Qwen3-14B is a dense language model in the original Qwen3 release, combining thinking and non-thinking behaviour in one model. Qwen positions the family for logical reasoning, mathematics, coding, creative writing, role-based dialogue and instruction following. It accepts text and returns text, with multilingual instruction and translation capabilities across the family’s 119 languages and dialects. A useful conversation brief specifies the language, the reader’s level of knowledge and the exact result: an explanation, a rewrite, a worked problem or a proposed code change.
The instruction-trained model contains 14.8 billion total parameters in 40 layers. It is the dense 14B edition, rather than a mixture-of-experts model or a later model with a similar family name. Its native context is 32,768 tokens. For a document task, include the relevant passages and their headings, then ask for the specific comparison or explanation needed. For example, a brief can provide two versions of a process and ask for a table of changed conditions, followed by a revised procedure that preserves the stated exceptions. Ask for the revised procedure to retain the source headings and identify the changed conditions.
Thinking is enabled by default in the producer’s chat template. The hard enable_thinking=False setting disables the reasoning section completely. If thinking remains enabled, /think or /no_think in the prompt or system instruction can change the requested mode from turn to turn; the latest instruction applies. An enabled template can still return an empty <think> block for a soft non-thinking request. The hard-disabled setting cannot be reversed by adding /think to the text. Select the mode to match the problem: a direct rewrite can use a different response style from a multi-step mathematical explanation.
The official generation example separates thinking content from the final answer. To make that final answer useful, supply the premises or source material and define its structure before generation. Qwen recommends a boxed final result for mathematics and an explicit answer field for multiple-choice questions. In a teaching brief, one can similarly ask for the result, the essential explanation and one worked example. For multi-turn conversations, the producer recommends keeping the final answer in history while omitting the earlier thinking content, so later questions build on the delivered result.
Qwen describes agent and tool-calling capabilities in both thinking and non-thinking modes. Its recommended Qwen-Agent integration provides templates and parsers for defined tools, including retrieval and a code interpreter in the example. An application can give the model named tools, their accepted arguments and a stopping condition. For a code investigation, prepare the source excerpt and failure details, ask it to identify any required check and then return the actual tool result for interpretation. The final response can be a diagnosis, a proposed change and any remaining questions tied to the supplied evidence.
The producer validates a 131,072-token extension with YaRN, separate from the native window. It cautions that static scaling may affect short-input behaviour and recommends configuring it when longer contexts are required. Its card also explains a 40,960-position default allocation for typical prompt and output lengths. Organise long input into named sections and reserve space for reasoning and the final deliverable instead of filling every position with background material. The extended setting depends on the prescribed configuration.
Qwen recommends temperature 0.6 and top-p 0.95 for thinking, and 0.7 and 0.8 for non-thinking, with top-k 20 and min-p 0 in both cases. It warns against greedy decoding in thinking mode because of possible degradation and repetition. Its recommended output allowance is 32,768 tokens for most queries, with 38,912 described for especially complex mathematics and programming tasks. These recommendations guide generation; they do not define an independent fixed response limit. Explicit language and formatting instructions are especially useful when a result must remain consistent across a multilingual conversation.
", "aboutText": "Qwen3-14B is a dense language model in the original Qwen3 release, combining thinking and non-thinking behaviour in one model. Qwen positions the family for logical reasoning, mathematics, coding, creative writing, role-based dialogue and instruction following. It accepts text and returns text, with multilingual instruction and translation capabilities across the family’s 119 languages and dialects. A useful conversation brief specifies the language, the reader’s level of knowledge and the exact result: an explanation, a rewrite, a worked problem or a proposed code change.\n\nThe instruction-trained model contains 14.8 billion total parameters in 40 layers. It is the dense 14B edition, rather than a mixture-of-experts model or a later model with a similar family name. Its native context is 32,768 tokens. For a document task, include the relevant passages and their headings, then ask for the specific comparison or explanation needed. For example, a brief can provide two versions of a process and ask for a table of changed conditions, followed by a revised procedure that preserves the stated exceptions. Ask for the revised procedure to retain the source headings and identify the changed conditions.\n\nThinking is enabled by default in the producer’s chat template. The hard enable_thinking=False setting disables the reasoning section completely. If thinking remains enabled, /think or /no_think in the prompt or system instruction can change the requested mode from turn to turn; the latest instruction applies. An enabled template can still return an emptyTechnical example in English
Explain a changed approval rule\n\nCompare procedure V1: 'All purchase requests need manager approval.' V2: 'Requests above 100 credits need manager approval; smaller requests go directly to purchasing.' Explain the change to a new coordinator, give examples for 80 and 120 credits and identify the unanswered rule for exactly 100 credits. Keep the two versions distinct.A brief explanation, two worked examples and one boundary clarification.The answer must not invent the exactly-100-credit rule absent from V2.qwen/qwen3-14bQwen3-14B is Qwen’s dense text model for multilingual conversation, writing, coding and step-by-step reasoning. Its original hybrid design switches between thinking and direct-answer modes 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.
Qwen3-14B is a dense language model in the original Qwen3 release, combining thinking and non-thinking behaviour in one model. Qwen positions the family for logical reasoning, mathematics, coding, creative writing, role-based dialogue and instruction following. It accepts text and returns text, with multilingual instruction and translation capabilities across the family’s 119 languages and dialects. A useful conversation brief specifies the language, the reader’s level of knowledge and the exact result: an explanation, a rewrite, a worked problem or a proposed code change.
The instruction-trained model contains 14.8 billion total parameters in 40 layers. It is the dense 14B edition, rather than a mixture-of-experts model or a later model with a similar family name. Its native context is 32,768 tokens. For a document task, include the relevant passages and their headings, then ask for the specific comparison or explanation needed. For example, a brief can provide two versions of a process and ask for a table of changed conditions, followed by a revised procedure that preserves the stated exceptions. Ask for the revised procedure to retain the source headings and identify the changed conditions.
Thinking is enabled by default in the producer’s chat template. The hard enable_thinking=False setting disables the reasoning section completely. If thinking remains enabled, /think or /no_think in the prompt or system instruction can change the requested mode from turn to turn; the latest instruction applies. An enabled template can still return an empty <think> block for a soft non-thinking request. The hard-disabled setting cannot be reversed by adding /think to the text. Select the mode to match the problem: a direct rewrite can use a different response style from a multi-step mathematical explanation.
The official generation example separates thinking content from the final answer. To make that final answer useful, supply the premises or source material and define its structure before generation. Qwen recommends a boxed final result for mathematics and an explicit answer field for multiple-choice questions. In a teaching brief, one can similarly ask for the result, the essential explanation and one worked example. For multi-turn conversations, the producer recommends keeping the final answer in history while omitting the earlier thinking content, so later questions build on the delivered result.
Qwen describes agent and tool-calling capabilities in both thinking and non-thinking modes. Its recommended Qwen-Agent integration provides templates and parsers for defined tools, including retrieval and a code interpreter in the example. An application can give the model named tools, their accepted arguments and a stopping condition. For a code investigation, prepare the source excerpt and failure details, ask it to identify any required check and then return the actual tool result for interpretation. The final response can be a diagnosis, a proposed change and any remaining questions tied to the supplied evidence.
The producer validates a 131,072-token extension with YaRN, separate from the native window. It cautions that static scaling may affect short-input behaviour and recommends configuring it when longer contexts are required. Its card also explains a 40,960-position default allocation for typical prompt and output lengths. Organise long input into named sections and reserve space for reasoning and the final deliverable instead of filling every position with background material. The extended setting depends on the prescribed configuration.
Qwen recommends temperature 0.6 and top-p 0.95 for thinking, and 0.7 and 0.8 for non-thinking, with top-k 20 and min-p 0 in both cases. It warns against greedy decoding in thinking mode because of possible degradation and repetition. Its recommended output allowance is 32,768 tokens for most queries, with 38,912 described for especially complex mathematics and programming tasks. These recommendations guide generation; they do not define an independent fixed response limit. Explicit language and formatting instructions are especially useful when a result must remain consistent across a multilingual conversation.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qwen/qwen3-14b | 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 $0.0002 / 1K tokens Output · Output tokens $0.00058 / 1K tokens Input · Cache read $0 / 1K tokens Input · Cache write $0 / 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 $0.0002 / 1K tokens Output · Output tokens $0.00058 / 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/qwen3-14b", "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/qwen3-14b',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/qwen3-14b',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/qwen3-14b
Use the method paths shown above.
qwen/qwen3-14bQwen3-14B is Qwen’s dense text model for multilingual conversation, writing, coding and step-by-step reasoning. Its original hybrid design switches between thinking and direct-answer modes 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.
Qwen3-14B is a dense language model in the original Qwen3 release, combining thinking and non-thinking behaviour in one model. Qwen positions the family for logical reasoning, mathematics, coding, creative writing, role-based dialogue and instruction following. It accepts text and returns text, with multilingual instruction and translation capabilities across the family’s 119 languages and dialects. A useful conversation brief specifies the language, the reader’s level of knowledge and the exact result: an explanation, a rewrite, a worked problem or a proposed code change.
The instruction-trained model contains 14.8 billion total parameters in 40 layers. It is the dense 14B edition, rather than a mixture-of-experts model or a later model with a similar family name. Its native context is 32,768 tokens. For a document task, include the relevant passages and their headings, then ask for the specific comparison or explanation needed. For example, a brief can provide two versions of a process and ask for a table of changed conditions, followed by a revised procedure that preserves the stated exceptions. Ask for the revised procedure to retain the source headings and identify the changed conditions.
Thinking is enabled by default in the producer’s chat template. The hard enable_thinking=False setting disables the reasoning section completely. If thinking remains enabled, /think or /no_think in the prompt or system instruction can change the requested mode from turn to turn; the latest instruction applies. An enabled template can still return an empty <think> block for a soft non-thinking request. The hard-disabled setting cannot be reversed by adding /think to the text. Select the mode to match the problem: a direct rewrite can use a different response style from a multi-step mathematical explanation.
The official generation example separates thinking content from the final answer. To make that final answer useful, supply the premises or source material and define its structure before generation. Qwen recommends a boxed final result for mathematics and an explicit answer field for multiple-choice questions. In a teaching brief, one can similarly ask for the result, the essential explanation and one worked example. For multi-turn conversations, the producer recommends keeping the final answer in history while omitting the earlier thinking content, so later questions build on the delivered result.
Qwen describes agent and tool-calling capabilities in both thinking and non-thinking modes. Its recommended Qwen-Agent integration provides templates and parsers for defined tools, including retrieval and a code interpreter in the example. An application can give the model named tools, their accepted arguments and a stopping condition. For a code investigation, prepare the source excerpt and failure details, ask it to identify any required check and then return the actual tool result for interpretation. The final response can be a diagnosis, a proposed change and any remaining questions tied to the supplied evidence.
The producer validates a 131,072-token extension with YaRN, separate from the native window. It cautions that static scaling may affect short-input behaviour and recommends configuring it when longer contexts are required. Its card also explains a 40,960-position default allocation for typical prompt and output lengths. Organise long input into named sections and reserve space for reasoning and the final deliverable instead of filling every position with background material. The extended setting depends on the prescribed configuration.
Qwen recommends temperature 0.6 and top-p 0.95 for thinking, and 0.7 and 0.8 for non-thinking, with top-k 20 and min-p 0 in both cases. It warns against greedy decoding in thinking mode because of possible degradation and repetition. Its recommended output allowance is 32,768 tokens for most queries, with 38,912 described for especially complex mathematics and programming tasks. These recommendations guide generation; they do not define an independent fixed response limit. Explicit language and formatting instructions are especially useful when a result must remain consistent across a multilingual conversation.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qwen/qwen3-14b | 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 $0.0002 / 1K tokens Output · Output tokens $0.00058 / 1K tokens Input · Cache read $0 / 1K tokens Input · Cache write $0 / 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 $0.0002 / 1K tokens Output · Output tokens $0.00058 / 1K tokens Input · Cache read $0 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "qwen/qwen3-14b",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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/qwen3-14b', '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/qwen3-14b', '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/qwen3-14b
Use the method paths shown above.
Technical example in English
Explain a changed approval rule\n\nCompare procedure V1: 'All purchase requests need manager approval.' V2: 'Requests above 100 credits need manager approval; smaller requests go directly to purchasing.' Explain the change to a new coordinator, give examples for 80 and 120 credits and identify the unanswered rule for exactly 100 credits. Keep the two versions distinct.A brief explanation, two worked examples and one boundary clarification.The answer must not invent the exactly-100-credit rule absent from V2.