Qwen3-32B is the largest dense model in the original Qwen3 release. It combines the family’s thinking mode for complex logic, mathematics and coding with non-thinking responses for general conversation. Qwen also highlights creative writing, role-based dialogue, multi-turn instruction following and agent-style tool use. The model processes text and generates text; multilingual instruction and translation are part of the original family’s support for 119 languages and dialects. It can be briefed for an analytical explanation, a coding proposal or a carefully specified piece of writing.
The exact edition has 32.8 billion total parameters across 64 layers. It is a dense model, distinct from Qwen3-30B-A3B’s expert-routing architecture and from later separately named Qwen3 editions. Its native context is 32,768 tokens. Prepare a demanding task with the relevant evidence, requirements and expected result together. For an engineering review, provide the component description, interface constraints and the issue to resolve, then ask for a proposal that identifies assumptions, dependencies and alternatives using only the supplied material where appropriate.
The producer’s chat template enables thinking by default and exposes a hard enable_thinking switch. Hard disabling prevents thinking content altogether. With thinking enabled, /think and /no_think in user or system instructions provide turn-by-turn soft control, and the latest instruction determines the requested behaviour. A soft non-thinking request can leave an empty thinking block; a /think marker cannot override a hard-disabled template. This lets the original model alternate between a direct drafting request and a question that benefits from an extended chain of reasoning, when the prescribed controls are applied.
The generation example parses a <think> section separately from the final answer. Qwen recommends making the final format explicit, such as a boxed mathematical answer or a single answer field for a multiple-choice task. In practical analysis, specify the requested conclusion and the supporting material: for example, a final design choice followed by constraints it satisfies and issues that remain open. Keep the final answer, rather than the earlier thinking content, in subsequent conversation history according to the producer’s guidance. This preserves the result that later questions need without carrying every reasoning step forward.
Tool calling is part of the documented model profile in both modes. Qwen recommends Qwen-Agent for tool-call templates and parsers and demonstrates retrieval, time information and a code interpreter. Define tools clearly, give their argument meanings and tell the model what constitutes a finished task. A useful workflow can ask for selected information to be retrieved, provide the actual returned content and then request a synthesis or a proposed implementation. The model’s requested call and the application’s tool execution are separate stages; the final answer should build on the returned evidence.
For longer inputs, the card documents YaRN extension to 131,072 tokens. The native window is smaller, and static scaling can affect short-input performance. Qwen recommends enabling the extension when a longer context is actually required; the card additionally explains a 40,960-position default prompt-and-output allocation. Select relevant documents and preserve headings, source boundaries and terminology. Leave room for the reasoning and final response, especially when the task requires reconciling several specifications rather than summarising one passage.
The official recommendations are temperature 0.6, top-p 0.95, top-k 20 and min-p 0 for thinking; for non-thinking, temperature 0.7 and top-p 0.8 replace the first two settings. Qwen advises against greedy decoding in thinking mode and notes that a high presence penalty may cause language mixing or reduced quality. It recommends a 32,768-token output allowance for most queries and describes 38,912 for particularly demanding mathematics and programming problems. Those allowances are generation guidance, not a universal hard response limit. A precise brief and a defined final format help focus the model’s available reasoning on the work the reader needs.
", "aboutText": "Qwen3-32B is the largest dense model in the original Qwen3 release. It combines the family’s thinking mode for complex logic, mathematics and coding with non-thinking responses for general conversation. Qwen also highlights creative writing, role-based dialogue, multi-turn instruction following and agent-style tool use. The model processes text and generates text; multilingual instruction and translation are part of the original family’s support for 119 languages and dialects. It can be briefed for an analytical explanation, a coding proposal or a carefully specified piece of writing.\n\nThe exact edition has 32.8 billion total parameters across 64 layers. It is a dense model, distinct from Qwen3-30B-A3B’s expert-routing architecture and from later separately named Qwen3 editions. Its native context is 32,768 tokens. Prepare a demanding task with the relevant evidence, requirements and expected result together. For an engineering review, provide the component description, interface constraints and the issue to resolve, then ask for a proposal that identifies assumptions, dependencies and alternatives using only the supplied material where appropriate.\n\nThe producer’s chat template enables thinking by default and exposes a hard enable_thinking switch. Hard disabling prevents thinking content altogether. With thinking enabled, /think and /no_think in user or system instructions provide turn-by-turn soft control, and the latest instruction determines the requested behaviour. A soft non-thinking request can leave an empty thinking block; a /think marker cannot override a hard-disabled template. This lets the original model alternate between a direct drafting request and a question that benefits from an extended chain of reasoning, when the prescribed controls are applied.\n\nThe generation example parses aTechnical example in English
Review a cache invalidation design\n\nA report cache is keyed only by report name. Reports also depend on account ID and selected month. Two users requesting the same name can receive the wrong account or month. Propose a revised key contract, explain the dependencies it captures and give three text test cases. Use only the described inputs; propose no repository edits.A key contract, dependency explanation and cases distinguishing account and month.Different accounts or months must not share a cache entry solely because the report name matches.qwen/qwen3-32bQwen3-32B is Qwen’s dense hybrid text model for complex reasoning, coding, multilingual writing and tool-directed tasks. It combines thinking and non-thinking modes within one model and has a native 32,768-token context.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Qwen3-32B is the largest dense model in the original Qwen3 release. It combines the family’s thinking mode for complex logic, mathematics and coding with non-thinking responses for general conversation. Qwen also highlights creative writing, role-based dialogue, multi-turn instruction following and agent-style tool use. The model processes text and generates text; multilingual instruction and translation are part of the original family’s support for 119 languages and dialects. It can be briefed for an analytical explanation, a coding proposal or a carefully specified piece of writing.
The exact edition has 32.8 billion total parameters across 64 layers. It is a dense model, distinct from Qwen3-30B-A3B’s expert-routing architecture and from later separately named Qwen3 editions. Its native context is 32,768 tokens. Prepare a demanding task with the relevant evidence, requirements and expected result together. For an engineering review, provide the component description, interface constraints and the issue to resolve, then ask for a proposal that identifies assumptions, dependencies and alternatives using only the supplied material where appropriate.
The producer’s chat template enables thinking by default and exposes a hard enable_thinking switch. Hard disabling prevents thinking content altogether. With thinking enabled, /think and /no_think in user or system instructions provide turn-by-turn soft control, and the latest instruction determines the requested behaviour. A soft non-thinking request can leave an empty thinking block; a /think marker cannot override a hard-disabled template. This lets the original model alternate between a direct drafting request and a question that benefits from an extended chain of reasoning, when the prescribed controls are applied.
The generation example parses a <think> section separately from the final answer. Qwen recommends making the final format explicit, such as a boxed mathematical answer or a single answer field for a multiple-choice task. In practical analysis, specify the requested conclusion and the supporting material: for example, a final design choice followed by constraints it satisfies and issues that remain open. Keep the final answer, rather than the earlier thinking content, in subsequent conversation history according to the producer’s guidance. This preserves the result that later questions need without carrying every reasoning step forward.
Tool calling is part of the documented model profile in both modes. Qwen recommends Qwen-Agent for tool-call templates and parsers and demonstrates retrieval, time information and a code interpreter. Define tools clearly, give their argument meanings and tell the model what constitutes a finished task. A useful workflow can ask for selected information to be retrieved, provide the actual returned content and then request a synthesis or a proposed implementation. The model’s requested call and the application’s tool execution are separate stages; the final answer should build on the returned evidence.
For longer inputs, the card documents YaRN extension to 131,072 tokens. The native window is smaller, and static scaling can affect short-input performance. Qwen recommends enabling the extension when a longer context is actually required; the card additionally explains a 40,960-position default prompt-and-output allocation. Select relevant documents and preserve headings, source boundaries and terminology. Leave room for the reasoning and final response, especially when the task requires reconciling several specifications rather than summarising one passage.
The official recommendations are temperature 0.6, top-p 0.95, top-k 20 and min-p 0 for thinking; for non-thinking, temperature 0.7 and top-p 0.8 replace the first two settings. Qwen advises against greedy decoding in thinking mode and notes that a high presence penalty may cause language mixing or reduced quality. It recommends a 32,768-token output allowance for most queries and describes 38,912 for particularly demanding mathematics and programming problems. Those allowances are generation guidance, not a universal hard response limit. A precise brief and a defined final format help focus the model’s available reasoning on the work the reader needs.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qwen/qwen3-32b | Default— |
Fieldmessages | Typemessage[] | RequirementRequired | Values & limits Minimum items: 1 | Default— |
Fieldmessages[].role | Typestring | RequirementRequired | Values & limits Examples: system, user, assistant, tool, function Conditions: These roles are explicitly represented by Source compatibility types; the exact model role set remains model-specific. Model-specific | Default— |
Fieldmessages[].content | Typestring|content_part[]|null | RequirementOptional | Values & limits | Default— |
Fieldmessages[].tool_calls | Typetool_call[] | RequirementOptional | Values & limits | Default— |
Fieldmessages[].tool_call_id | Typestring | RequirementOptional | Values & limits Applies when: role=tool; use actual returned ID | Default— |
Fieldmessages[].name | Typestring | RequirementOptional | Values & limits | Default— |
Fieldmessages[].reasoning_content | Typestring | RequirementOptional | Values & limits Applies when: Round-trip actual returned reasoning where this model uses it | Default— |
Fieldmessages[].reasoning_details | Typeobject|array | RequirementOptional | Values & limits Model-specific | Default— |
Fieldmax_tokens | Typeinteger | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
Fieldmax_completion_tokens | Typeinteger | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
Fieldstream_options.include_usage | Typeboolean | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtemperature | Typenumber | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtop_p | Typenumber | RequirementOptional | Values & limits Model-specific | Default— |
Fieldstop | Typestring|string[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtools | Typefunction_tool[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtools[].type | Typestring | RequirementOptional | Values & limits function Model-specific | Default— |
Fieldtools[].function.name | Typestring | RequirementRequired | Values & limits Applies when: function tool supplied | Default— |
Fieldtools[].function.description | Typestring | RequirementOptional | Values & limits | Default— |
Fieldtools[].function.parameters | TypeJSON_schema | RequirementOptional | Values & limits | Default— |
Fieldtool_choice | Typestring|object | RequirementOptional | Values & limits Model-specific | Default— |
Fieldparallel_tool_calls | Typeboolean | RequirementOptional | Values & limits Model-specific | Default— |
Fieldresponse_format | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Fieldreasoning_effort | Typestring | RequirementOptional | Values & limits Model-specific | Default— |
Fieldreasoning | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Fieldservice_tier | Typestring | RequirementOptional | Values & limits Model-specific | Default— |
Fieldinstructions | Typestring | RequirementOptional | Values & limits Compatibility field | Default— |
Fieldfunctions | Typefunction[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldfunction_call | Typestring|object | RequirementOptional | Values & limits Model-specific | Default— |
Fieldprompt_cache_options | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Fieldmodalities | Typestring[] | RequirementOptional | Values & limits text | Default— |
Fieldprovider | Typeobject | RequirementOptional | Values & limits Conditions: provider.options is rejected on this Ultra text route | Default— |
Fieldcache_control.ttl | Typestring | RequirementOptional | Values & limits Conditions: 1h is rejected in actual prompt-cache locations | Default— |
Text · UTF8 text
messages[].content
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, messages |
Parametermaterial_types | Contracttext |
Parametermessages | Contractmessage array with role/content shape |
Parameterfile_material | Contractactual UTF-8 document inserted as literal text; no file ID inferred |
Parameteroptional_controls | Contractstream, temperature, top_p, stop, max_tokens, max_completion_tokens, reasoning, response_format, tools, tool_choice |
Parametercontrol_scope | Contractmodel-specific; user function tools differ from hosted tools |
Parameteroutput_modalities | Contracttext |
Parameterhosted_operations | Contractfalse |
Parametermultimodal_input_binding | Contractnull |
Lifecycle: synchronous_or_streamed
Send exact model ID with messages.
Context length is not an output cap.
A text file may supply literal text; image/audio/file-object inputs need exact binding.
Tariff references do not add request options. Supported parameters are listed for the selected method.
Match each charge to the conditions shown. Use one rate for each set of alternative configurations.
| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
|---|---|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.000286 / 1K tokens Output · Output tokens $0.001144 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationRequest-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.000286 / 1K tokens Output · Output tokens $0.001144 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "qwen/qwen3-32b", "messages": [{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}]}')\n\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path("result.json").read_text())\nfor x in r.get("choices",[]):\n if x.get("message",{}).get("content"): print(x["message"]["content"])\nPY_RESULT\nfrom openai import OpenAI\nimport os\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nresult=client.chat.completions.create(model='qwen/qwen3-32b',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}])\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(result.to_dict(mode="json"))\nfrom openai import OpenAI\nimport os\nfrom pathlib import Path\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nwith client.chat.completions.stream(model='qwen/qwen3-32b',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:\n with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:\n for event in stream:\n payload=event.to_dict(mode="json")\n log.write(json.dumps(payload,ensure_ascii=False)+"\\n"); log.flush()\n print(json.dumps(payload,ensure_ascii=False))\n final=stream.get_final_completion()\n save_result(final.to_dict(mode="json"),"stream-result")\njson or SSE
Keep every complete returned response, file and content part.
Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.
Keep request/response IDs and headers. No generic text job retrieval URL is supplied.
| Field | Type |
|---|---|
Fieldchoices[].index | Typeinteger |
Fieldchoices[].message.content | Typestring|null |
Fieldchoices[].message.tool_calls | Typetool_call[] |
Fieldchoices[].message.reasoning_content | Typestring |
Fieldchoices[].message.reasoning_details | Typeobject|array |
Fieldchoices[].finish_reason | Typestring|null |
Fieldusage | Typeobject |
| Response | Condition | Next step |
|---|---|---|
Response400 · invalid_request_error | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |
Ailoot Ultra qwen/qwen3-32b
Use the method paths shown above.
qwen/qwen3-32bQwen3-32B is Qwen’s dense hybrid text model for complex reasoning, coding, multilingual writing and tool-directed tasks. It combines thinking and non-thinking modes within one model and has a native 32,768-token context.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Qwen3-32B is the largest dense model in the original Qwen3 release. It combines the family’s thinking mode for complex logic, mathematics and coding with non-thinking responses for general conversation. Qwen also highlights creative writing, role-based dialogue, multi-turn instruction following and agent-style tool use. The model processes text and generates text; multilingual instruction and translation are part of the original family’s support for 119 languages and dialects. It can be briefed for an analytical explanation, a coding proposal or a carefully specified piece of writing.
The exact edition has 32.8 billion total parameters across 64 layers. It is a dense model, distinct from Qwen3-30B-A3B’s expert-routing architecture and from later separately named Qwen3 editions. Its native context is 32,768 tokens. Prepare a demanding task with the relevant evidence, requirements and expected result together. For an engineering review, provide the component description, interface constraints and the issue to resolve, then ask for a proposal that identifies assumptions, dependencies and alternatives using only the supplied material where appropriate.
The producer’s chat template enables thinking by default and exposes a hard enable_thinking switch. Hard disabling prevents thinking content altogether. With thinking enabled, /think and /no_think in user or system instructions provide turn-by-turn soft control, and the latest instruction determines the requested behaviour. A soft non-thinking request can leave an empty thinking block; a /think marker cannot override a hard-disabled template. This lets the original model alternate between a direct drafting request and a question that benefits from an extended chain of reasoning, when the prescribed controls are applied.
The generation example parses a <think> section separately from the final answer. Qwen recommends making the final format explicit, such as a boxed mathematical answer or a single answer field for a multiple-choice task. In practical analysis, specify the requested conclusion and the supporting material: for example, a final design choice followed by constraints it satisfies and issues that remain open. Keep the final answer, rather than the earlier thinking content, in subsequent conversation history according to the producer’s guidance. This preserves the result that later questions need without carrying every reasoning step forward.
Tool calling is part of the documented model profile in both modes. Qwen recommends Qwen-Agent for tool-call templates and parsers and demonstrates retrieval, time information and a code interpreter. Define tools clearly, give their argument meanings and tell the model what constitutes a finished task. A useful workflow can ask for selected information to be retrieved, provide the actual returned content and then request a synthesis or a proposed implementation. The model’s requested call and the application’s tool execution are separate stages; the final answer should build on the returned evidence.
For longer inputs, the card documents YaRN extension to 131,072 tokens. The native window is smaller, and static scaling can affect short-input performance. Qwen recommends enabling the extension when a longer context is actually required; the card additionally explains a 40,960-position default prompt-and-output allocation. Select relevant documents and preserve headings, source boundaries and terminology. Leave room for the reasoning and final response, especially when the task requires reconciling several specifications rather than summarising one passage.
The official recommendations are temperature 0.6, top-p 0.95, top-k 20 and min-p 0 for thinking; for non-thinking, temperature 0.7 and top-p 0.8 replace the first two settings. Qwen advises against greedy decoding in thinking mode and notes that a high presence penalty may cause language mixing or reduced quality. It recommends a 32,768-token output allowance for most queries and describes 38,912 for particularly demanding mathematics and programming problems. Those allowances are generation guidance, not a universal hard response limit. A precise brief and a defined final format help focus the model’s available reasoning on the work the reader needs.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qwen/qwen3-32b | Default— |
Fieldmessages | Typemessage[] | RequirementRequired | Values & limits | Default— |
Fieldmessages[].role | Typestring | RequirementRequired | Values & limits user, assistant | Default— |
Fieldmessages[].content | Typestring | RequirementRequired | Values & limits | Default— |
Fieldmax_tokens | Typeinteger | RequirementRequired | Values & limits | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
Text · UTF-8 text
messages[].content string
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, messages, max_tokens |
Parameteroptional_controls | Contractstream |
Parametermaterial_types | Contracttext |
Parametertext_file_material | ContractRead the actual UTF-8 document and put its text in the indicated input or message content string. |
Lifecycle: synchronous_or_streamed
Tariff references do not add request options. Supported parameters are listed for the selected method.
Match each charge to the conditions shown. Use one rate for each set of alternative configurations.
| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
|---|---|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.000286 / 1K tokens Output · Output tokens $0.001144 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationRequest-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.000286 / 1K tokens Output · Output tokens $0.001144 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "qwen/qwen3-32b",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 document}"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ['AILOOT_TEXT_FILE'])\nif not source_file.is_file():\n raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')\ntext = source_file.read_text(encoding='utf-8')\nif not text.strip():\n raise SystemExit('Choose a document containing text')\npayload = {'model': 'qwen/qwen3-32b', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}\npayload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\\n\\n' + text\nPath('request.json').write_text(json.dumps(payload, ensure_ascii=False), encoding='utf-8')\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\n\nresult = json.loads(Path('result.json').read_text(encoding='utf-8'))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\nPY_RESULT\nimport json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ['AILOOT_TEXT_FILE'])\nif not source_file.is_file():\n raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')\ntext = source_file.read_text(encoding='utf-8')\nif not text.strip():\n raise SystemExit('Choose a document containing text')\npayload = {'model': 'qwen/qwen3-32b', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}\npayload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\\n\\n' + text\nfrom urllib.request import Request, urlopen\nfrom urllib.error import HTTPError\n\napi_key = os.environ['AILOOT_API_KEY']\nif not api_key.strip():\n raise SystemExit('Set AILOOT_API_KEY before making a request')\nheaders = {'x-api-key': 'PLACEHOLDER_KEY', 'anthropic-version': '2023-06-01', 'Content-Type': 'application/json'}\nheaders['x-api-key'] = api_key\nrequest = Request('https://api.ailoot.ai/v1/messages', data=json.dumps(payload, ensure_ascii=False).encode('utf-8'), headers=headers, method='POST')\ntry:\n with urlopen(request, timeout=120) as response:\n raw = response.read()\n Path('response-headers.txt').write_text(str(response.headers), encoding='utf-8')\nexcept HTTPError as error:\n Path('result.json').write_bytes(error.read())\n Path('response-headers.txt').write_text(str(error.headers), encoding='utf-8')\n raise\nPath('result.json').write_bytes(raw)\nimport json\nfrom pathlib import Path\n\nresult = json.loads(Path('result.json').read_text(encoding='utf-8'))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\nJSON or SSE
Keep every complete returned response, file and content part.
Keep all content blocks, thinking signatures and actual tool-use IDs. Assemble all SSE block deltas; a first text block is not the complete output.
Keep request/response IDs and headers. No generic text job retrieval URL is supplied.
| Field | Type |
|---|---|
Fieldid | Typestring |
Fieldmodel | Typestring |
Fieldcontent[] | Typetext|thinking|tool_use|other content block |
Fieldstop_reason | Typestring|null |
Fieldusage | Typeobject |
| Response | Condition | Next step |
|---|---|---|
Response400 · invalid_request_error | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |
Ailoot Ultra qwen/qwen3-32b
Use the method paths shown above.
Technical example in English
Review a cache invalidation design\n\nA report cache is keyed only by report name. Reports also depend on account ID and selected month. Two users requesting the same name can receive the wrong account or month. Propose a revised key contract, explain the dependencies it captures and give three text test cases. Use only the described inputs; propose no repository edits.A key contract, dependency explanation and cases distinguishing account and month.Different accounts or months must not share a cache entry solely because the report name matches.