ERNIE 5.0 Thinking is Baidu’s reasoning-oriented model family for complex questions, writing, instruction following and application-connected tasks. The maker’s named Thinking Preview profile combines deep reasoning with visual understanding and support for planning and tool use. Its producer text-response workflow is distinct from treating the entire ERNIE 5.0 research family’s multimodal generation capabilities as one interchangeable request contract.
State the question, the material that can be used and the conditions the answer must satisfy. A research comparison can define the criteria and request the evidence supporting each conclusion. A writing task can provide the audience, factual brief and desired structure. A coding question can identify the behavior to change and the relevant source fragment. Keep the final artifact specific enough to inspect.
For visual understanding, supply material that makes the relevant feature clear and state the question about it. A chart or document image needs readable labels and the surrounding context that establishes what its values mean. Check important text and numerical details against the original material. The model’s visual-understanding purpose does not remove the need to preserve the source with the returned interpretation.
Baidu’s AI Studio table lists the Thinking Preview profile with 128K context and a 119K maximum input. The Chinese table gives final-output settings up to 65,536 tokens and a 2K default, and separately lists a 60K thinking length. Keep these allowances in their roles: the task context, the generated reasoning and the requested final response are different parts of a useful result.
A large input allowance can hold related documents, while the requested answer should still match the decision or artifact needed. For a comparison, ask for a compact evidence table and the governing conclusion rather than repeating every supplied passage. For a technical answer, preserve the input case and expected behavior that make the result checkable. The named Preview specification should not be converted into a guarantee about a later updating selector’s underlying revision.
The manufacturer’s feature index lists the Thinking Preview profile for function calling, search enhancement and structured output. Define an application function and the arguments it needs, execute a returned request in the application and supply the actual result for continuation. An agent plan is not itself evidence that the planned operations finished.
A source-based answer should retain retrieved evidence and distinguish it from the supplied background or an inference. A structured record should define the required fields and how missing information is represented, with the returned values checked against the source. Native response-format and tool details belong to the selected producer interface; the basic practical requirement is a traceable text result rather than a plausible but unsupported completed field.
The useful artifact can be a reasoned comparison, a draft, a code-related explanation or a tool-informed answer. Review important identifiers, calculations and interpretations against the material that establishes them. Keep any incomplete lookup or contradictory source visible in the conclusion instead of using fluent wording to hide a gap.
The Thinking family, the named Preview profile and later ERNIE generations have distinct selectors and documented conditions. Preserve the task, source material, completed tool evidence and final response together. This makes the next turn a specific correction or extension of the same investigation rather than an ungrounded reconstruction of the earlier work.
", "aboutText": "ERNIE 5.0 Thinking is Baidu’s reasoning-oriented model family for complex questions, writing, instruction following and application-connected tasks. The maker’s named Thinking Preview profile combines deep reasoning with visual understanding and support for planning and tool use. Its producer text-response workflow is distinct from treating the entire ERNIE 5.0 research family’s multimodal generation capabilities as one interchangeable request contract.\n\n### Prepare evidence for the intended result\n\nState the question, the material that can be used and the conditions the answer must satisfy. A research comparison can define the criteria and request the evidence supporting each conclusion. A writing task can provide the audience, factual brief and desired structure. A coding question can identify the behavior to change and the relevant source fragment. Keep the final artifact specific enough to inspect.\n\nFor visual understanding, supply material that makes the relevant feature clear and state the question about it. A chart or document image needs readable labels and the surrounding context that establishes what its values mean. Check important text and numerical details against the original material. The model’s visual-understanding purpose does not remove the need to preserve the source with the returned interpretation.\n\n### The documented Preview budgets\n\nBaidu’s AI Studio table lists the Thinking Preview profile with 128K context and a 119K maximum input. The Chinese table gives final-output settings up to 65,536 tokens and a 2K default, and separately lists a 60K thinking length. Keep these allowances in their roles: the task context, the generated reasoning and the requested final response are different parts of a useful result.\n\nA large input allowance can hold related documents, while the requested answer should still match the decision or artifact needed. For a comparison, ask for a compact evidence table and the governing conclusion rather than repeating every supplied passage. For a technical answer, preserve the input case and expected behavior that make the result checkable. The named Preview specification should not be converted into a guarantee about a later updating selector’s underlying revision.\n\n### Tools, search and structured text\n\nThe manufacturer’s feature index lists the Thinking Preview profile for function calling, search enhancement and structured output. Define an application function and the arguments it needs, execute a returned request in the application and supply the actual result for continuation. An agent plan is not itself evidence that the planned operations finished.\n\nA source-based answer should retain retrieved evidence and distinguish it from the supplied background or an inference. A structured record should define the required fields and how missing information is represented, with the returned values checked against the source. Native response-format and tool details belong to the selected producer interface; the basic practical requirement is a traceable text result rather than a plausible but unsupported completed field.\n\n### Inspect and continue the task\n\nThe useful artifact can be a reasoned comparison, a draft, a code-related explanation or a tool-informed answer. Review important identifiers, calculations and interpretations against the material that establishes them. Keep any incomplete lookup or contradictory source visible in the conclusion instead of using fluent wording to hide a gap.\n\nThe Thinking family, the named Preview profile and later ERNIE generations have distinct selectors and documented conditions. Preserve the task, source material, completed tool evidence and final response together. This makes the next turn a specific correction or extension of the same investigation rather than an ungrounded reconstruction of the earlier work.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "a1f91444538d789fdd7421780a71f9654bf40c152f76b72cce29761fd6980a36", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "en", "methods": [ { "html": "ernie-5.0-thinking-previewERNIE 5.0 Thinking combines deep reasoning, writing, visual understanding and tool-connected tasks. The documented Preview profile has 128K context, 119K maximum input and final-output settings up to 65,536 tokens, with a separate thinking budget.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
ERNIE 5.0 Thinking is Baidu’s reasoning-oriented model family for complex questions, writing, instruction following and application-connected tasks. The maker’s named Thinking Preview profile combines deep reasoning with visual understanding and support for planning and tool use. Its producer text-response workflow is distinct from treating the entire ERNIE 5.0 research family’s multimodal generation capabilities as one interchangeable request contract.
State the question, the material that can be used and the conditions the answer must satisfy. A research comparison can define the criteria and request the evidence supporting each conclusion. A writing task can provide the audience, factual brief and desired structure. A coding question can identify the behavior to change and the relevant source fragment. Keep the final artifact specific enough to inspect.
For visual understanding, supply material that makes the relevant feature clear and state the question about it. A chart or document image needs readable labels and the surrounding context that establishes what its values mean. Check important text and numerical details against the original material. The model’s visual-understanding purpose does not remove the need to preserve the source with the returned interpretation.
Baidu’s AI Studio table lists the Thinking Preview profile with 128K context and a 119K maximum input. The Chinese table gives final-output settings up to 65,536 tokens and a 2K default, and separately lists a 60K thinking length. Keep these allowances in their roles: the task context, the generated reasoning and the requested final response are different parts of a useful result.
A large input allowance can hold related documents, while the requested answer should still match the decision or artifact needed. For a comparison, ask for a compact evidence table and the governing conclusion rather than repeating every supplied passage. For a technical answer, preserve the input case and expected behavior that make the result checkable. The named Preview specification should not be converted into a guarantee about a later updating selector’s underlying revision.
The manufacturer’s feature index lists the Thinking Preview profile for function calling, search enhancement and structured output. Define an application function and the arguments it needs, execute a returned request in the application and supply the actual result for continuation. An agent plan is not itself evidence that the planned operations finished.
A source-based answer should retain retrieved evidence and distinguish it from the supplied background or an inference. A structured record should define the required fields and how missing information is represented, with the returned values checked against the source. Native response-format and tool details belong to the selected producer interface; the basic practical requirement is a traceable text result rather than a plausible but unsupported completed field.
The useful artifact can be a reasoned comparison, a draft, a code-related explanation or a tool-informed answer. Review important identifiers, calculations and interpretations against the material that establishes them. Keep any incomplete lookup or contradictory source visible in the conclusion instead of using fluent wording to hide a gap.
The Thinking family, the named Preview profile and later ERNIE generations have distinct selectors and documented conditions. Preserve the task, source material, completed tool evidence and final response together. This makes the next turn a specific correction or extension of the same investigation rather than an ungrounded reconstruction of the earlier work.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits ernie-5.0-thinking-preview | Default— |
Fieldmessages | Typemessage[] | RequirementRequired | Values & limits Minimum items: 1 | Default— |
Fieldmessages[].role | Typestring | RequirementRequired | Values & limits Model-specific | Default— |
Fieldmessages[].content | Typestring | RequirementOptional | Values & limits Applies when: Text conversation | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
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 |
Parametercontrol_scope | ContractText conversation; stream is a boolean and defaults to false. |
Parameteroutput_modalities | Contracttext |
Parameterhosted_operations | Contractfalse |
Parametermultimodal_input_binding | Contractnull |
Method aliases: /chat/completions
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 $0.001892 / 1K tokens Output · Output tokens $0.003146 / 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":"ernie-5.0-thinking-preview","messages":[{"role":"user","content":"hello"}],"stream":false}')\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="ernie-5.0-thinking-preview", messages=[{"role":"user","content":"hello"}], stream=False)\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"))\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 ernie-5.0-thinking-preview
/chat/completions
ernie-5.0-thinking-previewERNIE 5.0 Thinking combines deep reasoning, writing, visual understanding and tool-connected tasks. The documented Preview profile has 128K context, 119K maximum input and final-output settings up to 65,536 tokens, with a separate thinking budget.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
ERNIE 5.0 Thinking is Baidu’s reasoning-oriented model family for complex questions, writing, instruction following and application-connected tasks. The maker’s named Thinking Preview profile combines deep reasoning with visual understanding and support for planning and tool use. Its producer text-response workflow is distinct from treating the entire ERNIE 5.0 research family’s multimodal generation capabilities as one interchangeable request contract.
State the question, the material that can be used and the conditions the answer must satisfy. A research comparison can define the criteria and request the evidence supporting each conclusion. A writing task can provide the audience, factual brief and desired structure. A coding question can identify the behavior to change and the relevant source fragment. Keep the final artifact specific enough to inspect.
For visual understanding, supply material that makes the relevant feature clear and state the question about it. A chart or document image needs readable labels and the surrounding context that establishes what its values mean. Check important text and numerical details against the original material. The model’s visual-understanding purpose does not remove the need to preserve the source with the returned interpretation.
Baidu’s AI Studio table lists the Thinking Preview profile with 128K context and a 119K maximum input. The Chinese table gives final-output settings up to 65,536 tokens and a 2K default, and separately lists a 60K thinking length. Keep these allowances in their roles: the task context, the generated reasoning and the requested final response are different parts of a useful result.
A large input allowance can hold related documents, while the requested answer should still match the decision or artifact needed. For a comparison, ask for a compact evidence table and the governing conclusion rather than repeating every supplied passage. For a technical answer, preserve the input case and expected behavior that make the result checkable. The named Preview specification should not be converted into a guarantee about a later updating selector’s underlying revision.
The manufacturer’s feature index lists the Thinking Preview profile for function calling, search enhancement and structured output. Define an application function and the arguments it needs, execute a returned request in the application and supply the actual result for continuation. An agent plan is not itself evidence that the planned operations finished.
A source-based answer should retain retrieved evidence and distinguish it from the supplied background or an inference. A structured record should define the required fields and how missing information is represented, with the returned values checked against the source. Native response-format and tool details belong to the selected producer interface; the basic practical requirement is a traceable text result rather than a plausible but unsupported completed field.
The useful artifact can be a reasoned comparison, a draft, a code-related explanation or a tool-informed answer. Review important identifiers, calculations and interpretations against the material that establishes them. Keep any incomplete lookup or contradictory source visible in the conclusion instead of using fluent wording to hide a gap.
The Thinking family, the named Preview profile and later ERNIE generations have distinct selectors and documented conditions. Preserve the task, source material, completed tool evidence and final response together. This makes the next turn a specific correction or extension of the same investigation rather than an ungrounded reconstruction of the earlier work.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits ernie-5.0-thinking-preview | 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 $0.001892 / 1K tokens Output · Output tokens $0.003146 / 1K tokens Input · Cache read $0 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "ernie-5.0-thinking-preview",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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': 'ernie-5.0-thinking-preview', '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': 'ernie-5.0-thinking-preview', '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 ernie-5.0-thinking-preview
/chat/completions