The fixed 0902 snapshot
Qwen3.8-Max-0902 is the September 2, 2026 snapshot of Qwen3.8-Max. The maker’s update notice identifies it as a specific upgrade of Max, with deeper coding capabilities, stronger agent collaboration and refined visual understanding. The release also documents the name qwen3.8-max-2026-09-02 for this snapshot. Preserve the requested dated identity when the work requires a fixed edition; a moving Max name does not itself remain a permanent record of that version.
Coding depth and sustained development
The manufacturer describes support for more complex engineering-scale projects and development tasks that continue over many steps. Prepare a repository question with the relevant modules, requirements, constraints and expected result. Ask the model to explain the affected components, propose an implementation sequence and return the required patch or code artifact. A useful completion report should distinguish the changes proposed from the checks actually performed by the connected workflow.
For a larger task, define intermediate evidence: the behavior that should change, the inputs exposing the current problem and the result expected after each step. Feed observed errors or review findings back into the next turn.
Agent collaboration and tools
The notice highlights improved coordination with several tools and more stable task delivery. Qwen’s Max family documentation describes autonomous planning and closed feedback loops. An application can provide tools for retrieval, inspection or permitted execution and return their results to the model. The model can then revise a plan in response to what happened rather than treat the initial proposal as completed work.
The managed Max reference lists function calling, structured outputs and retrieval or code-interpreter-style tools, with different built-in tools tied to different interfaces. The snapshot notice says it retains the tool ecosystem; it does not establish every tool’s availability through every application method. State the allowed tools and the final artifact explicitly. A prompt that requests a JSON result or an executed action should not be confused with an enforced schema or a real execution result.
Refined visual understanding
This edition improves chart reasoning, document parsing and multimodal perception. The Max family’s documented inputs are text, images and video, with text output. For a chart, retain labels, units and the relevant series, then ask which values support the conclusion. For a document, keep page and section identifiers and request a report linked to those identifiers. For a technical diagram, supply definitions alongside the image so the explanation can distinguish visible structure from unstated assumptions.
A visually grounded answer can connect a document passage, a figure and a user instruction. The output remains textual analysis or a draft code/document artifact; visual understanding does not imply image or video generation. Check small labels, table values and inferred relationships against the supplied source.
Context and thinking
The exact notice says the snapshot retains a one-million-token context and thinking mode. The managed Max family supports both thinking and direct responses, while reasoning depth and preservation controls are described in family documentation. The exact snapshot’s exposed control contract should follow its own interface rather than be copied from the text-only open Qwen3.8-2.4T-A95B checkpoint.
The maker’s managed Max reference uses rounded figures: maximum input 991K in direct mode or 983K in thinking mode, maximum output 131K, and maximum reasoning 262K. These are family reference values, not independently stated snapshot-specific hard ceilings. Input, history, represented visual material, reasoning and the final answer still need to fit the applicable configured limits.
Practical result and limits
Ask for a deliverable that can be reviewed: a patch with affected files, a chart explanation with supporting values, or a document comparison with cited sections. A long context can hold more evidence together, but it does not guarantee perfect recall or correctness. The exact update notice gives meaningful changes and retained features without publishing separate hard media limits or an independent output table for 0902. Preserve that boundary instead of treating the snapshot name as a performance or deployment guarantee.
", "aboutText": "The fixed 0902 snapshot\n\nQwen3.8-Max-0902 is the September 2, 2026 snapshot of Qwen3.8-Max. The maker’s update notice identifies it as a specific upgrade of Max, with deeper coding capabilities, stronger agent collaboration and refined visual understanding. The release also documents the name qwen3.8-max-2026-09-02 for this snapshot. Preserve the requested dated identity when the work requires a fixed edition; a moving Max name does not itself remain a permanent record of that version.\n\nCoding depth and sustained development\n\nThe manufacturer describes support for more complex engineering-scale projects and development tasks that continue over many steps. Prepare a repository question with the relevant modules, requirements, constraints and expected result. Ask the model to explain the affected components, propose an implementation sequence and return the required patch or code artifact. A useful completion report should distinguish the changes proposed from the checks actually performed by the connected workflow.\n\nFor a larger task, define intermediate evidence: the behavior that should change, the inputs exposing the current problem and the result expected after each step. Feed observed errors or review findings back into the next turn.\n\nAgent collaboration and tools\n\nThe notice highlights improved coordination with several tools and more stable task delivery. Qwen’s Max family documentation describes autonomous planning and closed feedback loops. An application can provide tools for retrieval, inspection or permitted execution and return their results to the model. The model can then revise a plan in response to what happened rather than treat the initial proposal as completed work.\n\nThe managed Max reference lists function calling, structured outputs and retrieval or code-interpreter-style tools, with different built-in tools tied to different interfaces. The snapshot notice says it retains the tool ecosystem; it does not establish every tool’s availability through every application method. State the allowed tools and the final artifact explicitly. A prompt that requests a JSON result or an executed action should not be confused with an enforced schema or a real execution result.\n\nRefined visual understanding\n\nThis edition improves chart reasoning, document parsing and multimodal perception. The Max family’s documented inputs are text, images and video, with text output. For a chart, retain labels, units and the relevant series, then ask which values support the conclusion. For a document, keep page and section identifiers and request a report linked to those identifiers. For a technical diagram, supply definitions alongside the image so the explanation can distinguish visible structure from unstated assumptions.\n\nA visually grounded answer can connect a document passage, a figure and a user instruction. The output remains textual analysis or a draft code/document artifact; visual understanding does not imply image or video generation. Check small labels, table values and inferred relationships against the supplied source.\n\nContext and thinking\n\nThe exact notice says the snapshot retains a one-million-token context and thinking mode. The managed Max family supports both thinking and direct responses, while reasoning depth and preservation controls are described in family documentation. The exact snapshot’s exposed control contract should follow its own interface rather than be copied from the text-only open Qwen3.8-2.4T-A95B checkpoint.\n\nThe maker’s managed Max reference uses rounded figures: maximum input 991K in direct mode or 983K in thinking mode, maximum output 131K, and maximum reasoning 262K. These are family reference values, not independently stated snapshot-specific hard ceilings. Input, history, represented visual material, reasoning and the final answer still need to fit the applicable configured limits.\n\nPractical result and limits\n\nAsk for a deliverable that can be reviewed: a patch with affected files, a chart explanation with supporting values, or a document comparison with cited sections. A long context can hold more evidence together, but it does not guarantee perfect recall or correctness. The exact update notice gives meaningful changes and retained features without publishing separate hard media limits or an independent output table for 0902. Preserve that boundary instead of treating the snapshot name as a performance or deployment guarantee.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Align a producer and a reader\n\nIn producer.py, records are emitted as {'status': 'ready', 'count': n}. In reader.py, code reads record['total']. The intended public record uses count; changing that contract is forbidden. Explain the failure, propose the smallest reader correction and provide a regression example for n=4. Return proposed code separately from the explanation.A source-linked defect explanation, a focused reader change and a regression example.The proposal must preserve the producer record contract and read count rather than introduce total.qwen/qwen3.8-max-0902Qwen3.8-Max-0902 is the September 2 snapshot of Qwen3.8 Max for engineering-scale coding, sustained development and visual analysis. The maker highlights stronger multi-tool collaboration, chart reasoning and document parsing, retaining a one-million-token context.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
The fixed 0902 snapshot
Qwen3.8-Max-0902 is the September 2, 2026 snapshot of Qwen3.8-Max. The maker’s update notice identifies it as a specific upgrade of Max, with deeper coding capabilities, stronger agent collaboration and refined visual understanding. The release also documents the name qwen3.8-max-2026-09-02 for this snapshot. Preserve the requested dated identity when the work requires a fixed edition; a moving Max name does not itself remain a permanent record of that version.
Coding depth and sustained development
The manufacturer describes support for more complex engineering-scale projects and development tasks that continue over many steps. Prepare a repository question with the relevant modules, requirements, constraints and expected result. Ask the model to explain the affected components, propose an implementation sequence and return the required patch or code artifact. A useful completion report should distinguish the changes proposed from the checks actually performed by the connected workflow.
For a larger task, define intermediate evidence: the behavior that should change, the inputs exposing the current problem and the result expected after each step. Feed observed errors or review findings back into the next turn.
Agent collaboration and tools
The notice highlights improved coordination with several tools and more stable task delivery. Qwen’s Max family documentation describes autonomous planning and closed feedback loops. An application can provide tools for retrieval, inspection or permitted execution and return their results to the model. The model can then revise a plan in response to what happened rather than treat the initial proposal as completed work.
The managed Max reference lists function calling, structured outputs and retrieval or code-interpreter-style tools, with different built-in tools tied to different interfaces. The snapshot notice says it retains the tool ecosystem; it does not establish every tool’s availability through every application method. State the allowed tools and the final artifact explicitly. A prompt that requests a JSON result or an executed action should not be confused with an enforced schema or a real execution result.
Refined visual understanding
This edition improves chart reasoning, document parsing and multimodal perception. The Max family’s documented inputs are text, images and video, with text output. For a chart, retain labels, units and the relevant series, then ask which values support the conclusion. For a document, keep page and section identifiers and request a report linked to those identifiers. For a technical diagram, supply definitions alongside the image so the explanation can distinguish visible structure from unstated assumptions.
A visually grounded answer can connect a document passage, a figure and a user instruction. The output remains textual analysis or a draft code/document artifact; visual understanding does not imply image or video generation. Check small labels, table values and inferred relationships against the supplied source.
Context and thinking
The exact notice says the snapshot retains a one-million-token context and thinking mode. The managed Max family supports both thinking and direct responses, while reasoning depth and preservation controls are described in family documentation. The exact snapshot’s exposed control contract should follow its own interface rather than be copied from the text-only open Qwen3.8-2.4T-A95B checkpoint.
The maker’s managed Max reference uses rounded figures: maximum input 991K in direct mode or 983K in thinking mode, maximum output 131K, and maximum reasoning 262K. These are family reference values, not independently stated snapshot-specific hard ceilings. Input, history, represented visual material, reasoning and the final answer still need to fit the applicable configured limits.
Practical result and limits
Ask for a deliverable that can be reviewed: a patch with affected files, a chart explanation with supporting values, or a document comparison with cited sections. A long context can hold more evidence together, but it does not guarantee perfect recall or correctness. The exact update notice gives meaningful changes and retained features without publishing separate hard media limits or an independent output table for 0902. Preserve that boundary instead of treating the snapshot name as a performance or deployment guarantee.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qwen/qwen3.8-max-0902 | 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 $0.004 / 1K tokens Output · Output tokens $0.012 / 1K tokens Input · Cache read $0.0005 / 1K tokens Input · Cache write $0.005 / 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 $0.004 / 1K tokens Output · Output tokens $0.012 / 1K tokens Input · Cache read $0.0005 / 1K tokens Input · Cache write $0.005 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${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-0902", "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-0902',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-0902',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-0902
Use the method paths shown above.
qwen/qwen3.8-max-0902Qwen3.8-Max-0902 is the September 2 snapshot of Qwen3.8 Max for engineering-scale coding, sustained development and visual analysis. The maker highlights stronger multi-tool collaboration, chart reasoning and document parsing, retaining a one-million-token context.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
The fixed 0902 snapshot
Qwen3.8-Max-0902 is the September 2, 2026 snapshot of Qwen3.8-Max. The maker’s update notice identifies it as a specific upgrade of Max, with deeper coding capabilities, stronger agent collaboration and refined visual understanding. The release also documents the name qwen3.8-max-2026-09-02 for this snapshot. Preserve the requested dated identity when the work requires a fixed edition; a moving Max name does not itself remain a permanent record of that version.
Coding depth and sustained development
The manufacturer describes support for more complex engineering-scale projects and development tasks that continue over many steps. Prepare a repository question with the relevant modules, requirements, constraints and expected result. Ask the model to explain the affected components, propose an implementation sequence and return the required patch or code artifact. A useful completion report should distinguish the changes proposed from the checks actually performed by the connected workflow.
For a larger task, define intermediate evidence: the behavior that should change, the inputs exposing the current problem and the result expected after each step. Feed observed errors or review findings back into the next turn.
Agent collaboration and tools
The notice highlights improved coordination with several tools and more stable task delivery. Qwen’s Max family documentation describes autonomous planning and closed feedback loops. An application can provide tools for retrieval, inspection or permitted execution and return their results to the model. The model can then revise a plan in response to what happened rather than treat the initial proposal as completed work.
The managed Max reference lists function calling, structured outputs and retrieval or code-interpreter-style tools, with different built-in tools tied to different interfaces. The snapshot notice says it retains the tool ecosystem; it does not establish every tool’s availability through every application method. State the allowed tools and the final artifact explicitly. A prompt that requests a JSON result or an executed action should not be confused with an enforced schema or a real execution result.
Refined visual understanding
This edition improves chart reasoning, document parsing and multimodal perception. The Max family’s documented inputs are text, images and video, with text output. For a chart, retain labels, units and the relevant series, then ask which values support the conclusion. For a document, keep page and section identifiers and request a report linked to those identifiers. For a technical diagram, supply definitions alongside the image so the explanation can distinguish visible structure from unstated assumptions.
A visually grounded answer can connect a document passage, a figure and a user instruction. The output remains textual analysis or a draft code/document artifact; visual understanding does not imply image or video generation. Check small labels, table values and inferred relationships against the supplied source.
Context and thinking
The exact notice says the snapshot retains a one-million-token context and thinking mode. The managed Max family supports both thinking and direct responses, while reasoning depth and preservation controls are described in family documentation. The exact snapshot’s exposed control contract should follow its own interface rather than be copied from the text-only open Qwen3.8-2.4T-A95B checkpoint.
The maker’s managed Max reference uses rounded figures: maximum input 991K in direct mode or 983K in thinking mode, maximum output 131K, and maximum reasoning 262K. These are family reference values, not independently stated snapshot-specific hard ceilings. Input, history, represented visual material, reasoning and the final answer still need to fit the applicable configured limits.
Practical result and limits
Ask for a deliverable that can be reviewed: a patch with affected files, a chart explanation with supporting values, or a document comparison with cited sections. A long context can hold more evidence together, but it does not guarantee perfect recall or correctness. The exact update notice gives meaningful changes and retained features without publishing separate hard media limits or an independent output table for 0902. Preserve that boundary instead of treating the snapshot name as a performance or deployment guarantee.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qwen/qwen3.8-max-0902 | 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 $0.004 / 1K tokens Output · Output tokens $0.012 / 1K tokens Input · Cache read $0.0005 / 1K tokens Input · Cache write $0.005 / 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 $0.004 / 1K tokens Output · Output tokens $0.012 / 1K tokens Input · Cache read $0.0005 / 1K tokens Input · Cache write $0.005 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "qwen/qwen3.8-max-0902",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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-0902', '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-0902', '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-0902
Use the method paths shown above.
Technical example in English
Align a producer and a reader\n\nIn producer.py, records are emitted as {'status': 'ready', 'count': n}. In reader.py, code reads record['total']. The intended public record uses count; changing that contract is forbidden. Explain the failure, propose the smallest reader correction and provide a regression example for n=4. Return proposed code separately from the explanation.A source-linked defect explanation, a focused reader change and a regression example.The proposal must preserve the producer record contract and read count rather than introduce total.