Qwen-Max is a large-scale text model in the Qwen family for tasks that combine language understanding, logical reasoning and a substantial written result. Its maker highlights Chinese and English coding, multilingual work, creative writing and role-based conversation. The model is designed to produce clearer, more detailed answers while following the requested response style.
The model name is updated on a rolling basis. The maker currently describes qwen-max as functionally equivalent to the qwen-max-2025-01-25 snapshot. The rolling name and the dated snapshot have different purposes: one follows the line as it evolves, while the other identifies a particular edition. Preserve that distinction when comparing repeated tasks or maintaining a consistent assistant configuration.
Model capabilities
Qwen-Max accepts text and produces text. It can work with a conversation, source passages, a software requirement or an existing code fragment. Use it when the result should be an explanation, a rewritten document, an implementation or a set of extracted fields. A scanned page or a screenshot needs a separate step that makes the required information available as text; this model's documented input is not an image.
The maker particularly identifies adherence to JSON formatting. A practical extraction task can specify fields such as a topic, the conditions explicitly mentioned in the source, and an unresolved question. Supply the source passage and the intended field names, and state how to represent missing information. This turns a conversational answer into data that an application can inspect and process. A request for JSON and a request for a prose explanation are different output requirements and should be stated separately.
The documented interfaces also include function calling, structured output, response-prefix continuation, context caching and batch inference. Function calls and web search are not exposed identically in every producer configuration. Treat them as options of the surrounding interface: the application supplies the tools, executes selected actions and returns their results. Caching and batch processing concern how work is submitted and reused, not a new content modality.
Context limits
The published specification lists a 32,768-token context window, a maximum input of 30,720 tokens and a maximum output of 8,192 tokens. Keep the source material, conversation and requested answer within the applicable limits. The output ceiling is useful for choosing between a compact answer and a long document: it should not be interpreted as a guarantee that every response will use that length.
For a document task, place the essential source sections before optional examples and state what the final artifact must contain. For example: provide a product description and a customer's questions, then request an answer that retains the supplied conditions, uses the customer's language and separates unanswered questions from confirmed information. The result can be a client-facing reply plus a small JSON record for the next step of the application.
For coding, provide the function's purpose, the accepted input, expected output and the existing fragment that must remain compatible. Ask for the implementation, an explanation of the decisions and examples covering an ordinary input and a boundary case. This uses the model's documented coding and reasoning focus without assuming access to a repository, a compiler or a running application.
For creative writing or role-based dialogue, define the audience, tone and facts that must survive revision. A role can organize the conversation, while the source material determines what the model should say. Request alternative introductions or explanations for different readers rather than an unspecified rewrite; each variant then has an observable purpose.
Meaningful limits
Qwen-Max is a text-to-text line, not a visual or speech-generation edition. The maker does not list fine-tuning as a supported interface capability on this card. Tool-enabled behavior depends on the connected interface, and the rolling name does not lock a permanent snapshot. These distinctions help select the right edition and prepare an input that matches the result you actually need.
", "aboutText": "Qwen-Max is a large-scale text model in the Qwen family for tasks that combine language understanding, logical reasoning and a substantial written result. Its maker highlights Chinese and English coding, multilingual work, creative writing and role-based conversation. The model is designed to produce clearer, more detailed answers while following the requested response style.\n\nThe model name is updated on a rolling basis. The maker currently describes qwen-max as functionally equivalent to the qwen-max-2025-01-25 snapshot. The rolling name and the dated snapshot have different purposes: one follows the line as it evolves, while the other identifies a particular edition. Preserve that distinction when comparing repeated tasks or maintaining a consistent assistant configuration.\n\nModel capabilities\n\nQwen-Max accepts text and produces text. It can work with a conversation, source passages, a software requirement or an existing code fragment. Use it when the result should be an explanation, a rewritten document, an implementation or a set of extracted fields. A scanned page or a screenshot needs a separate step that makes the required information available as text; this model's documented input is not an image.\n\nThe maker particularly identifies adherence to JSON formatting. A practical extraction task can specify fields such as a topic, the conditions explicitly mentioned in the source, and an unresolved question. Supply the source passage and the intended field names, and state how to represent missing information. This turns a conversational answer into data that an application can inspect and process. A request for JSON and a request for a prose explanation are different output requirements and should be stated separately.\n\nThe documented interfaces also include function calling, structured output, response-prefix continuation, context caching and batch inference. Function calls and web search are not exposed identically in every producer configuration. Treat them as options of the surrounding interface: the application supplies the tools, executes selected actions and returns their results. Caching and batch processing concern how work is submitted and reused, not a new content modality.\n\nContext limits\n\nThe published specification lists a 32,768-token context window, a maximum input of 30,720 tokens and a maximum output of 8,192 tokens. Keep the source material, conversation and requested answer within the applicable limits. The output ceiling is useful for choosing between a compact answer and a long document: it should not be interpreted as a guarantee that every response will use that length.\n\nFor a document task, place the essential source sections before optional examples and state what the final artifact must contain. For example: provide a product description and a customer's questions, then request an answer that retains the supplied conditions, uses the customer's language and separates unanswered questions from confirmed information. The result can be a client-facing reply plus a small JSON record for the next step of the application.\n\nFor coding, provide the function's purpose, the accepted input, expected output and the existing fragment that must remain compatible. Ask for the implementation, an explanation of the decisions and examples covering an ordinary input and a boundary case. This uses the model's documented coding and reasoning focus without assuming access to a repository, a compiler or a running application.\n\nFor creative writing or role-based dialogue, define the audience, tone and facts that must survive revision. A role can organize the conversation, while the source material determines what the model should say. Request alternative introductions or explanations for different readers rather than an unspecified rewrite; each variant then has an observable purpose.\n\nMeaningful limits\n\nQwen-Max is a text-to-text line, not a visual or speech-generation edition. The maker does not list fine-tuning as a supported interface capability on this card. Tool-enabled behavior depends on the connected interface, and the rolling name does not lock a permanent snapshot. These distinctions help select the right edition and prepare an input that matches the result you actually need.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "15a73674b0666b687d2b6fdc245e40f66f0033b7c4d5ceada2cfcd6cb7858036", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "en", "methods": [ { "html": "qwen-max-latestQwen-Max is a text model for multilingual conversation, logical reasoning, coding and content creation. It combines detailed instruction following with JSON-oriented output and control over response style.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Qwen-Max is a large-scale text model in the Qwen family for tasks that combine language understanding, logical reasoning and a substantial written result. Its maker highlights Chinese and English coding, multilingual work, creative writing and role-based conversation. The model is designed to produce clearer, more detailed answers while following the requested response style.
The model name is updated on a rolling basis. The maker currently describes qwen-max as functionally equivalent to the qwen-max-2025-01-25 snapshot. The rolling name and the dated snapshot have different purposes: one follows the line as it evolves, while the other identifies a particular edition. Preserve that distinction when comparing repeated tasks or maintaining a consistent assistant configuration.
Model capabilities
Qwen-Max accepts text and produces text. It can work with a conversation, source passages, a software requirement or an existing code fragment. Use it when the result should be an explanation, a rewritten document, an implementation or a set of extracted fields. A scanned page or a screenshot needs a separate step that makes the required information available as text; this model's documented input is not an image.
The maker particularly identifies adherence to JSON formatting. A practical extraction task can specify fields such as a topic, the conditions explicitly mentioned in the source, and an unresolved question. Supply the source passage and the intended field names, and state how to represent missing information. This turns a conversational answer into data that an application can inspect and process. A request for JSON and a request for a prose explanation are different output requirements and should be stated separately.
The documented interfaces also include function calling, structured output, response-prefix continuation, context caching and batch inference. Function calls and web search are not exposed identically in every producer configuration. Treat them as options of the surrounding interface: the application supplies the tools, executes selected actions and returns their results. Caching and batch processing concern how work is submitted and reused, not a new content modality.
Context limits
The published specification lists a 32,768-token context window, a maximum input of 30,720 tokens and a maximum output of 8,192 tokens. Keep the source material, conversation and requested answer within the applicable limits. The output ceiling is useful for choosing between a compact answer and a long document: it should not be interpreted as a guarantee that every response will use that length.
For a document task, place the essential source sections before optional examples and state what the final artifact must contain. For example: provide a product description and a customer's questions, then request an answer that retains the supplied conditions, uses the customer's language and separates unanswered questions from confirmed information. The result can be a client-facing reply plus a small JSON record for the next step of the application.
For coding, provide the function's purpose, the accepted input, expected output and the existing fragment that must remain compatible. Ask for the implementation, an explanation of the decisions and examples covering an ordinary input and a boundary case. This uses the model's documented coding and reasoning focus without assuming access to a repository, a compiler or a running application.
For creative writing or role-based dialogue, define the audience, tone and facts that must survive revision. A role can organize the conversation, while the source material determines what the model should say. Request alternative introductions or explanations for different readers rather than an unspecified rewrite; each variant then has an observable purpose.
Meaningful limits
Qwen-Max is a text-to-text line, not a visual or speech-generation edition. The maker does not list fine-tuning as a supported interface capability on this card. Tool-enabled behavior depends on the connected interface, and the rolling name does not lock a permanent snapshot. These distinctions help select the right edition and prepare an input that matches the result you actually need.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qwen-max-latest | Default— |
Fieldmessages | Typemessage[] | RequirementRequired | Values & limits Minimum items: 1 | Default— |
Fieldmessages[].role | Typestring | RequirementRequired | Values & limits Model-specific | Default— |
Fieldmessages[].content | Typestring | RequirementOptional | Values & limits Applies when: Text conversation | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
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 |
Parametercontrol_scope | ContractText conversation; stream is a boolean and defaults to false. |
Parameteroutput_modalities | Contracttext |
Parameterhosted_operations | Contractfalse |
Parametermultimodal_input_binding | Contractnull |
Method aliases: /chat/completions
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 $0.000686 / 1K tokens Output · Output tokens $0.002744 / 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-max-latest","messages":[{"role":"user","content":"hello"}],"stream":false}')\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-max-latest", messages=[{"role":"user","content":"hello"}], stream=False)\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"))\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-max-latest
/chat/completions
qwen-max-latestQwen-Max is a text model for multilingual conversation, logical reasoning, coding and content creation. It combines detailed instruction following with JSON-oriented output and control over response style.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Qwen-Max is a large-scale text model in the Qwen family for tasks that combine language understanding, logical reasoning and a substantial written result. Its maker highlights Chinese and English coding, multilingual work, creative writing and role-based conversation. The model is designed to produce clearer, more detailed answers while following the requested response style.
The model name is updated on a rolling basis. The maker currently describes qwen-max as functionally equivalent to the qwen-max-2025-01-25 snapshot. The rolling name and the dated snapshot have different purposes: one follows the line as it evolves, while the other identifies a particular edition. Preserve that distinction when comparing repeated tasks or maintaining a consistent assistant configuration.
Model capabilities
Qwen-Max accepts text and produces text. It can work with a conversation, source passages, a software requirement or an existing code fragment. Use it when the result should be an explanation, a rewritten document, an implementation or a set of extracted fields. A scanned page or a screenshot needs a separate step that makes the required information available as text; this model's documented input is not an image.
The maker particularly identifies adherence to JSON formatting. A practical extraction task can specify fields such as a topic, the conditions explicitly mentioned in the source, and an unresolved question. Supply the source passage and the intended field names, and state how to represent missing information. This turns a conversational answer into data that an application can inspect and process. A request for JSON and a request for a prose explanation are different output requirements and should be stated separately.
The documented interfaces also include function calling, structured output, response-prefix continuation, context caching and batch inference. Function calls and web search are not exposed identically in every producer configuration. Treat them as options of the surrounding interface: the application supplies the tools, executes selected actions and returns their results. Caching and batch processing concern how work is submitted and reused, not a new content modality.
Context limits
The published specification lists a 32,768-token context window, a maximum input of 30,720 tokens and a maximum output of 8,192 tokens. Keep the source material, conversation and requested answer within the applicable limits. The output ceiling is useful for choosing between a compact answer and a long document: it should not be interpreted as a guarantee that every response will use that length.
For a document task, place the essential source sections before optional examples and state what the final artifact must contain. For example: provide a product description and a customer's questions, then request an answer that retains the supplied conditions, uses the customer's language and separates unanswered questions from confirmed information. The result can be a client-facing reply plus a small JSON record for the next step of the application.
For coding, provide the function's purpose, the accepted input, expected output and the existing fragment that must remain compatible. Ask for the implementation, an explanation of the decisions and examples covering an ordinary input and a boundary case. This uses the model's documented coding and reasoning focus without assuming access to a repository, a compiler or a running application.
For creative writing or role-based dialogue, define the audience, tone and facts that must survive revision. A role can organize the conversation, while the source material determines what the model should say. Request alternative introductions or explanations for different readers rather than an unspecified rewrite; each variant then has an observable purpose.
Meaningful limits
Qwen-Max is a text-to-text line, not a visual or speech-generation edition. The maker does not list fine-tuning as a supported interface capability on this card. Tool-enabled behavior depends on the connected interface, and the rolling name does not lock a permanent snapshot. These distinctions help select the right edition and prepare an input that matches the result you actually need.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qwen-max-latest | 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 $0.000686 / 1K tokens Output · Output tokens $0.002744 / 1K tokens Input · Cache read $0 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "qwen-max-latest",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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-max-latest', '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-max-latest', '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-max-latest
/chat/completions