Qwen3-1.7B combines direct answers and reasoning in a small dense language model. The manufacturer describes instruction following, creative writing, role-based conversations, mathematics, logical problems and code, with more than 100 supported languages and dialects. It receives text and produces text. A useful starting task is a tightly specified transformation: turn a short customer message into a polite reply, explain a term for a particular reader or convert a meeting note into an action list.
The exact release has 1.7 billion parameters, including 1.4 billion outside embeddings, and 28 layers. Grouped-query attention uses 16 query heads and eight key/value heads. Its own model card lists a context length of 32,768 tokens. That is the edition’s documented window; larger-context figures from other Qwen3 sizes should remain attached to those separate cards. Keep source text, instructions, conversation history and the requested answer within the relevant sequence budget. For a reply assistant, supply the received message, verified background facts, audience and desired length rather than an entire unrelated correspondence archive.
The manufacturer’s quickstart formats a conversation with the model’s chat template. Prepare a small complete task that can be checked against its source. For an action-list example, give a note containing names, dates and decisions, ask for one item per action and require an explicit unknown value where ownership was not stated. For a programming example, provide one function and representative inputs, then ask the model to explain the branch that determines the result. A returned explanation should refer to the actual variables and conditions instead of introducing hypothetical behavior. The published integration expects a Qwen3-aware runtime; the card warns that Transformers versions below 4.51.0 do not recognize the required architecture.
Thinking is enabled by default in the supplied template. A hard switch selects non-thinking output without a reasoning section. When thinking remains enabled, /think and /no_think act as per-turn instructions, with the most recent one controlling the choice; they cannot override a hard-disabled mode. Use the direct setting for a short rewrite and a reasoning setting when an answer needs to reconcile several conditions. Keep intermediate reasoning separate from the final response and retain the final response in later dialogue 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.
Agentic use is part of the published capability set. The manufacturer recommends Qwen-Agent for tool formatting and parsing, while the application provides and executes the tools. A narrow assistant could request a dictionary lookup for a product term, receive the confirmed definition and then rewrite the user’s sentence. Define the allowed argument and returned fields; check both before using the result. The final text should distinguish supplied facts, returned information and questions that remain unanswered. The Qwen3 guide also describes parallel and multi-step tool calls, with arguments represented as objects and results supplied back into the conversation.
The output budget should fit the whole task. The model card provides generation examples and output-length recommendations; these are different from a proven service-side maximum. Short requested outputs are easy to verify: specify the fields, ordering and language, and keep the original message available for comparison. Evaluate the result on the actual class of inputs before relying on long-form generation. 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 size has a specific note about persistent repetition: the card suggests the recommended sampling settings and presence_penalty 1.5 when significant repetition occurs. Higher penalties can sometimes mix languages or reduce performance. For thinking, the suggested temperature is 0.6 with top-p 0.95, top-k 20 and min-p 0; for non-thinking, temperature is 0.7 with top-p 0.8, top-k 20 and min-p 0. Avoid greedy decoding in reasoning mode. Check names, dates, labels and repeated clauses, and validate any structured output before passing it to another part of an application.
", "aboutText": "Qwen3-1.7B combines direct answers and reasoning in a small dense language model. The manufacturer describes instruction following, creative writing, role-based conversations, mathematics, logical problems and code, with more than 100 supported languages and dialects. It receives text and produces text. A useful starting task is a tightly specified transformation: turn a short customer message into a polite reply, explain a term for a particular reader or convert a meeting note into an action list.\n\nThe exact release has 1.7 billion parameters, including 1.4 billion outside embeddings, and 28 layers. Grouped-query attention uses 16 query heads and eight key/value heads. Its own model card lists a context length of 32,768 tokens. That is the edition’s documented window; larger-context figures from other Qwen3 sizes should remain attached to those separate cards. Keep source text, instructions, conversation history and the requested answer within the relevant sequence budget. For a reply assistant, supply the received message, verified background facts, audience and desired length rather than an entire unrelated correspondence archive.\n\nThe manufacturer’s quickstart formats a conversation with the model’s chat template. Prepare a small complete task that can be checked against its source. For an action-list example, give a note containing names, dates and decisions, ask for one item per action and require an explicit unknown value where ownership was not stated. For a programming example, provide one function and representative inputs, then ask the model to explain the branch that determines the result. A returned explanation should refer to the actual variables and conditions instead of introducing hypothetical behavior. 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\nThinking is enabled by default in the supplied template. A hard switch selects non-thinking output without a reasoning section. When thinking remains enabled, /think and /no_think act as per-turn instructions, with the most recent one controlling the choice; they cannot override a hard-disabled mode. Use the direct setting for a short rewrite and a reasoning setting when an answer needs to reconcile several conditions. Keep intermediate reasoning separate from the final response and retain the final response in later dialogue 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\nAgentic use is part of the published capability set. The manufacturer recommends Qwen-Agent for tool formatting and parsing, while the application provides and executes the tools. A narrow assistant could request a dictionary lookup for a product term, receive the confirmed definition and then rewrite the user’s sentence. Define the allowed argument and returned fields; check both before using the result. The final text should distinguish supplied facts, returned information and questions that remain unanswered. 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 output budget should fit the whole task. The model card provides generation examples and output-length recommendations; these are different from a proven service-side maximum. Short requested outputs are easy to verify: specify the fields, ordering and language, and keep the original message available for comparison. Evaluate the result on the actual class of inputs before relying on long-form generation. 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 size has a specific note about persistent repetition: the card suggests the recommended sampling settings and presence_penalty 1.5 when significant repetition occurs. Higher penalties can sometimes mix languages or reduce performance. For thinking, the suggested temperature is 0.6 with top-p 0.95, top-k 20 and min-p 0; for non-thinking, temperature is 0.7 with top-p 0.8, top-k 20 and min-p 0. Avoid greedy decoding in reasoning mode. Check names, dates, labels and repeated clauses, and validate any structured output before passing it to another part of an application.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Convert a short note into actions\n\nTurn this note into an action list: 'Mina will order six folders by Thursday. Leo will check the cupboard today. Someone must print the welcome sheets before Friday, but we have not assigned that task.' Return one row per action with owner, task and deadline; use 'unassigned' where needed.Three action rows retaining names, deadlines and the unassigned printing owner.Do not assign the printing task to Mina or Leo without evidence in the note.qwen3-1.7bQwen3-1.7B is a compact dense text model with both direct-response and thinking modes. It supports multilingual dialogue, writing, code and tool-oriented instructions, with a 32,768-token context documented for this exact release.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Qwen3-1.7B combines direct answers and reasoning in a small dense language model. The manufacturer describes instruction following, creative writing, role-based conversations, mathematics, logical problems and code, with more than 100 supported languages and dialects. It receives text and produces text. A useful starting task is a tightly specified transformation: turn a short customer message into a polite reply, explain a term for a particular reader or convert a meeting note into an action list.
The exact release has 1.7 billion parameters, including 1.4 billion outside embeddings, and 28 layers. Grouped-query attention uses 16 query heads and eight key/value heads. Its own model card lists a context length of 32,768 tokens. That is the edition’s documented window; larger-context figures from other Qwen3 sizes should remain attached to those separate cards. Keep source text, instructions, conversation history and the requested answer within the relevant sequence budget. For a reply assistant, supply the received message, verified background facts, audience and desired length rather than an entire unrelated correspondence archive.
The manufacturer’s quickstart formats a conversation with the model’s chat template. Prepare a small complete task that can be checked against its source. For an action-list example, give a note containing names, dates and decisions, ask for one item per action and require an explicit unknown value where ownership was not stated. For a programming example, provide one function and representative inputs, then ask the model to explain the branch that determines the result. A returned explanation should refer to the actual variables and conditions instead of introducing hypothetical behavior. The published integration expects a Qwen3-aware runtime; the card warns that Transformers versions below 4.51.0 do not recognize the required architecture.
Thinking is enabled by default in the supplied template. A hard switch selects non-thinking output without a reasoning section. When thinking remains enabled, /think and /no_think act as per-turn instructions, with the most recent one controlling the choice; they cannot override a hard-disabled mode. Use the direct setting for a short rewrite and a reasoning setting when an answer needs to reconcile several conditions. Keep intermediate reasoning separate from the final response and retain the final response in later dialogue 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.
Agentic use is part of the published capability set. The manufacturer recommends Qwen-Agent for tool formatting and parsing, while the application provides and executes the tools. A narrow assistant could request a dictionary lookup for a product term, receive the confirmed definition and then rewrite the user’s sentence. Define the allowed argument and returned fields; check both before using the result. The final text should distinguish supplied facts, returned information and questions that remain unanswered. The Qwen3 guide also describes parallel and multi-step tool calls, with arguments represented as objects and results supplied back into the conversation.
The output budget should fit the whole task. The model card provides generation examples and output-length recommendations; these are different from a proven service-side maximum. Short requested outputs are easy to verify: specify the fields, ordering and language, and keep the original message available for comparison. Evaluate the result on the actual class of inputs before relying on long-form generation. 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 size has a specific note about persistent repetition: the card suggests the recommended sampling settings and presence_penalty 1.5 when significant repetition occurs. Higher penalties can sometimes mix languages or reduce performance. For thinking, the suggested temperature is 0.6 with top-p 0.95, top-k 20 and min-p 0; for non-thinking, temperature is 0.7 with top-p 0.8, top-k 20 and min-p 0. Avoid greedy decoding in reasoning mode. Check names, dates, labels and repeated clauses, and validate any structured output before passing it to another part of an application.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qwen3-1.7b | 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": "qwen3-1.7b", "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='qwen3-1.7b',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='qwen3-1.7b',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 qwen3-1.7b
Use the method paths shown above.
qwen3-1.7bQwen3-1.7B is a compact dense text model with both direct-response and thinking modes. It supports multilingual dialogue, writing, code and tool-oriented instructions, with a 32,768-token context documented for this exact release.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Qwen3-1.7B combines direct answers and reasoning in a small dense language model. The manufacturer describes instruction following, creative writing, role-based conversations, mathematics, logical problems and code, with more than 100 supported languages and dialects. It receives text and produces text. A useful starting task is a tightly specified transformation: turn a short customer message into a polite reply, explain a term for a particular reader or convert a meeting note into an action list.
The exact release has 1.7 billion parameters, including 1.4 billion outside embeddings, and 28 layers. Grouped-query attention uses 16 query heads and eight key/value heads. Its own model card lists a context length of 32,768 tokens. That is the edition’s documented window; larger-context figures from other Qwen3 sizes should remain attached to those separate cards. Keep source text, instructions, conversation history and the requested answer within the relevant sequence budget. For a reply assistant, supply the received message, verified background facts, audience and desired length rather than an entire unrelated correspondence archive.
The manufacturer’s quickstart formats a conversation with the model’s chat template. Prepare a small complete task that can be checked against its source. For an action-list example, give a note containing names, dates and decisions, ask for one item per action and require an explicit unknown value where ownership was not stated. For a programming example, provide one function and representative inputs, then ask the model to explain the branch that determines the result. A returned explanation should refer to the actual variables and conditions instead of introducing hypothetical behavior. The published integration expects a Qwen3-aware runtime; the card warns that Transformers versions below 4.51.0 do not recognize the required architecture.
Thinking is enabled by default in the supplied template. A hard switch selects non-thinking output without a reasoning section. When thinking remains enabled, /think and /no_think act as per-turn instructions, with the most recent one controlling the choice; they cannot override a hard-disabled mode. Use the direct setting for a short rewrite and a reasoning setting when an answer needs to reconcile several conditions. Keep intermediate reasoning separate from the final response and retain the final response in later dialogue 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.
Agentic use is part of the published capability set. The manufacturer recommends Qwen-Agent for tool formatting and parsing, while the application provides and executes the tools. A narrow assistant could request a dictionary lookup for a product term, receive the confirmed definition and then rewrite the user’s sentence. Define the allowed argument and returned fields; check both before using the result. The final text should distinguish supplied facts, returned information and questions that remain unanswered. The Qwen3 guide also describes parallel and multi-step tool calls, with arguments represented as objects and results supplied back into the conversation.
The output budget should fit the whole task. The model card provides generation examples and output-length recommendations; these are different from a proven service-side maximum. Short requested outputs are easy to verify: specify the fields, ordering and language, and keep the original message available for comparison. Evaluate the result on the actual class of inputs before relying on long-form generation. 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 size has a specific note about persistent repetition: the card suggests the recommended sampling settings and presence_penalty 1.5 when significant repetition occurs. Higher penalties can sometimes mix languages or reduce performance. For thinking, the suggested temperature is 0.6 with top-p 0.95, top-k 20 and min-p 0; for non-thinking, temperature is 0.7 with top-p 0.8, top-k 20 and min-p 0. Avoid greedy decoding in reasoning mode. Check names, dates, labels and repeated clauses, and validate any structured output before passing it to another part of an application.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qwen3-1.7b | 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 $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "qwen3-1.7b",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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': 'qwen3-1.7b', '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': 'qwen3-1.7b', '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 qwen3-1.7b
Use the method paths shown above.
Technical example in English
Convert a short note into actions\n\nTurn this note into an action list: 'Mina will order six folders by Thursday. Leo will check the cupboard today. Someone must print the welcome sheets before Friday, but we have not assigned that task.' Return one row per action with owner, task and deadline; use 'unassigned' where needed.Three action rows retaining names, deadlines and the unassigned printing owner.Do not assign the printing task to Mina or Leo without evidence in the note.