt rather than several unrelated assets. Label images and explain their role if there is more than one. Preserve the audio and timing information that matter to the question. Ask for a focused deliverable, such as a spoken explanation for a listener or a concise textual list of scene details. These are authored applications of the documented mixed-input capabilities, not claims that a particular clip has already been analyzed.
Text and speech output
The maker’s model description supports text responses and simultaneous streamed text and speech. A spoken explanation can make sense for conversational assistance, while text is easier to inspect, search and compare with source material. The chosen output mode and voice controls depend on the interface exposing the model. Streaming describes delivery in successive pieces; it is not a guaranteed response time or evidence that a separate real-time conversation protocol is available.
Context and output limits
The dedicated specification lists a 32,768-token context window, a maximum input length of 30,720 tokens and a maximum output length of 2,048 tokens. Prepare the source material and desired answer with those separate limits in mind. Multimodal input must fit its representation budget rather than only a count of typed characters. A request for a lengthy narration should be narrowed to a brief explanation that fits the output allowance.
Those token limits do not establish a universal duration in minutes or a universal count of images. Media preprocessing and the selected edition affect how much material fits. The model page does not publish a checkpoint architecture or parameter count, so the Turbo label should not be used to invent a size or to borrow the architecture of another Omni model.
Tools and substantive limitations
The exact model’s capability matrix does not support function calling, built-in web search or enforced structured outputs. It lists batch inference in some manufacturer configurations and context caching in another. Asking for a list or a JSON-shaped answer is a text-format request, not a schema-enforcement guarantee. The model’s ability to understand a visual or spoken task also does not grant access to current information or external systems.
Check whether the answer distinguishes visible evidence, audible content and interpretation. Speech quotations, small visual labels and inferred relationships should be compared with the supplied material. For a spoken result, keep the accompanying text when available so a reviewer can inspect the explanation. The practical advantage is connecting several modalities in one response, with a concise output sized for the documented edition.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qwen-omni-turbo | 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 $0.0046 / 1K tokens Output · Output tokens $0.0138 / 1K tokens Input · Cache read $0 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "qwen-omni-turbo",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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-omni-turbo', '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-omni-turbo', '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-omni-turbo
Use the method paths shown above.
Technical example in English
Reconcile written scene and speech notes\n\nCompare these text notes from a training clip. [Visible note] The operator places a red tag on the empty bin. [Speech transcript] "Use a yellow tag when cleaning is due." Summarize the discrepancy and draft one clarification question for the trainer. Use only the supplied notes; do not claim to hear audio or view video.A concise discrepancy statement and one question, with visible-note and speech-transcript evidence kept separate.Check that neither color is silently corrected and the response makes no claim of media access.