Source: https://ailoot.ai/models/en/qwen-qwen3-omni-30b-a3b-thinking/ Canonical: https://ailoot.ai/models/en/qwen-qwen3-omni-30b-a3b-thinking/ Language: en # Qwen3 Omni 30B A3B Thinking [Markdown](https://ailoot.ai/models/en/qwen-qwen3-omni-30b-a3b-thinking/index.md) · [JSON](https://ailoot.ai/models/en/qwen-qwen3-omni-30b-a3b-thinking/facts.json) ## [Qwen3 Omni 30B A3B Thinking](https://ailoot.ai/models/en/qwen-qwen3-omni-30b-a3b-thinking/) Qwen3-Omni-30B-A3B-Thinking reasons over text, images, audio and video and returns text. This Thinker-only edition suits visual mathematics, audio analysis and questions that need evidence from several modalities; speech generation belongs to a different Omni release. - [**Ailoot Ultra · OpenAI Chat** `POST /v1/chat/completions` `Qwen/Qwen3-Omni-30B-A3B-Thinking`](https://ailoot.ai/models/en/qwen-qwen3-omni-30b-a3b-thinking/#method-0) - [**Ailoot Ultra · Anthropic Messages** `POST /v1/messages` `Qwen/Qwen3-Omni-30B-A3B-Thinking`](https://ailoot.ai/models/en/qwen-qwen3-omni-30b-a3b-thinking/#method-1) About the model This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below. Qwen3-Omni-30B-A3B-Thinking is the reasoning-oriented member of Qwen3-Omni. It understands text, images, audio and video, including combinations in the same conversation, and produces a text result. The exact Thinking edition contains the Thinker component and is equipped for reasoning; it does not include the Talker used for spoken output in the Instruct checkpoint. This distinction matters when selecting a model for an analytical report rather than a voiced conversation. The manufacturer describes Qwen3-Omni as a multilingual mixture-of-experts family with 119 text languages and 19 speech-input languages. Russian appears in the published speech-input list. The exact Thinking configuration includes 48 text-transformer layers, 128 experts and eight experts selected per token. It also has audio and vision processing components. These are characteristics of the named checkpoint; its multimodal understanding should not be replaced by the capabilities of a plain-text Qwen3 model with a similar size label. The usage cookbooks cover speech recognition and translation, music and environmental-sound analysis, mixed audio, image questions, OCR, object grounding, video descriptions and audio-visual questions. Image mathematics specifically highlights the Thinking edition. For a geometry task, supply the full diagram, readable labels and the question, then request a solution that distinguishes visible givens from assumptions. For a recorded demonstration, identify the action or discrepancy to investigate and ask for observations tied to the relevant parts of the material. The expected artifact can be a written solution, a structured observation list or an explanation of what the evidence supports. Prepare the input as a multimodal conversation using the matching processor and chat template. The maker’s processing toolkit handles interleaved text, images, audio and video. Qwen describes streaming text responses as part of the family’s interaction design and demonstrates mixed-media batch inference with text-only output. In each dialogue round, the manufacturer recommends an explicit text instruction alongside the media. A bare video leaves the task ambiguous: state whether to summarize actions, compare two scenes, explain a sound or solve the displayed problem. Label multiple inputs and their relationship so the final text can connect the right question to the right material. For video that contains speech or event sounds, decide whether its audio is part of the task. The documented flow uses use\_audio\_in\_video consistently during preprocessing and generation, and the card warns that changing this setting between dialogue rounds can cause unexpected results. A scene-only question and an audio-visual question therefore need different preparation. Keep the original clip available, select the relevant interval and avoid omitting the sound track when the requested conclusion depends on what was said or heard. The published text configuration sets max\_position\_embeddings to 65,536. The card’s vLLM examples separately use a 32,768-token model-length setting and a 16,384-token generation setting. These show a configured inference example rather than a single universal maximum output limit. Media are represented through the processor, so request size is not just the number of typed characters. Reserve room for the text result and use a bounded source segment when a long recording contains only a short event relevant to the question. The maker demonstrates Transformers and vLLM workflows, with processor support and media decoding as explicit dependencies. The shared card also documents interface differences, including separate handling of video and audio in a serving example. Select the exact Thinking checkpoint and its supported processing path rather than assuming that every example on the family card has the same output behavior. Speech voices and Talker controls on that page apply to Instruct, not to this Thinker-only model. For a useful final result, ask for an evidence-based explanation and a clearly separated conclusion. In a visual problem, retain units, symbols and labels; in audio, distinguish audible content from an inferred source; in a video, distinguish observed actions from an interpretation of intent. Inspect the result against the supplied material and identify uncertain or unreadable details explicitly. The model’s text answer can support analysis or a later application step, while any tool execution, factual confirmation or media transformation remains a separate operation that needs its own input and result. Practical task ### Reconcile demonstration annotations Technical example in English ``` Reconcile demonstration annotations Analyze these supplied text annotations of a demonstration. T0 visual note: valve indicator reads Closed. T1 speech transcript: "I am opening the valve now." T2 visual note: indicator still reads Closed; valve mechanism is off camera. State what each source establishes, whether successful opening is confirmed and what evidence would resolve the discrepancy. ``` #### Expected result ``` An evidence table separating visual notes from quoted speech, followed by a conclusion and one verification need. ``` #### Check the result ``` Check that a spoken intention is not treated as proof of the off-camera action or a faulty indicator. ``` **Ailoot Ultra · OpenAI Chat** `POST /v1/chat/completions` `Qwen/Qwen3-Omni-30B-A3B-Thinking` [`Qwen/Qwen3-Omni-30B-A3B-Thinking`](https://ailoot.ai/models/en/#m=Qwen%2FQwen3-Omni-30B-A3B-Thinking&route=Ultra&caller=Qwen%2FQwen3-Omni-30B-A3B-Thinking&fmt=chat) Alibaba /`Qwen/Qwen3-Omni-30B-A3B-Thinking` ### Overview Qwen3-Omni-30B-A3B-Thinking reasons over text, images, audio and video and returns text. This Thinker-only edition suits visual mathematics, audio analysis and questions that need evidence from several modalities; speech generation belongs to a different Omni release. Accepted inputs Text Results Text ### Available in Ailoot · inputs & methods **Ailoot Ultra · OpenAI Chat** `POST /v1/chat/completions` Input types `text` Output types `text` Output format json or SSE | Field | Type | Requirement | Values & limits | Default | | --- | --- | --- | --- | --- | | Field`model` | Type`string` | RequirementRequired | Values & limits Qwen/Qwen3-Omni-30B-A3B-Thinking | Default— | | Field`messages` | Type`message[]` | RequirementRequired | Values & limits Minimum items: 1 | Default— | | Field`messages[].role` | Type`string` | 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— | | Field`messages[].content` | Type`string\|content_part[]\|null` | RequirementOptional | Values & limits | Default— | | Field`messages[].tool_calls` | Type`tool_call[]` | RequirementOptional | Values & limits | Default— | | Field`messages[].tool_call_id` | Type`string` | RequirementOptional | Values & limits Applies when: role=tool; use actual returned ID | Default— | | Field`messages[].name` | Type`string` | RequirementOptional | Values & limits | Default— | | Field`messages[].reasoning_content` | Type`string` | RequirementOptional | Values & limits Applies when: Round-trip actual returned reasoning where this model uses it | Default— | | Field`messages[].reasoning_details` | Type`object\|array` | RequirementOptional | Values & limits Model-specific | Default— | | Field`max_tokens` | Type`integer` | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— | | Field`max_completion_tokens` | Type`integer` | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— | | Field`stream` | Type`boolean` | RequirementOptional | Values & limits | Defaultfalse | | Field`stream_options.include_usage` | Type`boolean` | RequirementOptional | Values & limits Model-specific | Default— | | Field`temperature` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— | | Field`top_p` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— | | Field`stop` | Type`string\|string[]` | RequirementOptional | Values & limits Model-specific | Default— | | Field`tools` | Type`function_tool[]` | RequirementOptional | Values & limits Model-specific | Default— | | Field`tools[].type` | Type`string` | RequirementOptional | Values & limits function Model-specific | Default— | | Field`tools[].function.name` | Type`string` | RequirementRequired | Values & limits Applies when: function tool supplied | Default— | | Field`tools[].function.description` | Type`string` | RequirementOptional | Values & limits | Default— | | Field`tools[].function.parameters` | Type`JSON_schema` | RequirementOptional | Values & limits | Default— | | Field`tool_choice` | Type`string\|object` | RequirementOptional | Values & limits Model-specific | Default— | | Field`parallel_tool_calls` | Type`boolean` | RequirementOptional | Values & limits Model-specific | Default— | | Field`response_format` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— | | Field`reasoning_effort` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— | | Field`reasoning` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— | | Field`service_tier` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— | | Field`instructions` | Type`string` | RequirementOptional | Values & limits Compatibility field | Default— | | Field`functions` | Type`function[]` | RequirementOptional | Values & limits Model-specific | Default— | | Field`function_call` | Type`string\|object` | RequirementOptional | Values & limits Model-specific | Default— | | Field`prompt_cache_options` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— | | Field`modalities` | Type`string[]` | RequirementOptional | Values & limits text | Default— | | Field`provider` | Type`object` | RequirementOptional | Values & limits Conditions: provider.options is rejected on this Ultra text route | Default— | | Field`cache_control.ttl` | Type`string` | RequirementOptional | Values & limits Conditions: 1h is rejected in actual prompt-cache locations | Default— | Input material combinations **Text** · UTF8 text `messages[].content` Method parameters and lifecycle | Parameter | Contract | | --- | --- | | Parameter`content_type` | Contractapplication/json | | Parameter`required` | Contractmodel, messages | | Parameter`material_types` | Contracttext | | Parameter`messages` | Contractmessage array with role/content shape | | Parameter`file_material` | Contractactual UTF-8 document inserted as literal text; no file ID inferred | | Parameter`optional_controls` | Contractstream, temperature, top\_p, stop, max\_tokens, max\_completion\_tokens, reasoning, response\_format, tools, tool\_choice | | Parameter`control_scope` | Contractmodel-specific; user function tools differ from hosted tools | | Parameter`output_modalities` | Contracttext | | Parameter`hosted_operations` | Contractfalse | | Parameter`multimodal_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. ### Pricing Tariff references do not add request options. Supported parameters are listed for the selected method. Fast mode Not specified When fast mode is selected Flex mode Not specified When flex mode is selected Maximum reasoning effort Not specified When maximum reasoning effort uses the default adjustment #### Ailoot rates #### Prices by configuration | Configuration | Rate schedule | Charge | | --- | --- | --- | | ConfigurationBase token rates | Rate scheduleBase rate | Charge Input · Input tokens **$0.0002** / 1K tokens Output · Output tokens **$0.0008** / 1K tokens Input · Cache read **$0** / 1K tokens Input · Cache write **$0** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens | Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. [How reservation and settlement work →](https://ailoot.ai/docs/en/billing/reserve/) ### Example requests #### Ailoot Ultra · OpenAI Chat curlPython SDKPython stream ```bash set -eu : "${AILOOT_API_KEY:?Set your Ailoot API key}" python3 - <<'PY_REQUEST' import json,os from pathlib import Path p=json.loads('{"model": "Qwen/Qwen3-Omni-30B-A3B-Thinking", "messages": [{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}]}') Path("request.json").write_text(json.dumps(p,ensure_ascii=False)) PY_REQUEST curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \ -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \ --data-binary @request.json -D response-headers.txt -o result.json python3 - <<'PY_RESULT' import json from pathlib import Path r=json.loads(Path("result.json").read_text()) for x in r.get("choices",[]): if x.get("message",{}).get("content"): print(x["message"]["content"]) PY_RESULT ``` ```python from openai import OpenAI import os if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request") client=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0) result=client.chat.completions.create(model='Qwen/Qwen3-Omni-30B-A3B-Thinking',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) import base64, json from pathlib import Path def save_result(data, stem="result"): # Keep every field, including usage, IDs, reasoning and tool requests. Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8") print(json.dumps(data, ensure_ascii=False, indent=2)) def save_blob(encoded, suffix, label): raw = base64.b64decode(encoded, altchars=b"-_", validate=True) 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 file = Path(stem + "-" + label + "." + ext) file.write_bytes(raw) print("Saved", file) for index, block in enumerate(data.get("content") or []): print("Content", index, json.dumps(block, ensure_ascii=False)) for choice in data.get("choices") or []: print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False)) for index, item in enumerate(data.get("output") or []): print("Output", index, json.dumps(item, ensure_ascii=False)) if item.get("type") == "image_generation_call" and item.get("result"): save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index)) for ci, candidate in enumerate(data.get("candidates") or []): for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []): print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False)) blob = part.get("inlineData") or part.get("inline_data") if blob and blob.get("data"): mime = blob.get("mimeType") or blob.get("mime_type") suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin") save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi)) save_result(result.to_dict(mode="json")) ``` ```python from openai import OpenAI import os from pathlib import Path if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request") client=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0) import base64, json from pathlib import Path def save_result(data, stem="result"): # Keep every field, including usage, IDs, reasoning and tool requests. Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8") print(json.dumps(data, ensure_ascii=False, indent=2)) def save_blob(encoded, suffix, label): raw = base64.b64decode(encoded, altchars=b"-_", validate=True) 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 file = Path(stem + "-" + label + "." + ext) file.write_bytes(raw) print("Saved", file) for index, block in enumerate(data.get("content") or []): print("Content", index, json.dumps(block, ensure_ascii=False)) for choice in data.get("choices") or []: print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False)) for index, item in enumerate(data.get("output") or []): print("Output", index, json.dumps(item, ensure_ascii=False)) if item.get("type") == "image_generation_call" and item.get("result"): save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index)) for ci, candidate in enumerate(data.get("candidates") or []): for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []): print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False)) blob = part.get("inlineData") or part.get("inline_data") if blob and blob.get("data"): mime = blob.get("mimeType") or blob.get("mime_type") suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin") save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi)) with client.chat.completions.stream(model='Qwen/Qwen3-Omni-30B-A3B-Thinking',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream: with Path("stream-events.jsonl").open("w",encoding="utf-8") as log: for event in stream: payload=event.to_dict(mode="json") log.write(json.dumps(payload,ensure_ascii=False)+"\n"); log.flush() print(json.dumps(payload,ensure_ascii=False)) final=stream.get_final_completion() save_result(final.to_dict(mode="json"),"stream-result") ``` ### Receive and save results #### Ailoot Ultra · OpenAI Chat json or SSE ##### Keep all completed results 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. ##### If the original response needs checking Keep request/response IDs and headers. No generic text job retrieval URL is supplied. Response fields | Field | Type | | --- | --- | | Field`choices[].index` | Typeinteger | | Field`choices[].message.content` | Typestring\|null | | Field`choices[].message.tool_calls` | Typetool\_call\[\] | | Field`choices[].message.reasoning_content` | Typestring | | Field`choices[].message.reasoning_details` | Typeobject\|array | | Field`choices[].finish_reason` | Typestring\|null | | Field`usage` | Typeobject | Errors and next steps | 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. | ### Aliases #### Model aliases **Ailoot Ultra** [`Qwen/Qwen3-Omni-30B-A3B-Thinking`](https://ailoot.ai/models/en/#m=Qwen%2FQwen3-Omni-30B-A3B-Thinking&route=Ultra&caller=Qwen%2FQwen3-Omni-30B-A3B-Thinking&fmt=chat) #### Method path aliases Use the method paths shown above. #### Related caller IDs [`Qwen/Qwen3-Omni-30B-A3B-Thinking`](https://ailoot.ai/models/en/#m=Qwen%2FQwen3-Omni-30B-A3B-Thinking&route=Ultra&caller=Qwen%2FQwen3-Omni-30B-A3B-Thinking&fmt=chat) **Ailoot Ultra · Anthropic Messages** `POST /v1/messages` `Qwen/Qwen3-Omni-30B-A3B-Thinking` [`Qwen/Qwen3-Omni-30B-A3B-Thinking`](https://ailoot.ai/models/en/#m=Qwen%2FQwen3-Omni-30B-A3B-Thinking&route=Ultra&caller=Qwen%2FQwen3-Omni-30B-A3B-Thinking&fmt=messages) Alibaba /`Qwen/Qwen3-Omni-30B-A3B-Thinking` ### Overview Qwen3-Omni-30B-A3B-Thinking reasons over text, images, audio and video and returns text. This Thinker-only edition suits visual mathematics, audio analysis and questions that need evidence from several modalities; speech generation belongs to a different Omni release. Accepted inputs Text Results json · sse ### Available in Ailoot · inputs & methods **Ailoot Ultra · Anthropic Messages** `POST /v1/messages` Input types `text` Output types `json`, `sse` Output format JSON or SSE | Field | Type | Requirement | Values & limits | Default | | --- | --- | --- | --- | --- | | Field`model` | Type`string` | RequirementRequired | Values & limits Qwen/Qwen3-Omni-30B-A3B-Thinking | Default— | | Field`messages` | Type`message[]` | RequirementRequired | Values & limits | Default— | | Field`messages[].role` | Type`string` | RequirementRequired | Values & limits user, assistant | Default— | | Field`messages[].content` | Type`string` | RequirementRequired | Values & limits | Default— | | Field`max_tokens` | Type`integer` | RequirementRequired | Values & limits | Default— | | Field`stream` | Type`boolean` | RequirementOptional | Values & limits | Defaultfalse | Input material combinations **Text** · UTF-8 text `messages[].content string` Method parameters and lifecycle | Parameter | Contract | | --- | --- | | Parameter`content_type` | Contractapplication/json | | Parameter`required` | Contractmodel, messages, max\_tokens | | Parameter`optional_controls` | Contractstream | | Parameter`material_types` | Contracttext | | Parameter`text_file_material` | ContractRead the actual UTF-8 document and put its text in the indicated input or message content string. | Lifecycle: `synchronous_or_streamed` ### Pricing Tariff references do not add request options. Supported parameters are listed for the selected method. Fast mode Not specified When fast mode is selected Flex mode Not specified When flex mode is selected Maximum reasoning effort Not specified When maximum reasoning effort uses the default adjustment #### Ailoot rates #### Prices by configuration | Configuration | Rate schedule | Charge | | --- | --- | --- | | ConfigurationBase token rates | Rate scheduleBase rate | Charge Input · Input tokens **$0.0002** / 1K tokens Output · Output tokens **$0.0008** / 1K tokens Input · Cache read **$0** / 1K tokens Input · Cache write **$0** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens | Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. [How reservation and settlement work →](https://ailoot.ai/docs/en/billing/reserve/) ### Example requests #### Ailoot Ultra · Anthropic Messages Complete minimal JSON bodycurl · use your UTF-8 documentPython · save the complete result ```json { "model": "Qwen/Qwen3-Omni-30B-A3B-Thinking", "max_tokens": 128, "messages": [ { "role": "user", "content": "Summarize the incident report." } ], "stream": false } ``` ```bash set -eu : "${AILOOT_API_KEY:?Set your Ailoot API key}" : "${AILOOT_TEXT_FILE:?Set your actual UTF-8 document}" export AILOOT_TEXT_FILE python3 - <<'PY_REQUEST' import json, os from pathlib import Path source_file = Path(os.environ['AILOOT_TEXT_FILE']) if not source_file.is_file(): raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document') text = source_file.read_text(encoding='utf-8') if not text.strip(): raise SystemExit('Choose a document containing text') payload = {'model': 'Qwen/Qwen3-Omni-30B-A3B-Thinking', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]} payload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\n\n' + text Path('request.json').write_text(json.dumps(payload, ensure_ascii=False), encoding='utf-8') PY_REQUEST curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \ -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \ --data-binary @request.json -D response-headers.txt -o result.json python3 - <<'PY_RESULT' import json from pathlib import Path result = json.loads(Path('result.json').read_text(encoding='utf-8')) print(json.dumps(result, ensure_ascii=False, indent=2)) PY_RESULT ``` ```python import json, os from pathlib import Path source_file = Path(os.environ['AILOOT_TEXT_FILE']) if not source_file.is_file(): raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document') text = source_file.read_text(encoding='utf-8') if not text.strip(): raise SystemExit('Choose a document containing text') payload = {'model': 'Qwen/Qwen3-Omni-30B-A3B-Thinking', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]} payload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\n\n' + text from urllib.request import Request, urlopen from urllib.error import HTTPError api_key = os.environ['AILOOT_API_KEY'] if not api_key.strip(): raise SystemExit('Set AILOOT_API_KEY before making a request') headers = {'x-api-key': 'PLACEHOLDER_KEY', 'anthropic-version': '2023-06-01', 'Content-Type': 'application/json'} headers['x-api-key'] = api_key request = Request('https://api.ailoot.ai/v1/messages', data=json.dumps(payload, ensure_ascii=False).encode('utf-8'), headers=headers, method='POST') try: with urlopen(request, timeout=120) as response: raw = response.read() Path('response-headers.txt').write_text(str(response.headers), encoding='utf-8') except HTTPError as error: Path('result.json').write_bytes(error.read()) Path('response-headers.txt').write_text(str(error.headers), encoding='utf-8') raise Path('result.json').write_bytes(raw) import json from pathlib import Path result = json.loads(Path('result.json').read_text(encoding='utf-8')) print(json.dumps(result, ensure_ascii=False, indent=2)) ``` ### Receive and save results #### Ailoot Ultra · Anthropic Messages JSON or SSE ##### Keep all completed results 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. ##### If the original response needs checking Keep request/response IDs and headers. No generic text job retrieval URL is supplied. Response fields | Field | Type | | --- | --- | | Field`id` | Typestring | | Field`model` | Typestring | | Field`content[]` | Typetext\|thinking\|tool\_use\|other content block | | Field`stop_reason` | Typestring\|null | | Field`usage` | Typeobject | Errors and next steps | 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. | ### Aliases #### Model aliases **Ailoot Ultra** [`Qwen/Qwen3-Omni-30B-A3B-Thinking`](https://ailoot.ai/models/en/#m=Qwen%2FQwen3-Omni-30B-A3B-Thinking&route=Ultra&caller=Qwen%2FQwen3-Omni-30B-A3B-Thinking&fmt=messages) #### Method path aliases Use the method paths shown above. #### Related caller IDs [`Qwen/Qwen3-Omni-30B-A3B-Thinking`](https://ailoot.ai/models/en/#m=Qwen%2FQwen3-Omni-30B-A3B-Thinking&route=Ultra&caller=Qwen%2FQwen3-Omni-30B-A3B-Thinking&fmt=messages) FAQ · Qwen/Qwen3-Omni-30B-A3B-Thinking What inputs and results are available? `POST /v1/chat/completions` · `Qwen/Qwen3-Omni-30B-A3B-Thinking`: `text` → `text` `POST /v1/messages` · `Qwen/Qwen3-Omni-30B-A3B-Thinking`: `text` → `json`, `sse` Which fields does the request use? `POST /v1/chat/completions` · `Qwen/Qwen3-Omni-30B-A3B-Thinking`: `model`, `messages`, `stream`, `modalities`, `provider` `POST /v1/messages` · `Qwen/Qwen3-Omni-30B-A3B-Thinking`: `model`, `messages`, `max_tokens`, `stream` What limits apply? `POST /v1/chat/completions` · `Qwen/Qwen3-Omni-30B-A3B-Thinking`: `messages.min_items`: `1` Connect Ailoot to Claude Code, OpenCode, Hermes or your own app. ## The company and its project portfolio The company and its project portfolio: millions of customers; monthly sales in the billions. ## Buy tokens at a discount. Subscription discounts for regular use. Promo codes offer up to 50% off token purchases. Subscription Choose a discounted plan for your regular requests. Promo code: up to 50% off Enter your code at checkout. The price updates to reflect the current promotion. Spending in your history The model, tokens and amount are recorded for each request. [Choose a subscription](https://ailoot.ai/docs/en/billing/subscriptions/) · [View model prices](https://ailoot.ai/models/en/) ## Connect the API to a product you sell. Use Ailoot in SaaS, apps and bots under its official service offer and licence agreement. Request a reseller licence for resale. Commercial application Add text, image, video and audio generation to paid features in your service. Reseller licence Send a description of your project and how you provide access. Request written terms for use and resale. Documents on the website The service offer, licence agreement and data processing policy are available before you connect. [Request a reseller licence](mailto:support@ailoot.ai) · [Service offer and licence agreement](https://ailoot.ai/legal/offer?lang=en) ## Ailoot · The company and its project portfolio Ailoot combines established operating experience, a large client base, stable service and ongoing KPI control. The company and its project portfolio: millions of customers; monthly sales in the billions. Ailoot brings that operating experience to API access for AI features in customer products, agents, applications and automations.