QwQ-Plus — 2025-03-05 is a dated entry in the QwQ-Plus text-reasoning family. The manufacturer describes QwQ-Plus as an enhanced QwQ line trained from Qwen2.5, with reinforcement learning used to develop reasoning. Its highlighted task directions are mathematics, programming and other questions that require connecting several conditions. The useful result is a text solution, explanation or implementation grounded in the material provided by the user.
A reasoning task needs a definite target. For mathematics, give the complete statement, definitions, allowed variable ranges and the quantity or assertion to establish. Ask for a final result in a specific form and for enough explanation to check the transitions. If evaluating an attempted solution, include the original problem and the disputed step together. The model can then discuss the actual issue rather than reconstructing missing assumptions from a partial fragment.
For programming, provide the relevant code, language, expected behavior and an input that exposes the problem. A useful request asks for a revised function, an explanation of the changed condition and examples showing the intended behavior. Preserve the interface and state which surrounding behavior must remain unchanged. When comparing algorithms, define the criteria first—for example, correctness on the supplied cases and the relevant complexity assumptions—then request a reasoned choice rather than a general list of alternatives.
The manufacturer’s chat reference recommends placing QwQ instructions in the user request instead of relying on a system message. Separate source data from the task, including any text or code that is being quoted for analysis. State how to handle insufficient information: name the missing condition or ask a focused follow-up rather than assuming a value. If the application already has results from a calculator, test runner or search tool, pass those results explicitly and ask the model to use them as evidence.
The documented QwQ service flow returns output through streaming. Keep intermediate reasoning and the completed answer distinguishable, and assemble the returned fragments before treating the answer as a finished artifact. A partial stream may contain an unfinished calculation or an abandoned approach. For a user-facing result, identify the final conclusion and the checks supporting it, while retaining enough source context to review what was actually asked.
For a repeatable reasoning task, retain the exact dated model name with the input version, requested output format and generation settings. In a follow-up, identify the particular step that should change and keep the accepted facts explicit. Give relevant excerpts rather than unrelated background, and set a concise answer target so the request leaves room for both the analysis and the final result.
For an analytical task, label the compared options and state the decision rule. For a proof, distinguish premises from the claim; for a program, distinguish an observed failure from a proposed cause. Ask the final answer to identify which conclusion follows from the supplied facts and which part depends on an assumption. Verify arithmetic with the original numbers, test proposed code against the actual cases and inspect any structured-looking output before an application consumes it. A requested table or JSON-like layout is an output instruction, not a guarantee of constrained structured generation.
Choose this reasoning-oriented task format when the route to a result needs to be explained and checked. A useful final artifact may be a checked solution, a code change with relevant examples or a comparison that makes the deciding condition explicit. External actions still require a defined application tool and a returned result; reasoning text by itself does not establish that a calculation was executed or that a proposed change was applied.
", "aboutText": "QwQ-Plus — 2025-03-05 is a dated entry in the QwQ-Plus text-reasoning family. The manufacturer describes QwQ-Plus as an enhanced QwQ line trained from Qwen2.5, with reinforcement learning used to develop reasoning. Its highlighted task directions are mathematics, programming and other questions that require connecting several conditions. The useful result is a text solution, explanation or implementation grounded in the material provided by the user.\n\nA reasoning task needs a definite target. For mathematics, give the complete statement, definitions, allowed variable ranges and the quantity or assertion to establish. Ask for a final result in a specific form and for enough explanation to check the transitions. If evaluating an attempted solution, include the original problem and the disputed step together. The model can then discuss the actual issue rather than reconstructing missing assumptions from a partial fragment.\n\nFor programming, provide the relevant code, language, expected behavior and an input that exposes the problem. A useful request asks for a revised function, an explanation of the changed condition and examples showing the intended behavior. Preserve the interface and state which surrounding behavior must remain unchanged. When comparing algorithms, define the criteria first—for example, correctness on the supplied cases and the relevant complexity assumptions—then request a reasoned choice rather than a general list of alternatives.\n\nThe manufacturer’s chat reference recommends placing QwQ instructions in the user request instead of relying on a system message. Separate source data from the task, including any text or code that is being quoted for analysis. State how to handle insufficient information: name the missing condition or ask a focused follow-up rather than assuming a value. If the application already has results from a calculator, test runner or search tool, pass those results explicitly and ask the model to use them as evidence.\n\nThe documented QwQ service flow returns output through streaming. Keep intermediate reasoning and the completed answer distinguishable, and assemble the returned fragments before treating the answer as a finished artifact. A partial stream may contain an unfinished calculation or an abandoned approach. For a user-facing result, identify the final conclusion and the checks supporting it, while retaining enough source context to review what was actually asked.\n\nFor a repeatable reasoning task, retain the exact dated model name with the input version, requested output format and generation settings. In a follow-up, identify the particular step that should change and keep the accepted facts explicit. Give relevant excerpts rather than unrelated background, and set a concise answer target so the request leaves room for both the analysis and the final result.\n\nFor an analytical task, label the compared options and state the decision rule. For a proof, distinguish premises from the claim; for a program, distinguish an observed failure from a proposed cause. Ask the final answer to identify which conclusion follows from the supplied facts and which part depends on an assumption. Verify arithmetic with the original numbers, test proposed code against the actual cases and inspect any structured-looking output before an application consumes it. A requested table or JSON-like layout is an output instruction, not a guarantee of constrained structured generation.\n\nChoose this reasoning-oriented task format when the route to a result needs to be explained and checked. A useful final artifact may be a checked solution, a code change with relevant examples or a comparison that makes the deciding condition explicit. External actions still require a defined application tool and a returned result; reasoning text by itself does not establish that a calculation was executed or that a proposed change was applied.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Check a batch-capacity claim\n\nA processor handles 18 records per minute and must finish 1,000 records within one hour. Each run also needs a fixed seven-minute setup, during which no records are processed. Determine whether one run can meet the deadline under these assumptions. Show the available processing time, capacity and minimum rate needed, rounding only where required.A feasibility calculation with processing time, attainable capacity and the rate required to meet the deadline.The seven-minute setup is deducted before applying the processing rate, and units remain consistent.qwq-plus-2025-03-05QwQ-Plus — 2025-03-05 keeps a dated identity in Qwen’s text-reasoning family. Its Qwen2.5-based, reinforcement-trained approach is intended for mathematics, programming and problems that need a justified result from several connected conditions.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
QwQ-Plus — 2025-03-05 is a dated entry in the QwQ-Plus text-reasoning family. The manufacturer describes QwQ-Plus as an enhanced QwQ line trained from Qwen2.5, with reinforcement learning used to develop reasoning. Its highlighted task directions are mathematics, programming and other questions that require connecting several conditions. The useful result is a text solution, explanation or implementation grounded in the material provided by the user.
A reasoning task needs a definite target. For mathematics, give the complete statement, definitions, allowed variable ranges and the quantity or assertion to establish. Ask for a final result in a specific form and for enough explanation to check the transitions. If evaluating an attempted solution, include the original problem and the disputed step together. The model can then discuss the actual issue rather than reconstructing missing assumptions from a partial fragment.
For programming, provide the relevant code, language, expected behavior and an input that exposes the problem. A useful request asks for a revised function, an explanation of the changed condition and examples showing the intended behavior. Preserve the interface and state which surrounding behavior must remain unchanged. When comparing algorithms, define the criteria first—for example, correctness on the supplied cases and the relevant complexity assumptions—then request a reasoned choice rather than a general list of alternatives.
The manufacturer’s chat reference recommends placing QwQ instructions in the user request instead of relying on a system message. Separate source data from the task, including any text or code that is being quoted for analysis. State how to handle insufficient information: name the missing condition or ask a focused follow-up rather than assuming a value. If the application already has results from a calculator, test runner or search tool, pass those results explicitly and ask the model to use them as evidence.
The documented QwQ service flow returns output through streaming. Keep intermediate reasoning and the completed answer distinguishable, and assemble the returned fragments before treating the answer as a finished artifact. A partial stream may contain an unfinished calculation or an abandoned approach. For a user-facing result, identify the final conclusion and the checks supporting it, while retaining enough source context to review what was actually asked.
For a repeatable reasoning task, retain the exact dated model name with the input version, requested output format and generation settings. In a follow-up, identify the particular step that should change and keep the accepted facts explicit. Give relevant excerpts rather than unrelated background, and set a concise answer target so the request leaves room for both the analysis and the final result.
For an analytical task, label the compared options and state the decision rule. For a proof, distinguish premises from the claim; for a program, distinguish an observed failure from a proposed cause. Ask the final answer to identify which conclusion follows from the supplied facts and which part depends on an assumption. Verify arithmetic with the original numbers, test proposed code against the actual cases and inspect any structured-looking output before an application consumes it. A requested table or JSON-like layout is an output instruction, not a guarantee of constrained structured generation.
Choose this reasoning-oriented task format when the route to a result needs to be explained and checked. A useful final artifact may be a checked solution, a code change with relevant examples or a comparison that makes the deciding condition explicit. External actions still require a defined application tool and a returned result; reasoning text by itself does not establish that a calculation was executed or that a proposed change was applied.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qwq-plus-2025-03-05 | Default— |
Fieldmessages | Typemessage[] | RequirementRequired | Values & limits Minimum items: 1 | Default— |
Fieldmessages[].role | Typestring | RequirementRequired | Values & limits Examples: system, user, assistant, tool, function Conditions: These roles are explicitly represented by Source compatibility types; the exact model role set remains model-specific. Model-specific | Default— |
Fieldmessages[].content | Typestring|content_part[]|null | RequirementOptional | Values & limits | Default— |
Fieldmessages[].tool_calls | Typetool_call[] | RequirementOptional | Values & limits | Default— |
Fieldmessages[].tool_call_id | Typestring | RequirementOptional | Values & limits Applies when: role=tool; use actual returned ID | Default— |
Fieldmessages[].name | Typestring | RequirementOptional | Values & limits | Default— |
Fieldmessages[].reasoning_content | Typestring | RequirementOptional | Values & limits Applies when: Round-trip actual returned reasoning where this model uses it | Default— |
Fieldmessages[].reasoning_details | Typeobject|array | RequirementOptional | Values & limits Model-specific | Default— |
Fieldmax_tokens | Typeinteger | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
Fieldmax_completion_tokens | Typeinteger | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
Fieldstream_options.include_usage | Typeboolean | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtemperature | Typenumber | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtop_p | Typenumber | RequirementOptional | Values & limits Model-specific | Default— |
Fieldstop | Typestring|string[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtools | Typefunction_tool[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtools[].type | Typestring | RequirementOptional | Values & limits function Model-specific | Default— |
Fieldtools[].function.name | Typestring | RequirementRequired | Values & limits Applies when: function tool supplied | Default— |
Fieldtools[].function.description | Typestring | RequirementOptional | Values & limits | Default— |
Fieldtools[].function.parameters | TypeJSON_schema | RequirementOptional | Values & limits | Default— |
Fieldtool_choice | Typestring|object | RequirementOptional | Values & limits Model-specific | Default— |
Fieldparallel_tool_calls | Typeboolean | RequirementOptional | Values & limits Model-specific | Default— |
Fieldresponse_format | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Fieldreasoning_effort | Typestring | RequirementOptional | Values & limits Model-specific | Default— |
Fieldreasoning | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Fieldservice_tier | Typestring | RequirementOptional | Values & limits Model-specific | Default— |
Fieldinstructions | Typestring | RequirementOptional | Values & limits Compatibility field | Default— |
Fieldfunctions | Typefunction[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldfunction_call | Typestring|object | RequirementOptional | Values & limits Model-specific | Default— |
Fieldprompt_cache_options | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Fieldmodalities | Typestring[] | RequirementOptional | Values & limits text | Default— |
Fieldprovider | Typeobject | RequirementOptional | Values & limits Conditions: provider.options is rejected on this Ultra text route | Default— |
Fieldcache_control.ttl | Typestring | RequirementOptional | Values & limits Conditions: 1h is rejected in actual prompt-cache locations | Default— |
Text · UTF8 text
messages[].content
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, messages |
Parametermaterial_types | Contracttext |
Parametermessages | Contractmessage array with role/content shape |
Parameterfile_material | Contractactual UTF-8 document inserted as literal text; no file ID inferred |
Parameteroptional_controls | Contractstream, temperature, top_p, stop, max_tokens, max_completion_tokens, reasoning, response_format, tools, tool_choice |
Parametercontrol_scope | Contractmodel-specific; user function tools differ from hosted tools |
Parameteroutput_modalities | Contracttext |
Parameterhosted_operations | Contractfalse |
Parametermultimodal_input_binding | Contractnull |
Lifecycle: synchronous_or_streamed
Send exact model ID with messages.
Context length is not an output cap.
A text file may supply literal text; image/audio/file-object inputs need exact binding.
Tariff references do not add request options. Supported parameters are listed for the selected method.
| Configuration | Rate schedule | Charge |
|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Charge Input · Input tokens $0.00046 / 1K tokens Output · Output tokens $0.00116 / 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": "qwq-plus-2025-03-05", "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='qwq-plus-2025-03-05',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='qwq-plus-2025-03-05',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 qwq-plus-2025-03-05
Use the method paths shown above.
qwq-plus-2025-03-05QwQ-Plus — 2025-03-05 keeps a dated identity in Qwen’s text-reasoning family. Its Qwen2.5-based, reinforcement-trained approach is intended for mathematics, programming and problems that need a justified result from several connected conditions.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
QwQ-Plus — 2025-03-05 is a dated entry in the QwQ-Plus text-reasoning family. The manufacturer describes QwQ-Plus as an enhanced QwQ line trained from Qwen2.5, with reinforcement learning used to develop reasoning. Its highlighted task directions are mathematics, programming and other questions that require connecting several conditions. The useful result is a text solution, explanation or implementation grounded in the material provided by the user.
A reasoning task needs a definite target. For mathematics, give the complete statement, definitions, allowed variable ranges and the quantity or assertion to establish. Ask for a final result in a specific form and for enough explanation to check the transitions. If evaluating an attempted solution, include the original problem and the disputed step together. The model can then discuss the actual issue rather than reconstructing missing assumptions from a partial fragment.
For programming, provide the relevant code, language, expected behavior and an input that exposes the problem. A useful request asks for a revised function, an explanation of the changed condition and examples showing the intended behavior. Preserve the interface and state which surrounding behavior must remain unchanged. When comparing algorithms, define the criteria first—for example, correctness on the supplied cases and the relevant complexity assumptions—then request a reasoned choice rather than a general list of alternatives.
The manufacturer’s chat reference recommends placing QwQ instructions in the user request instead of relying on a system message. Separate source data from the task, including any text or code that is being quoted for analysis. State how to handle insufficient information: name the missing condition or ask a focused follow-up rather than assuming a value. If the application already has results from a calculator, test runner or search tool, pass those results explicitly and ask the model to use them as evidence.
The documented QwQ service flow returns output through streaming. Keep intermediate reasoning and the completed answer distinguishable, and assemble the returned fragments before treating the answer as a finished artifact. A partial stream may contain an unfinished calculation or an abandoned approach. For a user-facing result, identify the final conclusion and the checks supporting it, while retaining enough source context to review what was actually asked.
For a repeatable reasoning task, retain the exact dated model name with the input version, requested output format and generation settings. In a follow-up, identify the particular step that should change and keep the accepted facts explicit. Give relevant excerpts rather than unrelated background, and set a concise answer target so the request leaves room for both the analysis and the final result.
For an analytical task, label the compared options and state the decision rule. For a proof, distinguish premises from the claim; for a program, distinguish an observed failure from a proposed cause. Ask the final answer to identify which conclusion follows from the supplied facts and which part depends on an assumption. Verify arithmetic with the original numbers, test proposed code against the actual cases and inspect any structured-looking output before an application consumes it. A requested table or JSON-like layout is an output instruction, not a guarantee of constrained structured generation.
Choose this reasoning-oriented task format when the route to a result needs to be explained and checked. A useful final artifact may be a checked solution, a code change with relevant examples or a comparison that makes the deciding condition explicit. External actions still require a defined application tool and a returned result; reasoning text by itself does not establish that a calculation was executed or that a proposed change was applied.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qwq-plus-2025-03-05 | 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 $0.00046 / 1K tokens Output · Output tokens $0.00116 / 1K tokens Input · Cache read $0 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "qwq-plus-2025-03-05",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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': 'qwq-plus-2025-03-05', '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': 'qwq-plus-2025-03-05', '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 qwq-plus-2025-03-05
Use the method paths shown above.
Technical example in English
Check a batch-capacity claim\n\nA processor handles 18 records per minute and must finish 1,000 records within one hour. Each run also needs a fixed seven-minute setup, during which no records are processed. Determine whether one run can meet the deadline under these assumptions. Show the available processing time, capacity and minimum rate needed, rounding only where required.A feasibility calculation with processing time, attainable capacity and the rate required to meet the deadline.The seven-minute setup is deducted before applying the processing rate, and units remain consistent.