ERNIE 4.5 300B-A47B is Baidu’s large text model in the ERNIE 4.5 family. Its mixture-of-experts design contains 300 billion parameters in total and activates 47 billion for each token. The published model configuration gives a context length of 131,072 tokens. It takes text and generates text, supporting a conversation, an explanation or a new document based on the question and material provided.
ERNIE 4.5 highlights. Baidu describes joint training of language and visual information across the family, with routing that lets different modalities share some parameters while retaining dedicated processing. The text variant focuses on general language understanding and generation. The family’s development also includes infrastructure for efficient training and inference and post-training with supervised examples and preference-based optimisation. These design choices explain the model’s background; they do not turn a text request into image input.
Model configuration. The published text model has 54 layers, 64 query attention heads and 8 key/value heads. Its text expert configuration lists 64 experts, with 8 activated at a time. For practical input preparation, use the context to preserve the passages required by the task, along with their headings and relationships. The conversation and generated answer share the available context budget, so select relevant material and specify the length of the result rather than treating the entire window as answer space.
A request begins with a question or instruction. For document analysis, supply labelled sections and ask for a conclusion with the section supporting each point. For drafting, provide the audience, the source facts and the required structure. You might ask for a service explanation, a requirements summary or a comparison of two internal procedures. Include the rules that govern ambiguous cases, and ask for a missing-information note when the source does not justify a definite answer.
Grounded reference answering. The manufacturer publishes Chinese and English prompting examples for a workflow that supplies the current time, reference articles and a question. The model is instructed to judge whether the references are relevant and current, favour authoritative material and state when the evidence is insufficient. To apply that pattern, label each supplied reference, retain its publication time where available and separate reference content from the question. The expected result is an answer based on those passages, not an assumption that a retrieval step has already happened.
Generation guidance. Baidu’s card recommends temperature 0.8 and top-p 0.8 for its published model examples. Treat these as manufacturer guidance when configuring a compatible generation setup, then evaluate the output against the task’s requirements. The model’s PT and Paddle releases denote different weight formats; the named text edition remains distinct from the VL vision-language model and from a Base training checkpoint. A practical review should check important factual statements, numerical details and the completeness of the requested sections against the supplied material.
", "aboutText": "ERNIE 4.5 300B-A47B is Baidu’s large text model in the ERNIE 4.5 family. Its mixture-of-experts design contains 300 billion parameters in total and activates 47 billion for each token. The published model configuration gives a context length of 131,072 tokens. It takes text and generates text, supporting a conversation, an explanation or a new document based on the question and material provided.\n\nERNIE 4.5 highlights. Baidu describes joint training of language and visual information across the family, with routing that lets different modalities share some parameters while retaining dedicated processing. The text variant focuses on general language understanding and generation. The family’s development also includes infrastructure for efficient training and inference and post-training with supervised examples and preference-based optimisation. These design choices explain the model’s background; they do not turn a text request into image input.\n\nModel configuration. The published text model has 54 layers, 64 query attention heads and 8 key/value heads. Its text expert configuration lists 64 experts, with 8 activated at a time. For practical input preparation, use the context to preserve the passages required by the task, along with their headings and relationships. The conversation and generated answer share the available context budget, so select relevant material and specify the length of the result rather than treating the entire window as answer space.\n\nA request begins with a question or instruction. For document analysis, supply labelled sections and ask for a conclusion with the section supporting each point. For drafting, provide the audience, the source facts and the required structure. You might ask for a service explanation, a requirements summary or a comparison of two internal procedures. Include the rules that govern ambiguous cases, and ask for a missing-information note when the source does not justify a definite answer.\n\nGrounded reference answering. The manufacturer publishes Chinese and English prompting examples for a workflow that supplies the current time, reference articles and a question. The model is instructed to judge whether the references are relevant and current, favour authoritative material and state when the evidence is insufficient. To apply that pattern, label each supplied reference, retain its publication time where available and separate reference content from the question. The expected result is an answer based on those passages, not an assumption that a retrieval step has already happened.\n\nGeneration guidance. Baidu’s card recommends temperature 0.8 and top-p 0.8 for its published model examples. Treat these as manufacturer guidance when configuring a compatible generation setup, then evaluate the output against the task’s requirements. The model’s PT and Paddle releases denote different weight formats; the named text edition remains distinct from the VL vision-language model and from a Base training checkpoint. A practical review should check important factual statements, numerical details and the completeness of the requested sections against the supplied material.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Resolve conflicting reference passages\n\nAnswer the question using these references only. R1, old handbook: Trial accounts retain exports for 7 days. R2, current handbook: Trial exports are retained for 14 days; paid-account exports for 90 days. Question: How long can a trial customer retrieve an export? Cite the relevant reference and explain why the other passage differs.A short answer with the retention period, reference identifier and a sentence describing the documented version conflict.Check that the answer uses the current trial rule and does not substitute the paid-account period.baidu/ERNIE-4.5-300B-A47BERNIE 4.5 300B-A47B is Baidu’s text mixture-of-experts model with 300 billion total parameters, 47 billion active parameters per token and a published 131,072-token context. It supports language understanding and generation, including answers grounded in reference passages you supply.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
ERNIE 4.5 300B-A47B is Baidu’s large text model in the ERNIE 4.5 family. Its mixture-of-experts design contains 300 billion parameters in total and activates 47 billion for each token. The published model configuration gives a context length of 131,072 tokens. It takes text and generates text, supporting a conversation, an explanation or a new document based on the question and material provided.
ERNIE 4.5 highlights. Baidu describes joint training of language and visual information across the family, with routing that lets different modalities share some parameters while retaining dedicated processing. The text variant focuses on general language understanding and generation. The family’s development also includes infrastructure for efficient training and inference and post-training with supervised examples and preference-based optimisation. These design choices explain the model’s background; they do not turn a text request into image input.
Model configuration. The published text model has 54 layers, 64 query attention heads and 8 key/value heads. Its text expert configuration lists 64 experts, with 8 activated at a time. For practical input preparation, use the context to preserve the passages required by the task, along with their headings and relationships. The conversation and generated answer share the available context budget, so select relevant material and specify the length of the result rather than treating the entire window as answer space.
A request begins with a question or instruction. For document analysis, supply labelled sections and ask for a conclusion with the section supporting each point. For drafting, provide the audience, the source facts and the required structure. You might ask for a service explanation, a requirements summary or a comparison of two internal procedures. Include the rules that govern ambiguous cases, and ask for a missing-information note when the source does not justify a definite answer.
Grounded reference answering. The manufacturer publishes Chinese and English prompting examples for a workflow that supplies the current time, reference articles and a question. The model is instructed to judge whether the references are relevant and current, favour authoritative material and state when the evidence is insufficient. To apply that pattern, label each supplied reference, retain its publication time where available and separate reference content from the question. The expected result is an answer based on those passages, not an assumption that a retrieval step has already happened.
Generation guidance. Baidu’s card recommends temperature 0.8 and top-p 0.8 for its published model examples. Treat these as manufacturer guidance when configuring a compatible generation setup, then evaluate the output against the task’s requirements. The model’s PT and Paddle releases denote different weight formats; the named text edition remains distinct from the VL vision-language model and from a Base training checkpoint. A practical review should check important factual statements, numerical details and the completeness of the requested sections against the supplied material.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits baidu/ERNIE-4.5-300B-A47B | 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 $0.0006 / 1K tokens Output · Output tokens $0.00228 / 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": "baidu/ERNIE-4.5-300B-A47B", "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='baidu/ERNIE-4.5-300B-A47B',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='baidu/ERNIE-4.5-300B-A47B',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 baidu/ERNIE-4.5-300B-A47B
Use the method paths shown above.
baidu/ERNIE-4.5-300B-A47BERNIE 4.5 300B-A47B is Baidu’s text mixture-of-experts model with 300 billion total parameters, 47 billion active parameters per token and a published 131,072-token context. It supports language understanding and generation, including answers grounded in reference passages you supply.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
ERNIE 4.5 300B-A47B is Baidu’s large text model in the ERNIE 4.5 family. Its mixture-of-experts design contains 300 billion parameters in total and activates 47 billion for each token. The published model configuration gives a context length of 131,072 tokens. It takes text and generates text, supporting a conversation, an explanation or a new document based on the question and material provided.
ERNIE 4.5 highlights. Baidu describes joint training of language and visual information across the family, with routing that lets different modalities share some parameters while retaining dedicated processing. The text variant focuses on general language understanding and generation. The family’s development also includes infrastructure for efficient training and inference and post-training with supervised examples and preference-based optimisation. These design choices explain the model’s background; they do not turn a text request into image input.
Model configuration. The published text model has 54 layers, 64 query attention heads and 8 key/value heads. Its text expert configuration lists 64 experts, with 8 activated at a time. For practical input preparation, use the context to preserve the passages required by the task, along with their headings and relationships. The conversation and generated answer share the available context budget, so select relevant material and specify the length of the result rather than treating the entire window as answer space.
A request begins with a question or instruction. For document analysis, supply labelled sections and ask for a conclusion with the section supporting each point. For drafting, provide the audience, the source facts and the required structure. You might ask for a service explanation, a requirements summary or a comparison of two internal procedures. Include the rules that govern ambiguous cases, and ask for a missing-information note when the source does not justify a definite answer.
Grounded reference answering. The manufacturer publishes Chinese and English prompting examples for a workflow that supplies the current time, reference articles and a question. The model is instructed to judge whether the references are relevant and current, favour authoritative material and state when the evidence is insufficient. To apply that pattern, label each supplied reference, retain its publication time where available and separate reference content from the question. The expected result is an answer based on those passages, not an assumption that a retrieval step has already happened.
Generation guidance. Baidu’s card recommends temperature 0.8 and top-p 0.8 for its published model examples. Treat these as manufacturer guidance when configuring a compatible generation setup, then evaluate the output against the task’s requirements. The model’s PT and Paddle releases denote different weight formats; the named text edition remains distinct from the VL vision-language model and from a Base training checkpoint. A practical review should check important factual statements, numerical details and the completeness of the requested sections against the supplied material.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits baidu/ERNIE-4.5-300B-A47B | 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 $0.0006 / 1K tokens Output · Output tokens $0.00228 / 1K tokens Input · Cache read $0 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "baidu/ERNIE-4.5-300B-A47B",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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': 'baidu/ERNIE-4.5-300B-A47B', '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': 'baidu/ERNIE-4.5-300B-A47B', '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 baidu/ERNIE-4.5-300B-A47B
Use the method paths shown above.
Technical example in English
Resolve conflicting reference passages\n\nAnswer the question using these references only. R1, old handbook: Trial accounts retain exports for 7 days. R2, current handbook: Trial exports are retained for 14 days; paid-account exports for 90 days. Question: How long can a trial customer retrieve an export? Cite the relevant reference and explain why the other passage differs.A short answer with the retention period, reference identifier and a sentence describing the documented version conflict.Check that the answer uses the current trial rule and does not substitute the paid-account period.