Baichuan4 is the named fourth-generation general-conversation model in Baichuan’s lineup. The manufacturer documents a 32K context for this exact edition. Baichuan4-Turbo and Baichuan4-Air are separate editions with their own model profiles.
The model works with a text conversation and produces an assistant response or a function-call request in the maker’s documented workflow. Useful tasks include answering from supplied information, organizing a document’s contents, revising text and producing a structured record for an application.
Prepare messages in chronological order, with a system instruction first when one is needed. Keep the user’s task distinct from earlier assistant answers and external tool results. The producer reference accepts ordinary text strings or typed text-content structures, and uses a separate tool-message role for results of function calls.
For a comparison, supply both passages, label them clearly and ask for agreements, conflicts and supporting wording. For a revised explanation, specify the audience and the details that must survive the rewrite. A useful instruction is: “Compare these two project descriptions, list the changed requirements, and identify the passage that establishes each change.”
Baichuan4 is explicitly included in the producer’s JSON-object mode. Enabling that mode also requires a system or user instruction to produce JSON. Define the required fields and how missing information should appear. Parse and inspect the result before using it as an application record.
The producer’s conversation operation accepts max_tokens from 1 to 2,048, default 2,048. Its sampling settings are temperature from 0 to 1, default 0.3; top_p from 0 up to but excluding 1, default 0.85; and top_k from 0 to 20, default 5. Setting top_k to 0 turns off that strategy. The response allowance is different from the 32K context: prepare source material and room for the answer together.
If the completion reason is length, a written answer or JSON object may be incomplete. Preserve the partial result and the reason it stopped, then decide whether to shorten the requested artifact, reduce the input or revise the applicable response allowance.
The maker’s tools distinguish knowledge-base retrieval from web search. A knowledge-base request names the relevant collections. Its knowledge-base-only answer mode prevents an answer when retrieval finds no result. If web search and knowledge retrieval are both configured, the reference specifies that retrieval takes precedence.
For a changing fact, retain the actual retrieved or searched information so the final answer can be checked against it. Keep the source, date and relevant qualification with the observation. When the task concerns a supplied collection, ask a focused question instead of combining the retrieval question with unrelated creative instructions.
Baichuan4’s documented examples show selection among custom functions and continuation after the application returns a function’s result. Define each function with a name, purpose and argument schema. Preserve the assistant’s call and the matching tool result, then ask the next response to explain or use that observation.
A practical comparison can request two actual readings, such as values for two different dates, and ask for the difference between them. The application provides those readings; the model’s selected function and generated arguments are a request for that operation. The producer’s automatic or no-tool selection setting applies to functions. The reference advises keeping function calls separate from web-search or retrieval configurations.
Non-streaming is the default producer mode; streaming returns incremental response pieces that must be assembled. The completion reason distinguishes a normal stop, a tool request, an output or context-length limit and content filtering. Keep the finished message or object with the source material and tool observations needed to interpret it.
Review the result for the requested fields, supported comparisons and wording appropriate to its destination. Keep the exact Baichuan4 identity with the task when comparing another edition. The useful outcome is a completed text artifact or an explanation of an actual tool observation, with any unresolved part of the request still identifiable.
", "aboutText": "### Baichuan4 as a distinct conversation edition\n\nBaichuan4 is the named fourth-generation general-conversation model in Baichuan’s lineup. The manufacturer documents a 32K context for this exact edition. Baichuan4-Turbo and Baichuan4-Air are separate editions with their own model profiles.\n\nThe model works with a text conversation and produces an assistant response or a function-call request in the maker’s documented workflow. Useful tasks include answering from supplied information, organizing a document’s contents, revising text and producing a structured record for an application.\n\n### Supply a complete dialogue request\n\nPrepare messages in chronological order, with a system instruction first when one is needed. Keep the user’s task distinct from earlier assistant answers and external tool results. The producer reference accepts ordinary text strings or typed text-content structures, and uses a separate tool-message role for results of function calls.\n\nFor a comparison, supply both passages, label them clearly and ask for agreements, conflicts and supporting wording. For a revised explanation, specify the audience and the details that must survive the rewrite. A useful instruction is: “Compare these two project descriptions, list the changed requirements, and identify the passage that establishes each change.”\n\n### Choose output form and response allowance\n\nBaichuan4 is explicitly included in the producer’s JSON-object mode. Enabling that mode also requires a system or user instruction to produce JSON. Define the required fields and how missing information should appear. Parse and inspect the result before using it as an application record.\n\nThe producer’s conversation operation accepts max_tokens from 1 to 2,048, default 2,048. Its sampling settings are temperature from 0 to 1, default 0.3; top_p from 0 up to but excluding 1, default 0.85; and top_k from 0 to 20, default 5. Setting top_k to 0 turns off that strategy. The response allowance is different from the 32K context: prepare source material and room for the answer together.\n\nIf the completion reason is length, a written answer or JSON object may be incomplete. Preserve the partial result and the reason it stopped, then decide whether to shorten the requested artifact, reduce the input or revise the applicable response allowance.\n\n### Ground an answer in retrieved information\n\nThe maker’s tools distinguish knowledge-base retrieval from web search. A knowledge-base request names the relevant collections. Its knowledge-base-only answer mode prevents an answer when retrieval finds no result. If web search and knowledge retrieval are both configured, the reference specifies that retrieval takes precedence.\n\nFor a changing fact, retain the actual retrieved or searched information so the final answer can be checked against it. Keep the source, date and relevant qualification with the observation. When the task concerns a supplied collection, ask a focused question instead of combining the retrieval question with unrelated creative instructions.\n\n### Continue from a real function result\n\nBaichuan4’s documented examples show selection among custom functions and continuation after the application returns a function’s result. Define each function with a name, purpose and argument schema. Preserve the assistant’s call and the matching tool result, then ask the next response to explain or use that observation.\n\nA practical comparison can request two actual readings, such as values for two different dates, and ask for the difference between them. The application provides those readings; the model’s selected function and generated arguments are a request for that operation. The producer’s automatic or no-tool selection setting applies to functions. The reference advises keeping function calls separate from web-search or retrieval configurations.\n\n### Collect and inspect the final artifact\n\nNon-streaming is the default producer mode; streaming returns incremental response pieces that must be assembled. The completion reason distinguishes a normal stop, a tool request, an output or context-length limit and content filtering. Keep the finished message or object with the source material and tool observations needed to interpret it.\n\nReview the result for the requested fields, supported comparisons and wording appropriate to its destination. Keep the exact Baichuan4 identity with the task when comparing another edition. The useful outcome is a completed text artifact or an explanation of an actual tool observation, with any unresolved part of the request still identifiable.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
A requirements change record\n\nCompare these project notes. Version A: customers receive receipts by email; export contains all orders; support replies within two working days. Version B: receipts appear in the account; export includes paid orders only; support target remains two working days. List changes and unchanged requirements, quoting the wording that supports each finding.A comparison table containing requirement, previous wording, revised wording and change status.The support target is recorded as unchanged, and the export filter change is distinguished from receipt delivery.Baichuan4Baichuan4 is the named fourth-generation text-conversation model with a documented 32K context. Its producer workflow supports JSON-object answers, completed or streamed text, custom functions and evidence from knowledge-base retrieval or web search.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Baichuan4 is the named fourth-generation general-conversation model in Baichuan’s lineup. The manufacturer documents a 32K context for this exact edition. Baichuan4-Turbo and Baichuan4-Air are separate editions with their own model profiles.
The model works with a text conversation and produces an assistant response or a function-call request in the maker’s documented workflow. Useful tasks include answering from supplied information, organizing a document’s contents, revising text and producing a structured record for an application.
Prepare messages in chronological order, with a system instruction first when one is needed. Keep the user’s task distinct from earlier assistant answers and external tool results. The producer reference accepts ordinary text strings or typed text-content structures, and uses a separate tool-message role for results of function calls.
For a comparison, supply both passages, label them clearly and ask for agreements, conflicts and supporting wording. For a revised explanation, specify the audience and the details that must survive the rewrite. A useful instruction is: “Compare these two project descriptions, list the changed requirements, and identify the passage that establishes each change.”
Baichuan4 is explicitly included in the producer’s JSON-object mode. Enabling that mode also requires a system or user instruction to produce JSON. Define the required fields and how missing information should appear. Parse and inspect the result before using it as an application record.
The producer’s conversation operation accepts max_tokens from 1 to 2,048, default 2,048. Its sampling settings are temperature from 0 to 1, default 0.3; top_p from 0 up to but excluding 1, default 0.85; and top_k from 0 to 20, default 5. Setting top_k to 0 turns off that strategy. The response allowance is different from the 32K context: prepare source material and room for the answer together.
If the completion reason is length, a written answer or JSON object may be incomplete. Preserve the partial result and the reason it stopped, then decide whether to shorten the requested artifact, reduce the input or revise the applicable response allowance.
The maker’s tools distinguish knowledge-base retrieval from web search. A knowledge-base request names the relevant collections. Its knowledge-base-only answer mode prevents an answer when retrieval finds no result. If web search and knowledge retrieval are both configured, the reference specifies that retrieval takes precedence.
For a changing fact, retain the actual retrieved or searched information so the final answer can be checked against it. Keep the source, date and relevant qualification with the observation. When the task concerns a supplied collection, ask a focused question instead of combining the retrieval question with unrelated creative instructions.
Baichuan4’s documented examples show selection among custom functions and continuation after the application returns a function’s result. Define each function with a name, purpose and argument schema. Preserve the assistant’s call and the matching tool result, then ask the next response to explain or use that observation.
A practical comparison can request two actual readings, such as values for two different dates, and ask for the difference between them. The application provides those readings; the model’s selected function and generated arguments are a request for that operation. The producer’s automatic or no-tool selection setting applies to functions. The reference advises keeping function calls separate from web-search or retrieval configurations.
Non-streaming is the default producer mode; streaming returns incremental response pieces that must be assembled. The completion reason distinguishes a normal stop, a tool request, an output or context-length limit and content filtering. Keep the finished message or object with the source material and tool observations needed to interpret it.
Review the result for the requested fields, supported comparisons and wording appropriate to its destination. Keep the exact Baichuan4 identity with the task when comparing another edition. The useful outcome is a completed text artifact or an explanation of an actual tool observation, with any unresolved part of the request still identifiable.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits Baichuan4 | Default— |
Fieldmessages | Typemessage[] | RequirementRequired | Values & limits Minimum items: 1 | Default— |
Fieldmessages[].role | Typestring | RequirementRequired | Values & limits Examples: system, user, assistant, tool, function Conditions: These roles are explicitly represented by Source compatibility types; the exact model role set remains model-specific. Model-specific | Default— |
Fieldmessages[].content | Typestring|content_part[]|null | RequirementOptional | Values & limits | Default— |
Fieldmessages[].tool_calls | Typetool_call[] | RequirementOptional | Values & limits | Default— |
Fieldmessages[].tool_call_id | Typestring | RequirementOptional | Values & limits Applies when: role=tool; use actual returned ID | Default— |
Fieldmessages[].name | Typestring | RequirementOptional | Values & limits | Default— |
Fieldmessages[].reasoning_content | Typestring | RequirementOptional | Values & limits Applies when: Round-trip actual returned reasoning where this model uses it | Default— |
Fieldmessages[].reasoning_details | Typeobject|array | RequirementOptional | Values & limits Model-specific | Default— |
Fieldmax_tokens | Typeinteger | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
Fieldmax_completion_tokens | Typeinteger | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
Fieldstream_options.include_usage | Typeboolean | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtemperature | Typenumber | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtop_p | Typenumber | RequirementOptional | Values & limits Model-specific | Default— |
Fieldstop | Typestring|string[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtools | Typefunction_tool[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtools[].type | Typestring | RequirementOptional | Values & limits function Model-specific | Default— |
Fieldtools[].function.name | Typestring | RequirementRequired | Values & limits Applies when: function tool supplied | Default— |
Fieldtools[].function.description | Typestring | RequirementOptional | Values & limits | Default— |
Fieldtools[].function.parameters | TypeJSON_schema | RequirementOptional | Values & limits | Default— |
Fieldtool_choice | Typestring|object | RequirementOptional | Values & limits Model-specific | Default— |
Fieldparallel_tool_calls | Typeboolean | RequirementOptional | Values & limits Model-specific | Default— |
Fieldresponse_format | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Fieldreasoning_effort | Typestring | RequirementOptional | Values & limits Model-specific | Default— |
Fieldreasoning | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Fieldservice_tier | Typestring | RequirementOptional | Values & limits Model-specific | Default— |
Fieldinstructions | Typestring | RequirementOptional | Values & limits Compatibility field | Default— |
Fieldfunctions | Typefunction[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldfunction_call | Typestring|object | RequirementOptional | Values & limits Model-specific | Default— |
Fieldprompt_cache_options | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Fieldmodalities | Typestring[] | RequirementOptional | Values & limits text | Default— |
Fieldprovider | Typeobject | RequirementOptional | Values & limits Conditions: provider.options is rejected on this Ultra text route | Default— |
Fieldcache_control.ttl | Typestring | RequirementOptional | Values & limits Conditions: 1h is rejected in actual prompt-cache locations | Default— |
Text · UTF8 text
messages[].content
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, messages |
Parametermaterial_types | Contracttext |
Parametermessages | Contractmessage array with role/content shape |
Parameterfile_material | Contractactual UTF-8 document inserted as literal text; no file ID inferred |
Parameteroptional_controls | Contractstream, temperature, top_p, stop, max_tokens, max_completion_tokens, reasoning, response_format, tools, tool_choice |
Parametercontrol_scope | Contractmodel-specific; user function tools differ from hosted tools |
Parameteroutput_modalities | Contracttext |
Parameterhosted_operations | Contractfalse |
Parametermultimodal_input_binding | Contractnull |
Lifecycle: synchronous_or_streamed
Send exact model ID with messages.
Context length is not an output cap.
A text file may supply literal text; image/audio/file-object inputs need exact binding.
Tariff references do not add request options. Supported parameters are listed for the selected method.
| Configuration | Rate schedule | Charge |
|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Charge Input · Input tokens $0.03146 / 1K tokens Output · Output tokens $0.03146 / 1K tokens Input · Cache read $0 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "Baichuan4", "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='Baichuan4',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='Baichuan4',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 Baichuan4
Use the method paths shown above.
Baichuan4Baichuan4 is the named fourth-generation text-conversation model with a documented 32K context. Its producer workflow supports JSON-object answers, completed or streamed text, custom functions and evidence from knowledge-base retrieval or web search.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Baichuan4 is the named fourth-generation general-conversation model in Baichuan’s lineup. The manufacturer documents a 32K context for this exact edition. Baichuan4-Turbo and Baichuan4-Air are separate editions with their own model profiles.
The model works with a text conversation and produces an assistant response or a function-call request in the maker’s documented workflow. Useful tasks include answering from supplied information, organizing a document’s contents, revising text and producing a structured record for an application.
Prepare messages in chronological order, with a system instruction first when one is needed. Keep the user’s task distinct from earlier assistant answers and external tool results. The producer reference accepts ordinary text strings or typed text-content structures, and uses a separate tool-message role for results of function calls.
For a comparison, supply both passages, label them clearly and ask for agreements, conflicts and supporting wording. For a revised explanation, specify the audience and the details that must survive the rewrite. A useful instruction is: “Compare these two project descriptions, list the changed requirements, and identify the passage that establishes each change.”
Baichuan4 is explicitly included in the producer’s JSON-object mode. Enabling that mode also requires a system or user instruction to produce JSON. Define the required fields and how missing information should appear. Parse and inspect the result before using it as an application record.
The producer’s conversation operation accepts max_tokens from 1 to 2,048, default 2,048. Its sampling settings are temperature from 0 to 1, default 0.3; top_p from 0 up to but excluding 1, default 0.85; and top_k from 0 to 20, default 5. Setting top_k to 0 turns off that strategy. The response allowance is different from the 32K context: prepare source material and room for the answer together.
If the completion reason is length, a written answer or JSON object may be incomplete. Preserve the partial result and the reason it stopped, then decide whether to shorten the requested artifact, reduce the input or revise the applicable response allowance.
The maker’s tools distinguish knowledge-base retrieval from web search. A knowledge-base request names the relevant collections. Its knowledge-base-only answer mode prevents an answer when retrieval finds no result. If web search and knowledge retrieval are both configured, the reference specifies that retrieval takes precedence.
For a changing fact, retain the actual retrieved or searched information so the final answer can be checked against it. Keep the source, date and relevant qualification with the observation. When the task concerns a supplied collection, ask a focused question instead of combining the retrieval question with unrelated creative instructions.
Baichuan4’s documented examples show selection among custom functions and continuation after the application returns a function’s result. Define each function with a name, purpose and argument schema. Preserve the assistant’s call and the matching tool result, then ask the next response to explain or use that observation.
A practical comparison can request two actual readings, such as values for two different dates, and ask for the difference between them. The application provides those readings; the model’s selected function and generated arguments are a request for that operation. The producer’s automatic or no-tool selection setting applies to functions. The reference advises keeping function calls separate from web-search or retrieval configurations.
Non-streaming is the default producer mode; streaming returns incremental response pieces that must be assembled. The completion reason distinguishes a normal stop, a tool request, an output or context-length limit and content filtering. Keep the finished message or object with the source material and tool observations needed to interpret it.
Review the result for the requested fields, supported comparisons and wording appropriate to its destination. Keep the exact Baichuan4 identity with the task when comparing another edition. The useful outcome is a completed text artifact or an explanation of an actual tool observation, with any unresolved part of the request still identifiable.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits Baichuan4 | Default— |
Fieldmessages | Typemessage[] | RequirementRequired | Values & limits | Default— |
Fieldmessages[].role | Typestring | RequirementRequired | Values & limits user, assistant | Default— |
Fieldmessages[].content | Typestring | RequirementRequired | Values & limits | Default— |
Fieldmax_tokens | Typeinteger | RequirementRequired | Values & limits | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
Text · UTF-8 text
messages[].content string
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, messages, max_tokens |
Parameteroptional_controls | Contractstream |
Parametermaterial_types | Contracttext |
Parametertext_file_material | ContractRead the actual UTF-8 document and put its text in the indicated input or message content string. |
Lifecycle: synchronous_or_streamed
Tariff references do not add request options. Supported parameters are listed for the selected method.
| Configuration | Rate schedule | Charge |
|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Charge Input · Input tokens $0.03146 / 1K tokens Output · Output tokens $0.03146 / 1K tokens Input · Cache read $0 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "Baichuan4",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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': 'Baichuan4', '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': 'Baichuan4', '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 Baichuan4
Use the method paths shown above.
Technical example in English
A requirements change record\n\nCompare these project notes. Version A: customers receive receipts by email; export contains all orders; support replies within two working days. Version B: receipts appear in the account; export includes paid orders only; support target remains two working days. List changes and unchanged requirements, quoting the wording that supports each finding.A comparison table containing requirement, previous wording, revised wording and change status.The support target is recorded as unchanged, and the export filter change is distinguished from receipt delivery.