Qwen3-0.6B provides the Qwen3 hybrid text interface in a 0.6-billion-parameter dense model. Its family capabilities include instruction following, multilingual conversation, creative writing, role-based interaction, mathematics, code and logical reasoning. Thinking and ordinary generation are available within this same release. The compact size identifies the checkpoint, not a different input format or a substitute name for a larger Qwen3 model.
The model has 0.44 billion non-embedding parameters and 28 layers, with 16 query heads and eight key/value heads in grouped-query attention. The exact card documents 32,768 context tokens. Both incoming text and generated content occupy the model’s sequence, so reserve room for the answer when assembling instructions and examples. This release’s card does not document the expanded-context setup included on some larger Qwen3 cards. A practical first task is one short, clearly defined operation whose output can be compared directly with the source.
Use the manufacturer’s designated chat template to present the instruction and the material. For example, give a brief service note and ask for a customer-facing message that keeps the appointment date and product name unchanged. Supply the intended reader, tone and maximum requested length. For a label-selection task, list the permitted labels with definitions and include an ambiguous example showing how to report uncertainty. Ask for just the label and the corresponding passage from the input. These are concrete output requirements, not a claim that the model will always satisfy them without checking. The published integration expects a Qwen3-aware runtime; the card warns that Transformers versions below 4.51.0 do not recognize the required architecture.
The provided template defaults to thinking. A hard non-thinking setting suppresses the reasoning section; if thinking remains enabled, /think and /no_think can control the mode between turns, subject to the most recent instruction. A hard disable takes priority over these soft prompts. Select the setting that fits the operation: a simple approved-wording change can use a direct response, while explaining why a condition applies may need reasoning. Save the final answer rather than a previous reasoning section as conversation history. With thinking enabled, even a soft non-thinking request retains a reasoning block; its content may be empty. The hard disable removes that block.
The model card describes tool-oriented agent use and recommends Qwen-Agent for the templates and parsing. For a small glossary assistant, the application might expose one read-only lookup, validate its arguments, execute it and return the entry. The model can then explain the term in the user’s requested style. Define the tool result and the fallback for a missing entry in advance. A generated tool request should be handled as a request, with the application retaining responsibility for execution and the returned evidence. The Qwen3 guide also describes parallel and multi-step tool calls, with arguments represented as objects and results supplied back into the conversation.
The published quickstart and best-practice output lengths are guidance for generation, not a separate guaranteed API cap. With a focused operation, choose a compact final record, such as a rewritten sentence plus the unchanged names, or a label and the text supporting it. Check that record against the supplied material. If the task grows into a long explanation, evaluate the longer result on the same kind of real input rather than assuming the model’s compact identity establishes its accuracy or response quality. The Qwen3 documentation discusses assistant-message lengths of 38,912 tokens in thinking mode and 16,384 in non-thinking mode in its training-length explanation, and recommends evaluating the quality of longer generation. These figures are distinct from the overall context window and are not an endpoint-specific hard cap.
This exact card adds advice for significant repetition: use the recommended sampling setup and consider presence_penalty 1.5. Stronger penalties may cause language mixing or a performance decrease. Thinking mode is paired with temperature 0.6, top-p 0.95, top-k 20 and min-p 0; non-thinking with temperature 0.7, top-p 0.8, top-k 20 and min-p 0. The manufacturer warns against greedy decoding in thinking mode. Inspect repeated phrases, preserved names and the selected label; reject a malformed record instead of treating readable prose as proof that the required format was followed.
", "aboutText": "Qwen3-0.6B provides the Qwen3 hybrid text interface in a 0.6-billion-parameter dense model. Its family capabilities include instruction following, multilingual conversation, creative writing, role-based interaction, mathematics, code and logical reasoning. Thinking and ordinary generation are available within this same release. The compact size identifies the checkpoint, not a different input format or a substitute name for a larger Qwen3 model.\n\nThe model has 0.44 billion non-embedding parameters and 28 layers, with 16 query heads and eight key/value heads in grouped-query attention. The exact card documents 32,768 context tokens. Both incoming text and generated content occupy the model’s sequence, so reserve room for the answer when assembling instructions and examples. This release’s card does not document the expanded-context setup included on some larger Qwen3 cards. A practical first task is one short, clearly defined operation whose output can be compared directly with the source.\n\nUse the manufacturer’s designated chat template to present the instruction and the material. For example, give a brief service note and ask for a customer-facing message that keeps the appointment date and product name unchanged. Supply the intended reader, tone and maximum requested length. For a label-selection task, list the permitted labels with definitions and include an ambiguous example showing how to report uncertainty. Ask for just the label and the corresponding passage from the input. These are concrete output requirements, not a claim that the model will always satisfy them without checking. The published integration expects a Qwen3-aware runtime; the card warns that Transformers versions below 4.51.0 do not recognize the required architecture.\n\nThe provided template defaults to thinking. A hard non-thinking setting suppresses the reasoning section; if thinking remains enabled, /think and /no_think can control the mode between turns, subject to the most recent instruction. A hard disable takes priority over these soft prompts. Select the setting that fits the operation: a simple approved-wording change can use a direct response, while explaining why a condition applies may need reasoning. Save the final answer rather than a previous reasoning section as conversation history. With thinking enabled, even a soft non-thinking request retains a reasoning block; its content may be empty. The hard disable removes that block.\n\nThe model card describes tool-oriented agent use and recommends Qwen-Agent for the templates and parsing. For a small glossary assistant, the application might expose one read-only lookup, validate its arguments, execute it and return the entry. The model can then explain the term in the user’s requested style. Define the tool result and the fallback for a missing entry in advance. A generated tool request should be handled as a request, with the application retaining responsibility for execution and the returned evidence. The Qwen3 guide also describes parallel and multi-step tool calls, with arguments represented as objects and results supplied back into the conversation.\n\nThe published quickstart and best-practice output lengths are guidance for generation, not a separate guaranteed API cap. With a focused operation, choose a compact final record, such as a rewritten sentence plus the unchanged names, or a label and the text supporting it. Check that record against the supplied material. If the task grows into a long explanation, evaluate the longer result on the same kind of real input rather than assuming the model’s compact identity establishes its accuracy or response quality. The Qwen3 documentation discusses assistant-message lengths of 38,912 tokens in thinking mode and 16,384 in non-thinking mode in its training-length explanation, and recommends evaluating the quality of longer generation. These figures are distinct from the overall context window and are not an endpoint-specific hard cap.\n\nThis exact card adds advice for significant repetition: use the recommended sampling setup and consider presence_penalty 1.5. Stronger penalties may cause language mixing or a performance decrease. Thinking mode is paired with temperature 0.6, top-p 0.95, top-k 20 and min-p 0; non-thinking with temperature 0.7, top-p 0.8, top-k 20 and min-p 0. The manufacturer warns against greedy decoding in thinking mode. Inspect repeated phrases, preserved names and the selected label; reject a malformed record instead of treating readable prose as proof that the required format was followed.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
A single focused appointment rewrite\n\nRewrite this note as one friendly sentence for a customer, using at most 25 words: 'Appointment for Polar Fan repair: 14 June, 09:30. Bring the purchase receipt.' Preserve the product name, date, time and receipt instruction. Return only the sentence, with no heading or additional details.One customer-facing sentence of at most 25 words retaining all four facts.Polar Fan, 14 June and 09:30 remain exact, and the receipt instruction is present.qwen3-0.6bQwen3-0.6B is the smallest dense release in this Qwen3 set, with 0.6 billion parameters. It handles text instructions and multilingual dialogue through direct and thinking modes, with an edition-specific 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.
Qwen3-0.6B provides the Qwen3 hybrid text interface in a 0.6-billion-parameter dense model. Its family capabilities include instruction following, multilingual conversation, creative writing, role-based interaction, mathematics, code and logical reasoning. Thinking and ordinary generation are available within this same release. The compact size identifies the checkpoint, not a different input format or a substitute name for a larger Qwen3 model.
The model has 0.44 billion non-embedding parameters and 28 layers, with 16 query heads and eight key/value heads in grouped-query attention. The exact card documents 32,768 context tokens. Both incoming text and generated content occupy the model’s sequence, so reserve room for the answer when assembling instructions and examples. This release’s card does not document the expanded-context setup included on some larger Qwen3 cards. A practical first task is one short, clearly defined operation whose output can be compared directly with the source.
Use the manufacturer’s designated chat template to present the instruction and the material. For example, give a brief service note and ask for a customer-facing message that keeps the appointment date and product name unchanged. Supply the intended reader, tone and maximum requested length. For a label-selection task, list the permitted labels with definitions and include an ambiguous example showing how to report uncertainty. Ask for just the label and the corresponding passage from the input. These are concrete output requirements, not a claim that the model will always satisfy them without checking. The published integration expects a Qwen3-aware runtime; the card warns that Transformers versions below 4.51.0 do not recognize the required architecture.
The provided template defaults to thinking. A hard non-thinking setting suppresses the reasoning section; if thinking remains enabled, /think and /no_think can control the mode between turns, subject to the most recent instruction. A hard disable takes priority over these soft prompts. Select the setting that fits the operation: a simple approved-wording change can use a direct response, while explaining why a condition applies may need reasoning. Save the final answer rather than a previous reasoning section as conversation history. With thinking enabled, even a soft non-thinking request retains a reasoning block; its content may be empty. The hard disable removes that block.
The model card describes tool-oriented agent use and recommends Qwen-Agent for the templates and parsing. For a small glossary assistant, the application might expose one read-only lookup, validate its arguments, execute it and return the entry. The model can then explain the term in the user’s requested style. Define the tool result and the fallback for a missing entry in advance. A generated tool request should be handled as a request, with the application retaining responsibility for execution and the returned evidence. The Qwen3 guide also describes parallel and multi-step tool calls, with arguments represented as objects and results supplied back into the conversation.
The published quickstart and best-practice output lengths are guidance for generation, not a separate guaranteed API cap. With a focused operation, choose a compact final record, such as a rewritten sentence plus the unchanged names, or a label and the text supporting it. Check that record against the supplied material. If the task grows into a long explanation, evaluate the longer result on the same kind of real input rather than assuming the model’s compact identity establishes its accuracy or response quality. The Qwen3 documentation discusses assistant-message lengths of 38,912 tokens in thinking mode and 16,384 in non-thinking mode in its training-length explanation, and recommends evaluating the quality of longer generation. These figures are distinct from the overall context window and are not an endpoint-specific hard cap.
This exact card adds advice for significant repetition: use the recommended sampling setup and consider presence_penalty 1.5. Stronger penalties may cause language mixing or a performance decrease. Thinking mode is paired with temperature 0.6, top-p 0.95, top-k 20 and min-p 0; non-thinking with temperature 0.7, top-p 0.8, top-k 20 and min-p 0. The manufacturer warns against greedy decoding in thinking mode. Inspect repeated phrases, preserved names and the selected label; reject a malformed record instead of treating readable prose as proof that the required format was followed.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qwen3-0.6b | 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 $0.0001 / 1K tokens Output · Output tokens $0.001 / 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": "qwen3-0.6b", "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='qwen3-0.6b',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='qwen3-0.6b',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 qwen3-0.6b
Use the method paths shown above.
qwen3-0.6bQwen3-0.6B is the smallest dense release in this Qwen3 set, with 0.6 billion parameters. It handles text instructions and multilingual dialogue through direct and thinking modes, with an edition-specific 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.
Qwen3-0.6B provides the Qwen3 hybrid text interface in a 0.6-billion-parameter dense model. Its family capabilities include instruction following, multilingual conversation, creative writing, role-based interaction, mathematics, code and logical reasoning. Thinking and ordinary generation are available within this same release. The compact size identifies the checkpoint, not a different input format or a substitute name for a larger Qwen3 model.
The model has 0.44 billion non-embedding parameters and 28 layers, with 16 query heads and eight key/value heads in grouped-query attention. The exact card documents 32,768 context tokens. Both incoming text and generated content occupy the model’s sequence, so reserve room for the answer when assembling instructions and examples. This release’s card does not document the expanded-context setup included on some larger Qwen3 cards. A practical first task is one short, clearly defined operation whose output can be compared directly with the source.
Use the manufacturer’s designated chat template to present the instruction and the material. For example, give a brief service note and ask for a customer-facing message that keeps the appointment date and product name unchanged. Supply the intended reader, tone and maximum requested length. For a label-selection task, list the permitted labels with definitions and include an ambiguous example showing how to report uncertainty. Ask for just the label and the corresponding passage from the input. These are concrete output requirements, not a claim that the model will always satisfy them without checking. The published integration expects a Qwen3-aware runtime; the card warns that Transformers versions below 4.51.0 do not recognize the required architecture.
The provided template defaults to thinking. A hard non-thinking setting suppresses the reasoning section; if thinking remains enabled, /think and /no_think can control the mode between turns, subject to the most recent instruction. A hard disable takes priority over these soft prompts. Select the setting that fits the operation: a simple approved-wording change can use a direct response, while explaining why a condition applies may need reasoning. Save the final answer rather than a previous reasoning section as conversation history. With thinking enabled, even a soft non-thinking request retains a reasoning block; its content may be empty. The hard disable removes that block.
The model card describes tool-oriented agent use and recommends Qwen-Agent for the templates and parsing. For a small glossary assistant, the application might expose one read-only lookup, validate its arguments, execute it and return the entry. The model can then explain the term in the user’s requested style. Define the tool result and the fallback for a missing entry in advance. A generated tool request should be handled as a request, with the application retaining responsibility for execution and the returned evidence. The Qwen3 guide also describes parallel and multi-step tool calls, with arguments represented as objects and results supplied back into the conversation.
The published quickstart and best-practice output lengths are guidance for generation, not a separate guaranteed API cap. With a focused operation, choose a compact final record, such as a rewritten sentence plus the unchanged names, or a label and the text supporting it. Check that record against the supplied material. If the task grows into a long explanation, evaluate the longer result on the same kind of real input rather than assuming the model’s compact identity establishes its accuracy or response quality. The Qwen3 documentation discusses assistant-message lengths of 38,912 tokens in thinking mode and 16,384 in non-thinking mode in its training-length explanation, and recommends evaluating the quality of longer generation. These figures are distinct from the overall context window and are not an endpoint-specific hard cap.
This exact card adds advice for significant repetition: use the recommended sampling setup and consider presence_penalty 1.5. Stronger penalties may cause language mixing or a performance decrease. Thinking mode is paired with temperature 0.6, top-p 0.95, top-k 20 and min-p 0; non-thinking with temperature 0.7, top-p 0.8, top-k 20 and min-p 0. The manufacturer warns against greedy decoding in thinking mode. Inspect repeated phrases, preserved names and the selected label; reject a malformed record instead of treating readable prose as proof that the required format was followed.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qwen3-0.6b | 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 $0.0001 / 1K tokens Output · Output tokens $0.001 / 1K tokens Input · Cache read $0 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "qwen3-0.6b",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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': 'qwen3-0.6b', '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': 'qwen3-0.6b', '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 qwen3-0.6b
Use the method paths shown above.
Technical example in English
A single focused appointment rewrite\n\nRewrite this note as one friendly sentence for a customer, using at most 25 words: 'Appointment for Polar Fan repair: 14 June, 09:30. Bring the purchase receipt.' Preserve the product name, date, time and receipt instruction. Return only the sentence, with no heading or additional details.One customer-facing sentence of at most 25 words retaining all four facts.Polar Fan, 14 June and 09:30 remain exact, and the receipt instruction is present.