Qwen3-30B-A3B combines two styles of response in one text model: thinking for complex logical, mathematical and programming problems, and non-thinking for straightforward dialogue. Qwen also emphasises creative writing, role-based conversation, instruction following and integration with external tools. The original Qwen3 family supports 119 languages and dialects, making this model useful for multilingual questions, translation and conversation where the requested language can change between turns. State the output language, preserve terminology that should remain unchanged and describe the reader’s needs.
This is the original Qwen3-30B-A3B mixture-of-experts edition. Its 30.5 billion total parameters include 3.3 billion activated for each token; eight of its 128 experts are selected in the model’s expert layers. The sparse architecture is a meaningful distinction from Qwen3’s dense models. This profile concerns the original hybrid model, whose native context is 32,768 tokens, rather than a later separately named Instruct-2507 or Thinking-2507 edition. For an analysis brief, supply the relevant code or source passages, the question to resolve and the conditions that a valid answer must meet.
In the official chat template, thinking is enabled by default. The hard enable_thinking switch can disable it completely. When thinking remains enabled, /think and /no_think in a user or system instruction act as soft switches, and the most recent instruction controls the requested behaviour across turns. A /no_think request under an enabled template can still produce an empty thinking block; with the hard switch disabled, neither marker activates thinking. This distinction matters when a workflow alternates between an immediate rewrite and a more involved debugging or reasoning question.
Qwen’s examples separate the <think> section from the final response. For a coding problem, prepare the smallest relevant source excerpt, the observed failure and the desired result, then ask for a diagnosis and a proposed correction. For a mathematics problem, the producer recommends an explicit step-by-step instruction with the final answer placed in \\boxed{}. A multiple-choice brief can instead define a single answer field. In later conversation turns, Qwen recommends retaining the final answer and omitting the earlier thinking content from the history, rather than repeatedly carrying the entire reasoning section forward.
Tool calling is described for both modes. Qwen recommends Qwen-Agent to handle the model’s tool templates and parsing, with examples of retrieval, time information and a code interpreter. Describe the available tools and their arguments before asking it to plan a sequence. A useful brief might request a check of selected documentation followed by a reasoned implementation proposal; return each tool result to the conversation so the model can continue from actual evidence. The textual tool request and the application’s executed result remain separate parts of that workflow.
The card describes context extension to 131,072 tokens using YaRN. It is a configuration-dependent extension of the native window, and Qwen cautions that static scaling can affect shorter inputs. The card also explains a 40,960-position default configuration that allocates space for a typical prompt and a long response; this is distinct from its native-context description. Prepare long material with clear document boundaries, prioritise the parts relevant to the question and leave room for the answer and any reasoning.
For thinking, Qwen recommends temperature 0.6, top-p 0.95, top-k 20 and min-p 0, and advises against greedy decoding because it can degrade results or repeat indefinitely. For non-thinking, its guidance changes temperature to 0.7 and top-p to 0.8. It recommends a 32,768-token output allowance for most queries and describes 38,912 tokens for especially demanding mathematics and programming problems. These are producer generation settings, not a separate fixed response guarantee. Choose the mode and requested deliverable together so the response has space for both the necessary reasoning and the useful final result.
", "aboutText": "Qwen3-30B-A3B combines two styles of response in one text model: thinking for complex logical, mathematical and programming problems, and non-thinking for straightforward dialogue. Qwen also emphasises creative writing, role-based conversation, instruction following and integration with external tools. The original Qwen3 family supports 119 languages and dialects, making this model useful for multilingual questions, translation and conversation where the requested language can change between turns. State the output language, preserve terminology that should remain unchanged and describe the reader’s needs.\n\nThis is the original Qwen3-30B-A3B mixture-of-experts edition. Its 30.5 billion total parameters include 3.3 billion activated for each token; eight of its 128 experts are selected in the model’s expert layers. The sparse architecture is a meaningful distinction from Qwen3’s dense models. This profile concerns the original hybrid model, whose native context is 32,768 tokens, rather than a later separately named Instruct-2507 or Thinking-2507 edition. For an analysis brief, supply the relevant code or source passages, the question to resolve and the conditions that a valid answer must meet.\n\nIn the official chat template, thinking is enabled by default. The hard enable_thinking switch can disable it completely. When thinking remains enabled, /think and /no_think in a user or system instruction act as soft switches, and the most recent instruction controls the requested behaviour across turns. A /no_think request under an enabled template can still produce an empty thinking block; with the hard switch disabled, neither marker activates thinking. This distinction matters when a workflow alternates between an immediate rewrite and a more involved debugging or reasoning question.\n\nQwen’s examples separate theTechnical example in English
Explain a weighted-average mistake\n\nA student averages two class scores as (80 + 90) / 2. The first class has 10 students and the second has 30. Explain why that calculation does not give the combined student average, derive the correct weighted expression and state when the simple average would be valid. Finish with the combined average in a separate final line.A short explanation, a weighted formula, its evaluated result and the equal-weight condition.The explanation uses student counts as weights and distinguishes a class average from a student average.qwen/qwen3-30b-a3bQwen3-30B-A3B is Qwen’s mixture-of-experts text model with thinking and non-thinking modes for reasoning, coding and multilingual conversation. It has 30.5 billion total parameters, 3.3 billion active per token and a native 32,768-token context.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Qwen3-30B-A3B combines two styles of response in one text model: thinking for complex logical, mathematical and programming problems, and non-thinking for straightforward dialogue. Qwen also emphasises creative writing, role-based conversation, instruction following and integration with external tools. The original Qwen3 family supports 119 languages and dialects, making this model useful for multilingual questions, translation and conversation where the requested language can change between turns. State the output language, preserve terminology that should remain unchanged and describe the reader’s needs.
This is the original Qwen3-30B-A3B mixture-of-experts edition. Its 30.5 billion total parameters include 3.3 billion activated for each token; eight of its 128 experts are selected in the model’s expert layers. The sparse architecture is a meaningful distinction from Qwen3’s dense models. This profile concerns the original hybrid model, whose native context is 32,768 tokens, rather than a later separately named Instruct-2507 or Thinking-2507 edition. For an analysis brief, supply the relevant code or source passages, the question to resolve and the conditions that a valid answer must meet.
In the official chat template, thinking is enabled by default. The hard enable_thinking switch can disable it completely. When thinking remains enabled, /think and /no_think in a user or system instruction act as soft switches, and the most recent instruction controls the requested behaviour across turns. A /no_think request under an enabled template can still produce an empty thinking block; with the hard switch disabled, neither marker activates thinking. This distinction matters when a workflow alternates between an immediate rewrite and a more involved debugging or reasoning question.
Qwen’s examples separate the <think> section from the final response. For a coding problem, prepare the smallest relevant source excerpt, the observed failure and the desired result, then ask for a diagnosis and a proposed correction. For a mathematics problem, the producer recommends an explicit step-by-step instruction with the final answer placed in \\boxed{}. A multiple-choice brief can instead define a single answer field. In later conversation turns, Qwen recommends retaining the final answer and omitting the earlier thinking content from the history, rather than repeatedly carrying the entire reasoning section forward.
Tool calling is described for both modes. Qwen recommends Qwen-Agent to handle the model’s tool templates and parsing, with examples of retrieval, time information and a code interpreter. Describe the available tools and their arguments before asking it to plan a sequence. A useful brief might request a check of selected documentation followed by a reasoned implementation proposal; return each tool result to the conversation so the model can continue from actual evidence. The textual tool request and the application’s executed result remain separate parts of that workflow.
The card describes context extension to 131,072 tokens using YaRN. It is a configuration-dependent extension of the native window, and Qwen cautions that static scaling can affect shorter inputs. The card also explains a 40,960-position default configuration that allocates space for a typical prompt and a long response; this is distinct from its native-context description. Prepare long material with clear document boundaries, prioritise the parts relevant to the question and leave room for the answer and any reasoning.
For thinking, Qwen recommends temperature 0.6, top-p 0.95, top-k 20 and min-p 0, and advises against greedy decoding because it can degrade results or repeat indefinitely. For non-thinking, its guidance changes temperature to 0.7 and top-p to 0.8. It recommends a 32,768-token output allowance for most queries and describes 38,912 tokens for especially demanding mathematics and programming problems. These are producer generation settings, not a separate fixed response guarantee. Choose the mode and requested deliverable together so the response has space for both the necessary reasoning and the useful final result.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qwen/qwen3-30b-a3b | Default— |
Fieldmessages | Typemessage[] | RequirementRequired | Values & limits Minimum items: 1 | Default— |
Fieldmessages[].role | Typestring | RequirementRequired | Values & limits Examples: system, user, assistant, tool, function Conditions: These roles are explicitly represented by Source compatibility types; the exact model role set remains model-specific. Model-specific | Default— |
Fieldmessages[].content | Typestring|content_part[]|null | RequirementOptional | Values & limits | Default— |
Fieldmessages[].tool_calls | Typetool_call[] | RequirementOptional | Values & limits | Default— |
Fieldmessages[].tool_call_id | Typestring | RequirementOptional | Values & limits Applies when: role=tool; use actual returned ID | Default— |
Fieldmessages[].name | Typestring | RequirementOptional | Values & limits | Default— |
Fieldmessages[].reasoning_content | Typestring | RequirementOptional | Values & limits Applies when: Round-trip actual returned reasoning where this model uses it | Default— |
Fieldmessages[].reasoning_details | Typeobject|array | RequirementOptional | Values & limits Model-specific | Default— |
Fieldmax_tokens | Typeinteger | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
Fieldmax_completion_tokens | Typeinteger | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
Fieldstream_options.include_usage | Typeboolean | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtemperature | Typenumber | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtop_p | Typenumber | RequirementOptional | Values & limits Model-specific | Default— |
Fieldstop | Typestring|string[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtools | Typefunction_tool[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtools[].type | Typestring | RequirementOptional | Values & limits function Model-specific | Default— |
Fieldtools[].function.name | Typestring | RequirementRequired | Values & limits Applies when: function tool supplied | Default— |
Fieldtools[].function.description | Typestring | RequirementOptional | Values & limits | Default— |
Fieldtools[].function.parameters | TypeJSON_schema | RequirementOptional | Values & limits | Default— |
Fieldtool_choice | Typestring|object | RequirementOptional | Values & limits Model-specific | Default— |
Fieldparallel_tool_calls | Typeboolean | RequirementOptional | Values & limits Model-specific | Default— |
Fieldresponse_format | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Fieldreasoning_effort | Typestring | RequirementOptional | Values & limits Model-specific | Default— |
Fieldreasoning | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Fieldservice_tier | Typestring | RequirementOptional | Values & limits Model-specific | Default— |
Fieldinstructions | Typestring | RequirementOptional | Values & limits Compatibility field | Default— |
Fieldfunctions | Typefunction[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldfunction_call | Typestring|object | RequirementOptional | Values & limits Model-specific | Default— |
Fieldprompt_cache_options | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Fieldmodalities | Typestring[] | RequirementOptional | Values & limits text | Default— |
Fieldprovider | Typeobject | RequirementOptional | Values & limits Conditions: provider.options is rejected on this Ultra text route | Default— |
Fieldcache_control.ttl | Typestring | RequirementOptional | Values & limits Conditions: 1h is rejected in actual prompt-cache locations | Default— |
Text · UTF8 text
messages[].content
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, messages |
Parametermaterial_types | Contracttext |
Parametermessages | Contractmessage array with role/content shape |
Parameterfile_material | Contractactual UTF-8 document inserted as literal text; no file ID inferred |
Parameteroptional_controls | Contractstream, temperature, top_p, stop, max_tokens, max_completion_tokens, reasoning, response_format, tools, tool_choice |
Parametercontrol_scope | Contractmodel-specific; user function tools differ from hosted tools |
Parameteroutput_modalities | Contracttext |
Parameterhosted_operations | Contractfalse |
Parametermultimodal_input_binding | Contractnull |
Lifecycle: synchronous_or_streamed
Send exact model ID with messages.
Context length is not an output cap.
A text file may supply literal text; image/audio/file-object inputs need exact binding.
Tariff references do not add request options. Supported parameters are listed for the selected method.
Match each charge to the conditions shown. Use one rate for each set of alternative configurations.
| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
|---|---|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.00024 / 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 |
| ConfigurationRequest-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.00024 / 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": "qwen/qwen3-30b-a3b", "messages": [{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}]}')\n\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path("result.json").read_text())\nfor x in r.get("choices",[]):\n if x.get("message",{}).get("content"): print(x["message"]["content"])\nPY_RESULT\nfrom openai import OpenAI\nimport os\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nresult=client.chat.completions.create(model='qwen/qwen3-30b-a3b',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}])\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(result.to_dict(mode="json"))\nfrom openai import OpenAI\nimport os\nfrom pathlib import Path\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nwith client.chat.completions.stream(model='qwen/qwen3-30b-a3b',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:\n with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:\n for event in stream:\n payload=event.to_dict(mode="json")\n log.write(json.dumps(payload,ensure_ascii=False)+"\\n"); log.flush()\n print(json.dumps(payload,ensure_ascii=False))\n final=stream.get_final_completion()\n save_result(final.to_dict(mode="json"),"stream-result")\njson or SSE
Keep every complete returned response, file and content part.
Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.
Keep request/response IDs and headers. No generic text job retrieval URL is supplied.
| Field | Type |
|---|---|
Fieldchoices[].index | Typeinteger |
Fieldchoices[].message.content | Typestring|null |
Fieldchoices[].message.tool_calls | Typetool_call[] |
Fieldchoices[].message.reasoning_content | Typestring |
Fieldchoices[].message.reasoning_details | Typeobject|array |
Fieldchoices[].finish_reason | Typestring|null |
Fieldusage | Typeobject |
| Response | Condition | Next step |
|---|---|---|
Response400 · invalid_request_error | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |
Ailoot Ultra qwen/qwen3-30b-a3b
Use the method paths shown above.
qwen/qwen3-30b-a3bQwen3-30B-A3B is Qwen’s mixture-of-experts text model with thinking and non-thinking modes for reasoning, coding and multilingual conversation. It has 30.5 billion total parameters, 3.3 billion active per token and a native 32,768-token context.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Qwen3-30B-A3B combines two styles of response in one text model: thinking for complex logical, mathematical and programming problems, and non-thinking for straightforward dialogue. Qwen also emphasises creative writing, role-based conversation, instruction following and integration with external tools. The original Qwen3 family supports 119 languages and dialects, making this model useful for multilingual questions, translation and conversation where the requested language can change between turns. State the output language, preserve terminology that should remain unchanged and describe the reader’s needs.
This is the original Qwen3-30B-A3B mixture-of-experts edition. Its 30.5 billion total parameters include 3.3 billion activated for each token; eight of its 128 experts are selected in the model’s expert layers. The sparse architecture is a meaningful distinction from Qwen3’s dense models. This profile concerns the original hybrid model, whose native context is 32,768 tokens, rather than a later separately named Instruct-2507 or Thinking-2507 edition. For an analysis brief, supply the relevant code or source passages, the question to resolve and the conditions that a valid answer must meet.
In the official chat template, thinking is enabled by default. The hard enable_thinking switch can disable it completely. When thinking remains enabled, /think and /no_think in a user or system instruction act as soft switches, and the most recent instruction controls the requested behaviour across turns. A /no_think request under an enabled template can still produce an empty thinking block; with the hard switch disabled, neither marker activates thinking. This distinction matters when a workflow alternates between an immediate rewrite and a more involved debugging or reasoning question.
Qwen’s examples separate the <think> section from the final response. For a coding problem, prepare the smallest relevant source excerpt, the observed failure and the desired result, then ask for a diagnosis and a proposed correction. For a mathematics problem, the producer recommends an explicit step-by-step instruction with the final answer placed in \\boxed{}. A multiple-choice brief can instead define a single answer field. In later conversation turns, Qwen recommends retaining the final answer and omitting the earlier thinking content from the history, rather than repeatedly carrying the entire reasoning section forward.
Tool calling is described for both modes. Qwen recommends Qwen-Agent to handle the model’s tool templates and parsing, with examples of retrieval, time information and a code interpreter. Describe the available tools and their arguments before asking it to plan a sequence. A useful brief might request a check of selected documentation followed by a reasoned implementation proposal; return each tool result to the conversation so the model can continue from actual evidence. The textual tool request and the application’s executed result remain separate parts of that workflow.
The card describes context extension to 131,072 tokens using YaRN. It is a configuration-dependent extension of the native window, and Qwen cautions that static scaling can affect shorter inputs. The card also explains a 40,960-position default configuration that allocates space for a typical prompt and a long response; this is distinct from its native-context description. Prepare long material with clear document boundaries, prioritise the parts relevant to the question and leave room for the answer and any reasoning.
For thinking, Qwen recommends temperature 0.6, top-p 0.95, top-k 20 and min-p 0, and advises against greedy decoding because it can degrade results or repeat indefinitely. For non-thinking, its guidance changes temperature to 0.7 and top-p to 0.8. It recommends a 32,768-token output allowance for most queries and describes 38,912 tokens for especially demanding mathematics and programming problems. These are producer generation settings, not a separate fixed response guarantee. Choose the mode and requested deliverable together so the response has space for both the necessary reasoning and the useful final result.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qwen/qwen3-30b-a3b | Default— |
Fieldmessages | Typemessage[] | RequirementRequired | Values & limits | Default— |
Fieldmessages[].role | Typestring | RequirementRequired | Values & limits user, assistant | Default— |
Fieldmessages[].content | Typestring | RequirementRequired | Values & limits | Default— |
Fieldmax_tokens | Typeinteger | RequirementRequired | Values & limits | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
Text · UTF-8 text
messages[].content string
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, messages, max_tokens |
Parameteroptional_controls | Contractstream |
Parametermaterial_types | Contracttext |
Parametertext_file_material | ContractRead the actual UTF-8 document and put its text in the indicated input or message content string. |
Lifecycle: synchronous_or_streamed
Tariff references do not add request options. Supported parameters are listed for the selected method.
Match each charge to the conditions shown. Use one rate for each set of alternative configurations.
| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
|---|---|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.00024 / 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 |
| ConfigurationRequest-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.00024 / 1K tokens Output · Output tokens $0.001 / 1K tokens Input · Cache read $0 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "qwen/qwen3-30b-a3b",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 document}"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ['AILOOT_TEXT_FILE'])\nif not source_file.is_file():\n raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')\ntext = source_file.read_text(encoding='utf-8')\nif not text.strip():\n raise SystemExit('Choose a document containing text')\npayload = {'model': 'qwen/qwen3-30b-a3b', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}\npayload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\\n\\n' + text\nPath('request.json').write_text(json.dumps(payload, ensure_ascii=False), encoding='utf-8')\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\n\nresult = json.loads(Path('result.json').read_text(encoding='utf-8'))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\nPY_RESULT\nimport json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ['AILOOT_TEXT_FILE'])\nif not source_file.is_file():\n raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')\ntext = source_file.read_text(encoding='utf-8')\nif not text.strip():\n raise SystemExit('Choose a document containing text')\npayload = {'model': 'qwen/qwen3-30b-a3b', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}\npayload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\\n\\n' + text\nfrom urllib.request import Request, urlopen\nfrom urllib.error import HTTPError\n\napi_key = os.environ['AILOOT_API_KEY']\nif not api_key.strip():\n raise SystemExit('Set AILOOT_API_KEY before making a request')\nheaders = {'x-api-key': 'PLACEHOLDER_KEY', 'anthropic-version': '2023-06-01', 'Content-Type': 'application/json'}\nheaders['x-api-key'] = api_key\nrequest = Request('https://api.ailoot.ai/v1/messages', data=json.dumps(payload, ensure_ascii=False).encode('utf-8'), headers=headers, method='POST')\ntry:\n with urlopen(request, timeout=120) as response:\n raw = response.read()\n Path('response-headers.txt').write_text(str(response.headers), encoding='utf-8')\nexcept HTTPError as error:\n Path('result.json').write_bytes(error.read())\n Path('response-headers.txt').write_text(str(error.headers), encoding='utf-8')\n raise\nPath('result.json').write_bytes(raw)\nimport json\nfrom pathlib import Path\n\nresult = json.loads(Path('result.json').read_text(encoding='utf-8'))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\nJSON or SSE
Keep every complete returned response, file and content part.
Keep all content blocks, thinking signatures and actual tool-use IDs. Assemble all SSE block deltas; a first text block is not the complete output.
Keep request/response IDs and headers. No generic text job retrieval URL is supplied.
| Field | Type |
|---|---|
Fieldid | Typestring |
Fieldmodel | Typestring |
Fieldcontent[] | Typetext|thinking|tool_use|other content block |
Fieldstop_reason | Typestring|null |
Fieldusage | Typeobject |
| Response | Condition | Next step |
|---|---|---|
Response400 · invalid_request_error | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |
Ailoot Ultra qwen/qwen3-30b-a3b
Use the method paths shown above.
Technical example in English
Explain a weighted-average mistake\n\nA student averages two class scores as (80 + 90) / 2. The first class has 10 students and the second has 30. Explain why that calculation does not give the combined student average, derive the correct weighted expression and state when the simple average would be valid. Finish with the combined average in a separate final line.A short explanation, a weighted formula, its evaluated result and the equal-weight condition.The explanation uses student counts as weights and distinguishes a class average from a student average.