Qwen3-235B-A22B brings Qwen3’s hybrid reasoning approach to a large mixture-of-experts model. Its text capabilities cover mathematical and logical problems, code generation, creative writing, role-based conversations and multi-turn instruction following. It works across more than 100 languages and dialects. For a product-development discussion, provide the requirements, a concrete example and the decision you need: a design comparison, an implementation or an explanation that a particular audience can use.
The model has 235 billion parameters in total and activates 22 billion during processing. Its architecture contains 128 experts, selects eight of them and has 94 layers. These figures identify this release; the smaller Qwen3 models and the FP8 edition have separate identities. Input and output are text. A suitable engineering task is to compare two reconciliation algorithms using the same example records, identify the constraints each satisfies and return the chosen algorithm with test cases. Supply the real field names, duplicate-handling rules and expected totals so the answer can be checked against the original problem.
Prepare the request as chat messages, keeping source material separate from instructions. For a mathematics question, include the complete statement, permitted assumptions and notation, then request a final answer in a specified form. For code, include the relevant function, language, representative input and observed failure. Ask for the smallest justified change and describe which existing behavior must remain. For multilingual writing, give the audience and a terminology list rather than asking for a generic translation. 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 and non-thinking are modes of this same model. The manufacturer’s chat template enables thinking by default; a hard switch can disable it. When thinking remains enabled, /think and /no_think provide turn-level control, with the most recent instruction taking precedence. A hard-disabled mode does not respond to those soft switches. In a developer interface, keep the final answer distinct from the reasoning section, and carry the final answer into subsequent conversation history. Choose the mode deliberately: an algorithm dispute and a short rewrite need different amounts of analysis. With thinking enabled, even a soft non-thinking request retains a reasoning block; its content may be empty. The hard disable removes that block.
For agent workflows, the manufacturer recommends Qwen-Agent for tool templates and parsing. Tools may include connected services or a code interpreter; the application defines and executes them. For example, give an assistant a read-only inventory lookup with documented fields and ask it to compare returned stock with the supplied order. Define the tool’s purpose, accepted arguments, result shape and permission boundary. Require the final response to distinguish a proposed action from a confirmed tool result. The model’s tool-related capabilities do not make an external action occur by themselves. The Qwen3 guide also describes parallel and multi-step tool calls, with arguments represented as objects and results supplied back into the conversation.
The native context is 32,768 tokens. The manufacturer validates 131,072 tokens with YaRN expansion; this is configuration-dependent, and static scaling can affect shorter inputs. The context budget includes both request and generated response. For a long specification, identify the sections relevant to the decision, label them and reserve space for the answer instead of filling the entire budget with source text. The card recommends 32,768 output tokens for most queries rather than declaring that value a universal service limit. 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. The card also explains its default positional allocation of 40,960 tokens as 8,192 for typical prompts plus 32,768 for output; this is manufacturer configuration guidance, separate from the native training context and any endpoint limit.
Recommended thinking-mode sampling is temperature 0.6, top-p 0.95, top-k 20 and min-p 0; non-thinking uses 0.7, 0.8, 20 and 0. The manufacturer recommends sampled decoding and warns that greedy decoding in thinking mode can cause repetition. Higher presence penalties can also introduce language mixing. Make the result easy to inspect: request a named final-answer field, a decision table with reasons, or a code patch plus examples. Check calculations against the supplied numbers, run proposed code in the intended environment and review tool results before taking action.
", "aboutText": "Qwen3-235B-A22B brings Qwen3’s hybrid reasoning approach to a large mixture-of-experts model. Its text capabilities cover mathematical and logical problems, code generation, creative writing, role-based conversations and multi-turn instruction following. It works across more than 100 languages and dialects. For a product-development discussion, provide the requirements, a concrete example and the decision you need: a design comparison, an implementation or an explanation that a particular audience can use.\n\nThe model has 235 billion parameters in total and activates 22 billion during processing. Its architecture contains 128 experts, selects eight of them and has 94 layers. These figures identify this release; the smaller Qwen3 models and the FP8 edition have separate identities. Input and output are text. A suitable engineering task is to compare two reconciliation algorithms using the same example records, identify the constraints each satisfies and return the chosen algorithm with test cases. Supply the real field names, duplicate-handling rules and expected totals so the answer can be checked against the original problem.\n\nPrepare the request as chat messages, keeping source material separate from instructions. For a mathematics question, include the complete statement, permitted assumptions and notation, then request a final answer in a specified form. For code, include the relevant function, language, representative input and observed failure. Ask for the smallest justified change and describe which existing behavior must remain. For multilingual writing, give the audience and a terminology list rather than asking for a generic translation. 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 and non-thinking are modes of this same model. The manufacturer’s chat template enables thinking by default; a hard switch can disable it. When thinking remains enabled, /think and /no_think provide turn-level control, with the most recent instruction taking precedence. A hard-disabled mode does not respond to those soft switches. In a developer interface, keep the final answer distinct from the reasoning section, and carry the final answer into subsequent conversation history. Choose the mode deliberately: an algorithm dispute and a short rewrite need different amounts of analysis. 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\nFor agent workflows, the manufacturer recommends Qwen-Agent for tool templates and parsing. Tools may include connected services or a code interpreter; the application defines and executes them. For example, give an assistant a read-only inventory lookup with documented fields and ask it to compare returned stock with the supplied order. Define the tool’s purpose, accepted arguments, result shape and permission boundary. Require the final response to distinguish a proposed action from a confirmed tool result. The model’s tool-related capabilities do not make an external action occur by themselves. 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 native context is 32,768 tokens. The manufacturer validates 131,072 tokens with YaRN expansion; this is configuration-dependent, and static scaling can affect shorter inputs. The context budget includes both request and generated response. For a long specification, identify the sections relevant to the decision, label them and reserve space for the answer instead of filling the entire budget with source text. The card recommends 32,768 output tokens for most queries rather than declaring that value a universal service limit. 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. The card also explains its default positional allocation of 40,960 tokens as 8,192 for typical prompts plus 32,768 for output; this is manufacturer configuration guidance, separate from the native training context and any endpoint limit.\n\nRecommended thinking-mode sampling is temperature 0.6, top-p 0.95, top-k 20 and min-p 0; non-thinking uses 0.7, 0.8, 20 and 0. The manufacturer recommends sampled decoding and warns that greedy decoding in thinking mode can cause repetition. Higher presence penalties can also introduce language mixing. Make the result easy to inspect: request a named final-answer field, a decision table with reasons, or a code patch plus examples. Check calculations against the supplied numbers, run proposed code in the intended environment and review tool results before taking action.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Reconcile duplicate transaction records\n\nCompare two reconciliation rules on these records: (id=A, revision=1, amount=10), (A,2,12), (B,1,5). Rule X sums every row; rule Y keeps the highest revision per ID, then sums. Requirement: one current amount per ID; equal-revision disagreements must be flagged. Choose a rule, propose pseudocode and give tests for duplicates and conflicting ties.A rule comparison, chosen algorithm, expected total for the supplied records and conflict tests.Check the algorithm uses ID plus revision semantics and does not silently choose between conflicting equal revisions.qwen3-235b-a22bQwen3-235B-A22B combines detailed reasoning and direct text responses in one mixture-of-experts model. Use it for mathematical analysis, code, multilingual writing and assistants that work with connected tools.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Qwen3-235B-A22B brings Qwen3’s hybrid reasoning approach to a large mixture-of-experts model. Its text capabilities cover mathematical and logical problems, code generation, creative writing, role-based conversations and multi-turn instruction following. It works across more than 100 languages and dialects. For a product-development discussion, provide the requirements, a concrete example and the decision you need: a design comparison, an implementation or an explanation that a particular audience can use.
The model has 235 billion parameters in total and activates 22 billion during processing. Its architecture contains 128 experts, selects eight of them and has 94 layers. These figures identify this release; the smaller Qwen3 models and the FP8 edition have separate identities. Input and output are text. A suitable engineering task is to compare two reconciliation algorithms using the same example records, identify the constraints each satisfies and return the chosen algorithm with test cases. Supply the real field names, duplicate-handling rules and expected totals so the answer can be checked against the original problem.
Prepare the request as chat messages, keeping source material separate from instructions. For a mathematics question, include the complete statement, permitted assumptions and notation, then request a final answer in a specified form. For code, include the relevant function, language, representative input and observed failure. Ask for the smallest justified change and describe which existing behavior must remain. For multilingual writing, give the audience and a terminology list rather than asking for a generic translation. 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 and non-thinking are modes of this same model. The manufacturer’s chat template enables thinking by default; a hard switch can disable it. When thinking remains enabled, /think and /no_think provide turn-level control, with the most recent instruction taking precedence. A hard-disabled mode does not respond to those soft switches. In a developer interface, keep the final answer distinct from the reasoning section, and carry the final answer into subsequent conversation history. Choose the mode deliberately: an algorithm dispute and a short rewrite need different amounts of analysis. With thinking enabled, even a soft non-thinking request retains a reasoning block; its content may be empty. The hard disable removes that block.
For agent workflows, the manufacturer recommends Qwen-Agent for tool templates and parsing. Tools may include connected services or a code interpreter; the application defines and executes them. For example, give an assistant a read-only inventory lookup with documented fields and ask it to compare returned stock with the supplied order. Define the tool’s purpose, accepted arguments, result shape and permission boundary. Require the final response to distinguish a proposed action from a confirmed tool result. The model’s tool-related capabilities do not make an external action occur by themselves. The Qwen3 guide also describes parallel and multi-step tool calls, with arguments represented as objects and results supplied back into the conversation.
The native context is 32,768 tokens. The manufacturer validates 131,072 tokens with YaRN expansion; this is configuration-dependent, and static scaling can affect shorter inputs. The context budget includes both request and generated response. For a long specification, identify the sections relevant to the decision, label them and reserve space for the answer instead of filling the entire budget with source text. The card recommends 32,768 output tokens for most queries rather than declaring that value a universal service limit. 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. The card also explains its default positional allocation of 40,960 tokens as 8,192 for typical prompts plus 32,768 for output; this is manufacturer configuration guidance, separate from the native training context and any endpoint limit.
Recommended thinking-mode sampling is temperature 0.6, top-p 0.95, top-k 20 and min-p 0; non-thinking uses 0.7, 0.8, 20 and 0. The manufacturer recommends sampled decoding and warns that greedy decoding in thinking mode can cause repetition. Higher presence penalties can also introduce language mixing. Make the result easy to inspect: request a named final-answer field, a decision table with reasons, or a code patch plus examples. Check calculations against the supplied numbers, run proposed code in the intended environment and review tool results before taking action.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qwen3-235b-a22b | 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 $0.00114 / 1K tokens Output · Output tokens $0.00342 / 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": "qwen3-235b-a22b", "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='qwen3-235b-a22b',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='qwen3-235b-a22b',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 qwen3-235b-a22b
Use the method paths shown above.
qwen3-235b-a22bQwen3-235B-A22B combines detailed reasoning and direct text responses in one mixture-of-experts model. Use it for mathematical analysis, code, multilingual writing and assistants that work with connected tools.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Qwen3-235B-A22B brings Qwen3’s hybrid reasoning approach to a large mixture-of-experts model. Its text capabilities cover mathematical and logical problems, code generation, creative writing, role-based conversations and multi-turn instruction following. It works across more than 100 languages and dialects. For a product-development discussion, provide the requirements, a concrete example and the decision you need: a design comparison, an implementation or an explanation that a particular audience can use.
The model has 235 billion parameters in total and activates 22 billion during processing. Its architecture contains 128 experts, selects eight of them and has 94 layers. These figures identify this release; the smaller Qwen3 models and the FP8 edition have separate identities. Input and output are text. A suitable engineering task is to compare two reconciliation algorithms using the same example records, identify the constraints each satisfies and return the chosen algorithm with test cases. Supply the real field names, duplicate-handling rules and expected totals so the answer can be checked against the original problem.
Prepare the request as chat messages, keeping source material separate from instructions. For a mathematics question, include the complete statement, permitted assumptions and notation, then request a final answer in a specified form. For code, include the relevant function, language, representative input and observed failure. Ask for the smallest justified change and describe which existing behavior must remain. For multilingual writing, give the audience and a terminology list rather than asking for a generic translation. 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 and non-thinking are modes of this same model. The manufacturer’s chat template enables thinking by default; a hard switch can disable it. When thinking remains enabled, /think and /no_think provide turn-level control, with the most recent instruction taking precedence. A hard-disabled mode does not respond to those soft switches. In a developer interface, keep the final answer distinct from the reasoning section, and carry the final answer into subsequent conversation history. Choose the mode deliberately: an algorithm dispute and a short rewrite need different amounts of analysis. With thinking enabled, even a soft non-thinking request retains a reasoning block; its content may be empty. The hard disable removes that block.
For agent workflows, the manufacturer recommends Qwen-Agent for tool templates and parsing. Tools may include connected services or a code interpreter; the application defines and executes them. For example, give an assistant a read-only inventory lookup with documented fields and ask it to compare returned stock with the supplied order. Define the tool’s purpose, accepted arguments, result shape and permission boundary. Require the final response to distinguish a proposed action from a confirmed tool result. The model’s tool-related capabilities do not make an external action occur by themselves. The Qwen3 guide also describes parallel and multi-step tool calls, with arguments represented as objects and results supplied back into the conversation.
The native context is 32,768 tokens. The manufacturer validates 131,072 tokens with YaRN expansion; this is configuration-dependent, and static scaling can affect shorter inputs. The context budget includes both request and generated response. For a long specification, identify the sections relevant to the decision, label them and reserve space for the answer instead of filling the entire budget with source text. The card recommends 32,768 output tokens for most queries rather than declaring that value a universal service limit. 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. The card also explains its default positional allocation of 40,960 tokens as 8,192 for typical prompts plus 32,768 for output; this is manufacturer configuration guidance, separate from the native training context and any endpoint limit.
Recommended thinking-mode sampling is temperature 0.6, top-p 0.95, top-k 20 and min-p 0; non-thinking uses 0.7, 0.8, 20 and 0. The manufacturer recommends sampled decoding and warns that greedy decoding in thinking mode can cause repetition. Higher presence penalties can also introduce language mixing. Make the result easy to inspect: request a named final-answer field, a decision table with reasons, or a code patch plus examples. Check calculations against the supplied numbers, run proposed code in the intended environment and review tool results before taking action.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qwen3-235b-a22b | 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 $0.00114 / 1K tokens Output · Output tokens $0.00342 / 1K tokens Input · Cache read $0 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "qwen3-235b-a22b",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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': 'qwen3-235b-a22b', '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': 'qwen3-235b-a22b', '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 qwen3-235b-a22b
Use the method paths shown above.
Technical example in English
Reconcile duplicate transaction records\n\nCompare two reconciliation rules on these records: (id=A, revision=1, amount=10), (A,2,12), (B,1,5). Rule X sums every row; rule Y keeps the highest revision per ID, then sums. Requirement: one current amount per ID; equal-revision disagreements must be flagged. Choose a rule, propose pseudocode and give tests for duplicates and conflicting ties.A rule comparison, chosen algorithm, expected total for the supplied records and conflict tests.Check the algorithm uses ID plus revision semantics and does not silently choose between conflicting equal revisions.