Qwen3-Next highlights: direct text instructions
Qwen3-Next-80B-A3B-Instruct is the instruct, non-thinking text edition of Qwen3-Next. It accepts text and returns text, including explanations, code proposals and requested document artifacts. It does not generate explicit thinking blocks. Keep it distinct from the Thinking edition and the coding-specialized Qwen3-Coder-Next; sharing a family architecture does not make their response contracts interchangeable.
The family introduces hybrid attention combining Gated DeltaNet and gated attention, high-sparsity experts, stability optimizations including zero-centered and weight-decayed layer normalization, and multi-token prediction. Those changes address the representation and training of long sequences. Their inference efficiency depends on implementation, so architecture figures should not become a fixed latency or throughput guarantee.
Model overview
The checkpoint has 80 billion parameters in total and activates three billion. It has 48 layers in a repeated three-DeltaNet-to-one-gated-attention expert pattern. The maker lists 512 experts, ten activated experts and one shared expert, with pretraining on 15 trillion tokens followed by post-training. Activated parameters are not the size of the complete checkpoint.
The native context is 262,144 tokens, with documented extension to 1,010,000. The maker’s deployment examples allow a smaller context, such as 32,768, when resource constraints prevent the larger setting from working. Text, conversation history, tool observations and generated content share the configured sequence allowance. The extension is an additional configuration path rather than a default unlimited input.
Using the instruct interface
This model supports only instruct, non-thinking mode. It can explain an algorithm, show calculations or justify a conclusion in ordinary text without producing a dedicated thinking block. Ask for the artifact’s format and boundaries: a complete function, a concise report, an evidence table or an answer with supporting steps. A request for a long explanation does not turn it into the separately named Thinking checkpoint.
For a document task, preserve section identifiers and define the questions the report must answer. For code, provide the relevant function or module, input constraints and expected output. For mathematics, give the complete statement and request a delimited final result. Compare the returned calculations, code or explanation with the supplied conditions and actual results.
Implementation and tools
The maker documents tool calling and recommends Qwen-Agent for templates and parsing, with configured or MCP-connected tools. A connected workflow can provide retrieval, inspection or permitted execution and return actual observations. State the tools, allowed actions and visible completion conditions, then ask the final report to distinguish proposals from real returned results.
Multi-token prediction is part of training, but its inference use is implementation-dependent and is not generally available in every lightweight workflow. A template or architecture feature does not itself establish access to current sources, files or a code environment. Preserve the exact model and conversation format used by the chosen interface.
Ultra-long text
The maker validates approximately one-million-token context with YaRN and gives a factor-of-four recipe based on 262,144 native positions. For 524,288-token workloads, it suggests a factor of two. Static scaling can lower shorter-text performance, so configuration should follow the actual need for longer input.
Keep long material organized by document, code path or section and remove unrelated repetitions. Ask the answer to identify its supporting passages or conditions. Reserve space for the response rather than treat the largest context number as complete recall of every supplied detail. The published 1,010,000 extension figure and the validation around one million remain scoped to the maker’s long-context workflow.
Generation guidance
Best Practices recommend temperature 0.7, top_p 0.8, top_k 20 and min_p 0. Where supported, a presence penalty between zero and two can reduce repeated text, but higher values may mix languages or slightly reduce quality. The maker recommends a 16,384-token output allowance for most queries. This is a recommended generation budget rather than an independent hard maximum; it should not inherit the Thinking edition’s longer allowances.
Specify the result form explicitly, such as a mathematical delimiter or an answer field. Keep the final artifact easy to inspect and verify its calculations, quotations or code against the source. This text-only edition does not accept images, audio or video as its own input, so those materials need an appropriate separate representation before they can support the task.
Practical result
The useful output is a concrete text artifact grounded in the supplied conditions: a document explanation, code proposal or direct answer with the required supporting detail. Long context and tool calling can help carry more evidence through a workflow, while the non-thinking contract keeps this exact edition’s output style clear. Check the result in the real task environment rather than infer correctness from its length or confident wording.
", "aboutText": "Qwen3-Next highlights: direct text instructions\n\nQwen3-Next-80B-A3B-Instruct is the instruct, non-thinking text edition of Qwen3-Next. It accepts text and returns text, including explanations, code proposals and requested document artifacts. It does not generate explicit thinking blocks. Keep it distinct from the Thinking edition and the coding-specialized Qwen3-Coder-Next; sharing a family architecture does not make their response contracts interchangeable.\n\nThe family introduces hybrid attention combining Gated DeltaNet and gated attention, high-sparsity experts, stability optimizations including zero-centered and weight-decayed layer normalization, and multi-token prediction. Those changes address the representation and training of long sequences. Their inference efficiency depends on implementation, so architecture figures should not become a fixed latency or throughput guarantee.\n\nModel overview\n\nThe checkpoint has 80 billion parameters in total and activates three billion. It has 48 layers in a repeated three-DeltaNet-to-one-gated-attention expert pattern. The maker lists 512 experts, ten activated experts and one shared expert, with pretraining on 15 trillion tokens followed by post-training. Activated parameters are not the size of the complete checkpoint.\n\nThe native context is 262,144 tokens, with documented extension to 1,010,000. The maker’s deployment examples allow a smaller context, such as 32,768, when resource constraints prevent the larger setting from working. Text, conversation history, tool observations and generated content share the configured sequence allowance. The extension is an additional configuration path rather than a default unlimited input.\n\nUsing the instruct interface\n\nThis model supports only instruct, non-thinking mode. It can explain an algorithm, show calculations or justify a conclusion in ordinary text without producing a dedicated thinking block. Ask for the artifact’s format and boundaries: a complete function, a concise report, an evidence table or an answer with supporting steps. A request for a long explanation does not turn it into the separately named Thinking checkpoint.\n\nFor a document task, preserve section identifiers and define the questions the report must answer. For code, provide the relevant function or module, input constraints and expected output. For mathematics, give the complete statement and request a delimited final result. Compare the returned calculations, code or explanation with the supplied conditions and actual results.\n\nImplementation and tools\n\nThe maker documents tool calling and recommends Qwen-Agent for templates and parsing, with configured or MCP-connected tools. A connected workflow can provide retrieval, inspection or permitted execution and return actual observations. State the tools, allowed actions and visible completion conditions, then ask the final report to distinguish proposals from real returned results.\n\nMulti-token prediction is part of training, but its inference use is implementation-dependent and is not generally available in every lightweight workflow. A template or architecture feature does not itself establish access to current sources, files or a code environment. Preserve the exact model and conversation format used by the chosen interface.\n\nUltra-long text\n\nThe maker validates approximately one-million-token context with YaRN and gives a factor-of-four recipe based on 262,144 native positions. For 524,288-token workloads, it suggests a factor of two. Static scaling can lower shorter-text performance, so configuration should follow the actual need for longer input.\n\nKeep long material organized by document, code path or section and remove unrelated repetitions. Ask the answer to identify its supporting passages or conditions. Reserve space for the response rather than treat the largest context number as complete recall of every supplied detail. The published 1,010,000 extension figure and the validation around one million remain scoped to the maker’s long-context workflow.\n\nGeneration guidance\n\nBest Practices recommend temperature 0.7, top_p 0.8, top_k 20 and min_p 0. Where supported, a presence penalty between zero and two can reduce repeated text, but higher values may mix languages or slightly reduce quality. The maker recommends a 16,384-token output allowance for most queries. This is a recommended generation budget rather than an independent hard maximum; it should not inherit the Thinking edition’s longer allowances.\n\nSpecify the result form explicitly, such as a mathematical delimiter or an answer field. Keep the final artifact easy to inspect and verify its calculations, quotations or code against the source. This text-only edition does not accept images, audio or video as its own input, so those materials need an appropriate separate representation before they can support the task.\n\nPractical result\n\nThe useful output is a concrete text artifact grounded in the supplied conditions: a document explanation, code proposal or direct answer with the required supporting detail. Long context and tool calling can help carry more evidence through a workflow, while the non-thinking contract keeps this exact edition’s output style clear. Check the result in the real task environment rather than infer correctness from its length or confident wording.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Explain a section-specific decision\n\nAnswer only from these procedure sections. Section 2: standard purchases need a manager's approval. Section 4: emergency safety purchases may proceed first, but must be reported to that manager within one day. Case: a broken emergency exit light needs replacement today. Give a concise recommendation with section references and identify the follow-up obligation. Do not invent an approval already granted.A direct recommendation with supporting sections and the one-day reporting obligation.The emergency exception retains its reporting condition and is not generalised to all purchases.qwen/qwen3-next-80b-a3b-instructQwen3-Next-80B-A3B-Instruct is Qwen’s non-thinking text edition with 80 billion total and 3 billion activated parameters. It combines hybrid attention, sparse experts and tool calling with a native 262,144-token context, extendable to 1,010,000 through configuration.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Qwen3-Next highlights: direct text instructions
Qwen3-Next-80B-A3B-Instruct is the instruct, non-thinking text edition of Qwen3-Next. It accepts text and returns text, including explanations, code proposals and requested document artifacts. It does not generate explicit thinking blocks. Keep it distinct from the Thinking edition and the coding-specialized Qwen3-Coder-Next; sharing a family architecture does not make their response contracts interchangeable.
The family introduces hybrid attention combining Gated DeltaNet and gated attention, high-sparsity experts, stability optimizations including zero-centered and weight-decayed layer normalization, and multi-token prediction. Those changes address the representation and training of long sequences. Their inference efficiency depends on implementation, so architecture figures should not become a fixed latency or throughput guarantee.
Model overview
The checkpoint has 80 billion parameters in total and activates three billion. It has 48 layers in a repeated three-DeltaNet-to-one-gated-attention expert pattern. The maker lists 512 experts, ten activated experts and one shared expert, with pretraining on 15 trillion tokens followed by post-training. Activated parameters are not the size of the complete checkpoint.
The native context is 262,144 tokens, with documented extension to 1,010,000. The maker’s deployment examples allow a smaller context, such as 32,768, when resource constraints prevent the larger setting from working. Text, conversation history, tool observations and generated content share the configured sequence allowance. The extension is an additional configuration path rather than a default unlimited input.
Using the instruct interface
This model supports only instruct, non-thinking mode. It can explain an algorithm, show calculations or justify a conclusion in ordinary text without producing a dedicated thinking block. Ask for the artifact’s format and boundaries: a complete function, a concise report, an evidence table or an answer with supporting steps. A request for a long explanation does not turn it into the separately named Thinking checkpoint.
For a document task, preserve section identifiers and define the questions the report must answer. For code, provide the relevant function or module, input constraints and expected output. For mathematics, give the complete statement and request a delimited final result. Compare the returned calculations, code or explanation with the supplied conditions and actual results.
Implementation and tools
The maker documents tool calling and recommends Qwen-Agent for templates and parsing, with configured or MCP-connected tools. A connected workflow can provide retrieval, inspection or permitted execution and return actual observations. State the tools, allowed actions and visible completion conditions, then ask the final report to distinguish proposals from real returned results.
Multi-token prediction is part of training, but its inference use is implementation-dependent and is not generally available in every lightweight workflow. A template or architecture feature does not itself establish access to current sources, files or a code environment. Preserve the exact model and conversation format used by the chosen interface.
Ultra-long text
The maker validates approximately one-million-token context with YaRN and gives a factor-of-four recipe based on 262,144 native positions. For 524,288-token workloads, it suggests a factor of two. Static scaling can lower shorter-text performance, so configuration should follow the actual need for longer input.
Keep long material organized by document, code path or section and remove unrelated repetitions. Ask the answer to identify its supporting passages or conditions. Reserve space for the response rather than treat the largest context number as complete recall of every supplied detail. The published 1,010,000 extension figure and the validation around one million remain scoped to the maker’s long-context workflow.
Generation guidance
Best Practices recommend temperature 0.7, top_p 0.8, top_k 20 and min_p 0. Where supported, a presence penalty between zero and two can reduce repeated text, but higher values may mix languages or slightly reduce quality. The maker recommends a 16,384-token output allowance for most queries. This is a recommended generation budget rather than an independent hard maximum; it should not inherit the Thinking edition’s longer allowances.
Specify the result form explicitly, such as a mathematical delimiter or an answer field. Keep the final artifact easy to inspect and verify its calculations, quotations or code against the source. This text-only edition does not accept images, audio or video as its own input, so those materials need an appropriate separate representation before they can support the task.
Practical result
The useful output is a concrete text artifact grounded in the supplied conditions: a document explanation, code proposal or direct answer with the required supporting detail. Long context and tool calling can help carry more evidence through a workflow, while the non-thinking contract keeps this exact edition’s output style clear. Check the result in the real task environment rather than infer correctness from its length or confident wording.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qwen/qwen3-next-80b-a3b-instruct | 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 $0.000286 / 1K tokens Output · Output tokens $0.0022 / 1K tokens Input · Cache read $0.00014 / 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 $0.000286 / 1K tokens Output · Output tokens $0.0022 / 1K tokens Input · Cache read $0.00014 / 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-next-80b-a3b-instruct", "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-next-80b-a3b-instruct',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-next-80b-a3b-instruct',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-next-80b-a3b-instruct
Use the method paths shown above.
qwen/qwen3-next-80b-a3b-instructQwen3-Next-80B-A3B-Instruct is Qwen’s non-thinking text edition with 80 billion total and 3 billion activated parameters. It combines hybrid attention, sparse experts and tool calling with a native 262,144-token context, extendable to 1,010,000 through configuration.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Qwen3-Next highlights: direct text instructions
Qwen3-Next-80B-A3B-Instruct is the instruct, non-thinking text edition of Qwen3-Next. It accepts text and returns text, including explanations, code proposals and requested document artifacts. It does not generate explicit thinking blocks. Keep it distinct from the Thinking edition and the coding-specialized Qwen3-Coder-Next; sharing a family architecture does not make their response contracts interchangeable.
The family introduces hybrid attention combining Gated DeltaNet and gated attention, high-sparsity experts, stability optimizations including zero-centered and weight-decayed layer normalization, and multi-token prediction. Those changes address the representation and training of long sequences. Their inference efficiency depends on implementation, so architecture figures should not become a fixed latency or throughput guarantee.
Model overview
The checkpoint has 80 billion parameters in total and activates three billion. It has 48 layers in a repeated three-DeltaNet-to-one-gated-attention expert pattern. The maker lists 512 experts, ten activated experts and one shared expert, with pretraining on 15 trillion tokens followed by post-training. Activated parameters are not the size of the complete checkpoint.
The native context is 262,144 tokens, with documented extension to 1,010,000. The maker’s deployment examples allow a smaller context, such as 32,768, when resource constraints prevent the larger setting from working. Text, conversation history, tool observations and generated content share the configured sequence allowance. The extension is an additional configuration path rather than a default unlimited input.
Using the instruct interface
This model supports only instruct, non-thinking mode. It can explain an algorithm, show calculations or justify a conclusion in ordinary text without producing a dedicated thinking block. Ask for the artifact’s format and boundaries: a complete function, a concise report, an evidence table or an answer with supporting steps. A request for a long explanation does not turn it into the separately named Thinking checkpoint.
For a document task, preserve section identifiers and define the questions the report must answer. For code, provide the relevant function or module, input constraints and expected output. For mathematics, give the complete statement and request a delimited final result. Compare the returned calculations, code or explanation with the supplied conditions and actual results.
Implementation and tools
The maker documents tool calling and recommends Qwen-Agent for templates and parsing, with configured or MCP-connected tools. A connected workflow can provide retrieval, inspection or permitted execution and return actual observations. State the tools, allowed actions and visible completion conditions, then ask the final report to distinguish proposals from real returned results.
Multi-token prediction is part of training, but its inference use is implementation-dependent and is not generally available in every lightweight workflow. A template or architecture feature does not itself establish access to current sources, files or a code environment. Preserve the exact model and conversation format used by the chosen interface.
Ultra-long text
The maker validates approximately one-million-token context with YaRN and gives a factor-of-four recipe based on 262,144 native positions. For 524,288-token workloads, it suggests a factor of two. Static scaling can lower shorter-text performance, so configuration should follow the actual need for longer input.
Keep long material organized by document, code path or section and remove unrelated repetitions. Ask the answer to identify its supporting passages or conditions. Reserve space for the response rather than treat the largest context number as complete recall of every supplied detail. The published 1,010,000 extension figure and the validation around one million remain scoped to the maker’s long-context workflow.
Generation guidance
Best Practices recommend temperature 0.7, top_p 0.8, top_k 20 and min_p 0. Where supported, a presence penalty between zero and two can reduce repeated text, but higher values may mix languages or slightly reduce quality. The maker recommends a 16,384-token output allowance for most queries. This is a recommended generation budget rather than an independent hard maximum; it should not inherit the Thinking edition’s longer allowances.
Specify the result form explicitly, such as a mathematical delimiter or an answer field. Keep the final artifact easy to inspect and verify its calculations, quotations or code against the source. This text-only edition does not accept images, audio or video as its own input, so those materials need an appropriate separate representation before they can support the task.
Practical result
The useful output is a concrete text artifact grounded in the supplied conditions: a document explanation, code proposal or direct answer with the required supporting detail. Long context and tool calling can help carry more evidence through a workflow, while the non-thinking contract keeps this exact edition’s output style clear. Check the result in the real task environment rather than infer correctness from its length or confident wording.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qwen/qwen3-next-80b-a3b-instruct | 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 $0.000286 / 1K tokens Output · Output tokens $0.0022 / 1K tokens Input · Cache read $0.00014 / 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 $0.000286 / 1K tokens Output · Output tokens $0.0022 / 1K tokens Input · Cache read $0.00014 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "qwen/qwen3-next-80b-a3b-instruct",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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-next-80b-a3b-instruct', '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-next-80b-a3b-instruct', '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-next-80b-a3b-instruct
Use the method paths shown above.
Technical example in English
Explain a section-specific decision\n\nAnswer only from these procedure sections. Section 2: standard purchases need a manager's approval. Section 4: emergency safety purchases may proceed first, but must be reported to that manager within one day. Case: a broken emergency exit light needs replacement today. Give a concise recommendation with section references and identify the follow-up obligation. Do not invent an approval already granted.A direct recommendation with supporting sections and the one-day reporting obligation.The emergency exception retains its reporting condition and is not generalised to all purchases.