Introduction: Qwen3.8 Max family capabilities
Qwen3.8 Max Prime belongs to the Qwen3.8 Max family. Qwen develops this family for coding, professional work, research and tasks that span many connected steps. Its practical purpose is to keep the requirements in view, use new information as the work progresses and produce a finished textual artifact. The Prime edition retains its own identity; the family description does not establish a distinct set of weights or an edition-specific response-time guarantee.
Core work: coding, professional tasks and research
For a development task, provide the relevant project files or excerpts, the behavior being changed and the expected deliverable. Request a diagnosis, an implementation proposal and checks that would show whether the change meets the requirement. For a research task, supply the material to compare and ask for a report that distinguishes source evidence from interpretation. For a professional document, specify the audience, sections and criteria for a complete result. Use the source material and completion criteria to review the resulting diagnosis, report or document.
Agent execution and feedback
The maker emphasizes autonomous planning and the ability to use feedback from an environment. An agent task can be framed as a goal, permitted actions, relevant tools and a visible condition for completion. For example, an application might let the model inspect a repository, propose a change, receive the result of a permitted check and revise its next step. The model contributes planning and reasoning; the application connects tools and performs their actions.
Ask for a record of completed work and unresolved conditions alongside the final artifact. This helps distinguish a proposed next step from an executed action. A task that spans several steps still needs explicit inputs and feedback; a model’s planning capability is not evidence that it has access to a computer, current sources or business systems.
Compatibility and reasoning control
Qwen3.8’s family documentation describes integration with development harnesses and controls for reasoning depth through reasoning_effort. It also describes preserving reasoning context across conversation history through preserve_thinking. Those are manufacturer features whose availability and exact settings depend on the edition and interface. Keep corrections and tool results associated with the task they update, and ask for a concise final conclusion even when the reasoning is lengthy.
The maker distinguishes the managed Qwen3.8-Max offering from the open Qwen3.8-2.4T-A95B checkpoint. Its Max reference includes text, image and video input, text output and direct-answer support; the open checkpoint is text-only and always uses thinking. Those contracts should remain distinct. For Max-family visual work, provide readable document pages, diagrams or the relevant video segment and identify which evidence the answer should discuss.
Tools and structured results
The manufacturer’s managed Max reference lists function calling, structured outputs, retrieval and code-interpreter-style tools, with support depending on the interface. A useful document workflow can request a table of findings with supporting page or section references; a coding workflow can request a patch and a separate explanation. Enforced output schemas and external execution are features of the connected workflow, not consequences of putting the word JSON or “run” in a prompt. This family description does not promise that every listed managed feature is exposed by Prime or another application.
Context and edition-specific limits
The managed Max reference describes a one-million-token context, with separate rounded input, output and reasoning allowances. The open checkpoint instead documents a native 262,144-token context and conditional extension to 1,010,000. These are different producer specifications and should not be collapsed into one universal Prime limit. The exact Prime-specific output ceiling, media limits and control contract are not established by the family sources used here.
Prepare only the material needed for the task and reserve space for the explanation and final artifact. Preserve document boundaries and code identifiers in long inputs so conclusions remain traceable. Check generated code, calculations and cited passages against the supplied evidence. Keep the final implementation, report or document tied to the supplied evidence and the task’s completion criteria.
", "aboutText": "Introduction: Qwen3.8 Max family capabilities\n\nQwen3.8 Max Prime belongs to the Qwen3.8 Max family. Qwen develops this family for coding, professional work, research and tasks that span many connected steps. Its practical purpose is to keep the requirements in view, use new information as the work progresses and produce a finished textual artifact. The Prime edition retains its own identity; the family description does not establish a distinct set of weights or an edition-specific response-time guarantee.\n\nCore work: coding, professional tasks and research\n\nFor a development task, provide the relevant project files or excerpts, the behavior being changed and the expected deliverable. Request a diagnosis, an implementation proposal and checks that would show whether the change meets the requirement. For a research task, supply the material to compare and ask for a report that distinguishes source evidence from interpretation. For a professional document, specify the audience, sections and criteria for a complete result. Use the source material and completion criteria to review the resulting diagnosis, report or document.\n\nAgent execution and feedback\n\nThe maker emphasizes autonomous planning and the ability to use feedback from an environment. An agent task can be framed as a goal, permitted actions, relevant tools and a visible condition for completion. For example, an application might let the model inspect a repository, propose a change, receive the result of a permitted check and revise its next step. The model contributes planning and reasoning; the application connects tools and performs their actions.\n\nAsk for a record of completed work and unresolved conditions alongside the final artifact. This helps distinguish a proposed next step from an executed action. A task that spans several steps still needs explicit inputs and feedback; a model’s planning capability is not evidence that it has access to a computer, current sources or business systems.\n\nCompatibility and reasoning control\n\nQwen3.8’s family documentation describes integration with development harnesses and controls for reasoning depth through reasoning_effort. It also describes preserving reasoning context across conversation history through preserve_thinking. Those are manufacturer features whose availability and exact settings depend on the edition and interface. Keep corrections and tool results associated with the task they update, and ask for a concise final conclusion even when the reasoning is lengthy.\n\nThe maker distinguishes the managed Qwen3.8-Max offering from the open Qwen3.8-2.4T-A95B checkpoint. Its Max reference includes text, image and video input, text output and direct-answer support; the open checkpoint is text-only and always uses thinking. Those contracts should remain distinct. For Max-family visual work, provide readable document pages, diagrams or the relevant video segment and identify which evidence the answer should discuss.\n\nTools and structured results\n\nThe manufacturer’s managed Max reference lists function calling, structured outputs, retrieval and code-interpreter-style tools, with support depending on the interface. A useful document workflow can request a table of findings with supporting page or section references; a coding workflow can request a patch and a separate explanation. Enforced output schemas and external execution are features of the connected workflow, not consequences of putting the word JSON or “run” in a prompt. This family description does not promise that every listed managed feature is exposed by Prime or another application.\n\nContext and edition-specific limits\n\nThe managed Max reference describes a one-million-token context, with separate rounded input, output and reasoning allowances. The open checkpoint instead documents a native 262,144-token context and conditional extension to 1,010,000. These are different producer specifications and should not be collapsed into one universal Prime limit. The exact Prime-specific output ceiling, media limits and control contract are not established by the family sources used here.\n\nPrepare only the material needed for the task and reserve space for the explanation and final artifact. Preserve document boundaries and code identifiers in long inputs so conclusions remain traceable. Check generated code, calculations and cited passages against the supplied evidence. Keep the final implementation, report or document tied to the supplied evidence and the task’s completion criteria.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Produce an evidence-based readiness memo\n\nPrepare a release-readiness memo from supplied feedback. [REQUIREMENTS] New exports must preserve column order and empty headings. [CHECK A] Column order passed. [CHECK B] Empty headings were dropped. [REVIEW] Preserve all header cells, including blank ones. Give the decision, a focused correction proposal and the exact follow-up check needed. Do not report unexecuted work as complete.A short readiness decision with evidence, proposed correction and a targeted recheck definition.Check the memo treats the failed header case as unresolved despite the passing order check.qwen/qwen3.8-max-primeQwen3.8 Max Prime belongs to Qwen’s Max family for coding, professional work, research and sustained agent tasks. Its useful task scope includes interpreting requirements, working through feedback and preparing complete textual deliverables from supplied project material.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Introduction: Qwen3.8 Max family capabilities
Qwen3.8 Max Prime belongs to the Qwen3.8 Max family. Qwen develops this family for coding, professional work, research and tasks that span many connected steps. Its practical purpose is to keep the requirements in view, use new information as the work progresses and produce a finished textual artifact. The Prime edition retains its own identity; the family description does not establish a distinct set of weights or an edition-specific response-time guarantee.
Core work: coding, professional tasks and research
For a development task, provide the relevant project files or excerpts, the behavior being changed and the expected deliverable. Request a diagnosis, an implementation proposal and checks that would show whether the change meets the requirement. For a research task, supply the material to compare and ask for a report that distinguishes source evidence from interpretation. For a professional document, specify the audience, sections and criteria for a complete result. Use the source material and completion criteria to review the resulting diagnosis, report or document.
Agent execution and feedback
The maker emphasizes autonomous planning and the ability to use feedback from an environment. An agent task can be framed as a goal, permitted actions, relevant tools and a visible condition for completion. For example, an application might let the model inspect a repository, propose a change, receive the result of a permitted check and revise its next step. The model contributes planning and reasoning; the application connects tools and performs their actions.
Ask for a record of completed work and unresolved conditions alongside the final artifact. This helps distinguish a proposed next step from an executed action. A task that spans several steps still needs explicit inputs and feedback; a model’s planning capability is not evidence that it has access to a computer, current sources or business systems.
Compatibility and reasoning control
Qwen3.8’s family documentation describes integration with development harnesses and controls for reasoning depth through reasoning_effort. It also describes preserving reasoning context across conversation history through preserve_thinking. Those are manufacturer features whose availability and exact settings depend on the edition and interface. Keep corrections and tool results associated with the task they update, and ask for a concise final conclusion even when the reasoning is lengthy.
The maker distinguishes the managed Qwen3.8-Max offering from the open Qwen3.8-2.4T-A95B checkpoint. Its Max reference includes text, image and video input, text output and direct-answer support; the open checkpoint is text-only and always uses thinking. Those contracts should remain distinct. For Max-family visual work, provide readable document pages, diagrams or the relevant video segment and identify which evidence the answer should discuss.
Tools and structured results
The manufacturer’s managed Max reference lists function calling, structured outputs, retrieval and code-interpreter-style tools, with support depending on the interface. A useful document workflow can request a table of findings with supporting page or section references; a coding workflow can request a patch and a separate explanation. Enforced output schemas and external execution are features of the connected workflow, not consequences of putting the word JSON or “run” in a prompt. This family description does not promise that every listed managed feature is exposed by Prime or another application.
Context and edition-specific limits
The managed Max reference describes a one-million-token context, with separate rounded input, output and reasoning allowances. The open checkpoint instead documents a native 262,144-token context and conditional extension to 1,010,000. These are different producer specifications and should not be collapsed into one universal Prime limit. The exact Prime-specific output ceiling, media limits and control contract are not established by the family sources used here.
Prepare only the material needed for the task and reserve space for the explanation and final artifact. Preserve document boundaries and code identifiers in long inputs so conclusions remain traceable. Check generated code, calculations and cited passages against the supplied evidence. Keep the final implementation, report or document tied to the supplied evidence and the task’s completion criteria.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qwen/qwen3.8-max-prime | 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 $0.008 / 1K tokens Output · Output tokens $0.024 / 1K tokens Input · Cache read $0.001 / 1K tokens Input · Cache write — / 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 $0.008 / 1K tokens Output · Output tokens $0.024 / 1K tokens Input · Cache read $0.001 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "qwen/qwen3.8-max-prime", "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/qwen3.8-max-prime',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/qwen3.8-max-prime',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/qwen3.8-max-prime
Use the method paths shown above.
qwen/qwen3.8-max-primeQwen3.8 Max Prime belongs to Qwen’s Max family for coding, professional work, research and sustained agent tasks. Its useful task scope includes interpreting requirements, working through feedback and preparing complete textual deliverables from supplied project material.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Introduction: Qwen3.8 Max family capabilities
Qwen3.8 Max Prime belongs to the Qwen3.8 Max family. Qwen develops this family for coding, professional work, research and tasks that span many connected steps. Its practical purpose is to keep the requirements in view, use new information as the work progresses and produce a finished textual artifact. The Prime edition retains its own identity; the family description does not establish a distinct set of weights or an edition-specific response-time guarantee.
Core work: coding, professional tasks and research
For a development task, provide the relevant project files or excerpts, the behavior being changed and the expected deliverable. Request a diagnosis, an implementation proposal and checks that would show whether the change meets the requirement. For a research task, supply the material to compare and ask for a report that distinguishes source evidence from interpretation. For a professional document, specify the audience, sections and criteria for a complete result. Use the source material and completion criteria to review the resulting diagnosis, report or document.
Agent execution and feedback
The maker emphasizes autonomous planning and the ability to use feedback from an environment. An agent task can be framed as a goal, permitted actions, relevant tools and a visible condition for completion. For example, an application might let the model inspect a repository, propose a change, receive the result of a permitted check and revise its next step. The model contributes planning and reasoning; the application connects tools and performs their actions.
Ask for a record of completed work and unresolved conditions alongside the final artifact. This helps distinguish a proposed next step from an executed action. A task that spans several steps still needs explicit inputs and feedback; a model’s planning capability is not evidence that it has access to a computer, current sources or business systems.
Compatibility and reasoning control
Qwen3.8’s family documentation describes integration with development harnesses and controls for reasoning depth through reasoning_effort. It also describes preserving reasoning context across conversation history through preserve_thinking. Those are manufacturer features whose availability and exact settings depend on the edition and interface. Keep corrections and tool results associated with the task they update, and ask for a concise final conclusion even when the reasoning is lengthy.
The maker distinguishes the managed Qwen3.8-Max offering from the open Qwen3.8-2.4T-A95B checkpoint. Its Max reference includes text, image and video input, text output and direct-answer support; the open checkpoint is text-only and always uses thinking. Those contracts should remain distinct. For Max-family visual work, provide readable document pages, diagrams or the relevant video segment and identify which evidence the answer should discuss.
Tools and structured results
The manufacturer’s managed Max reference lists function calling, structured outputs, retrieval and code-interpreter-style tools, with support depending on the interface. A useful document workflow can request a table of findings with supporting page or section references; a coding workflow can request a patch and a separate explanation. Enforced output schemas and external execution are features of the connected workflow, not consequences of putting the word JSON or “run” in a prompt. This family description does not promise that every listed managed feature is exposed by Prime or another application.
Context and edition-specific limits
The managed Max reference describes a one-million-token context, with separate rounded input, output and reasoning allowances. The open checkpoint instead documents a native 262,144-token context and conditional extension to 1,010,000. These are different producer specifications and should not be collapsed into one universal Prime limit. The exact Prime-specific output ceiling, media limits and control contract are not established by the family sources used here.
Prepare only the material needed for the task and reserve space for the explanation and final artifact. Preserve document boundaries and code identifiers in long inputs so conclusions remain traceable. Check generated code, calculations and cited passages against the supplied evidence. Keep the final implementation, report or document tied to the supplied evidence and the task’s completion criteria.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qwen/qwen3.8-max-prime | 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 $0.008 / 1K tokens Output · Output tokens $0.024 / 1K tokens Input · Cache read $0.001 / 1K tokens Input · Cache write — / 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 $0.008 / 1K tokens Output · Output tokens $0.024 / 1K tokens Input · Cache read $0.001 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "qwen/qwen3.8-max-prime",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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/qwen3.8-max-prime', '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/qwen3.8-max-prime', '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/qwen3.8-max-prime
Use the method paths shown above.
Technical example in English
Produce an evidence-based readiness memo\n\nPrepare a release-readiness memo from supplied feedback. [REQUIREMENTS] New exports must preserve column order and empty headings. [CHECK A] Column order passed. [CHECK B] Empty headings were dropped. [REVIEW] Preserve all header cells, including blank ones. Give the decision, a focused correction proposal and the exact follow-up check needed. Do not report unexecuted work as complete.A short readiness decision with evidence, proposed correction and a targeted recheck definition.Check the memo treats the failed header case as unresolved despite the passing order check.