ERNIE 4.5 VL 424B-A47B is Baidu’s vision-language chat model, developed from the corresponding ERNIE 4.5 VL Base model. It combines textual instructions with visual material and generates a text answer. Its mixture-of-experts network has 424 billion parameters in total, with 47 billion activated for each token, and the manufacturer publishes a context length of 131,072 tokens.
ERNIE 4.5 highlights. The family uses a heterogeneous mixture-of-experts design that shares some knowledge across language and vision while preserving modality-specific processing. Baidu describes joint multimodal pre-training, efficient training and inference infrastructure, and post-training adapted to the intended modality. For the VL model, the emphasis is image understanding, task-specific visual instructions and reasoning that connects visual evidence with language. Its training includes supervised fine-tuning and reinforcement learning with verifiable rewards.
Model overview. The configuration lists 54 layers, 64 query attention heads and 8 key/value heads, with separate text and vision expert groups. Each group lists 64 experts and 8 activated experts. The manufacturer’s model table identifies text, image and video as input modalities for this edition and text as the output. Think of the output as an interpretation of the supplied content: a description, an answer to a visual question or a reasoned explanation of what the material supports.
Image understanding. Provide the original image and an explicit question. For a document page, retain labels, column headings and the text surrounding a disputed value, then request selected fields with the page location that supports them. For a diagram, state whether the goal is to explain its components, follow a process or compare it with a written specification. Ask the model to report the visible labels before drawing a conclusion so that you can review the observations separately from the interpretation.
Multimodal reasoning. When several images contribute to the same task, label their roles and explain which details should be compared. A useful request can pair a product photograph with a supplied specification and ask for a list of visible matches, differences and items the picture cannot establish. For time-based material, identify the event or change you want to understand and request a sequence of observations tied to the supplied frames or segments. The final artifact should make the evidence behind a claimed change easy to inspect.
Thinking and direct responses. Baidu describes thinking and non-thinking modes for its vision-language models. Thinking serves tasks that require analysis across visual and textual information; a direct response can serve a straightforward description or a simple visual question. State the needed result clearly, such as a concise answer, a comparison table or an explanation with supporting observations. Mode selection belongs to the generation setup rather than the ordinary wording of an image request.
Prepare material around the question. Use readable pages and relevant views, keep image labels consistent and reserve room for the requested text answer within the context. Ask the model to mark unreadable text and separate inferred properties from visible details. A picture may show a label, shape or arrangement while the answer also needs a supplied rule or specification. Confirm critical extracted values against the original and use an additional view when the evidence leaves an important detail unresolved.
", "aboutText": "ERNIE 4.5 VL 424B-A47B is Baidu’s vision-language chat model, developed from the corresponding ERNIE 4.5 VL Base model. It combines textual instructions with visual material and generates a text answer. Its mixture-of-experts network has 424 billion parameters in total, with 47 billion activated for each token, and the manufacturer publishes a context length of 131,072 tokens.\n\nERNIE 4.5 highlights. The family uses a heterogeneous mixture-of-experts design that shares some knowledge across language and vision while preserving modality-specific processing. Baidu describes joint multimodal pre-training, efficient training and inference infrastructure, and post-training adapted to the intended modality. For the VL model, the emphasis is image understanding, task-specific visual instructions and reasoning that connects visual evidence with language. Its training includes supervised fine-tuning and reinforcement learning with verifiable rewards.\n\nModel overview. The configuration lists 54 layers, 64 query attention heads and 8 key/value heads, with separate text and vision expert groups. Each group lists 64 experts and 8 activated experts. The manufacturer’s model table identifies text, image and video as input modalities for this edition and text as the output. Think of the output as an interpretation of the supplied content: a description, an answer to a visual question or a reasoned explanation of what the material supports.\n\nImage understanding. Provide the original image and an explicit question. For a document page, retain labels, column headings and the text surrounding a disputed value, then request selected fields with the page location that supports them. For a diagram, state whether the goal is to explain its components, follow a process or compare it with a written specification. Ask the model to report the visible labels before drawing a conclusion so that you can review the observations separately from the interpretation.\n\nMultimodal reasoning. When several images contribute to the same task, label their roles and explain which details should be compared. A useful request can pair a product photograph with a supplied specification and ask for a list of visible matches, differences and items the picture cannot establish. For time-based material, identify the event or change you want to understand and request a sequence of observations tied to the supplied frames or segments. The final artifact should make the evidence behind a claimed change easy to inspect.\n\nThinking and direct responses. Baidu describes thinking and non-thinking modes for its vision-language models. Thinking serves tasks that require analysis across visual and textual information; a direct response can serve a straightforward description or a simple visual question. State the needed result clearly, such as a concise answer, a comparison table or an explanation with supporting observations. Mode selection belongs to the generation setup rather than the ordinary wording of an image request.\n\nPrepare material around the question. Use readable pages and relevant views, keep image labels consistent and reserve room for the requested text answer within the context. Ask the model to mark unreadable text and separate inferred properties from visible details. A picture may show a label, shape or arrangement while the answer also needs a supplied rule or specification. Confirm critical extracted values against the original and use an additional view when the evidence leaves an important detail unresolved.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Check a transcribed approval flow\n\nReview this transcribed process: Draft -> Manager approval -> Publish. A second branch says Draft -> Publish for urgent items. Written rule: every publication needs manager approval, including urgent work. Identify the conflict, cite the relevant labels and propose a revised text sequence that follows the rule.The conflicting branch, a rule-linked explanation and a revised sequence expressed in text.Check that the revision includes manager approval on the urgent path and uses only the supplied transcription.baidu/ernie-4.5-vl-424b-a47bERNIE 4.5 VL 424B-A47B is Baidu’s vision-language mixture-of-experts model for image understanding and multimodal reasoning. Its published configuration has 424 billion total parameters, 47 billion active per token and a 131,072-token context; answers are generated as text.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
ERNIE 4.5 VL 424B-A47B is Baidu’s vision-language chat model, developed from the corresponding ERNIE 4.5 VL Base model. It combines textual instructions with visual material and generates a text answer. Its mixture-of-experts network has 424 billion parameters in total, with 47 billion activated for each token, and the manufacturer publishes a context length of 131,072 tokens.
ERNIE 4.5 highlights. The family uses a heterogeneous mixture-of-experts design that shares some knowledge across language and vision while preserving modality-specific processing. Baidu describes joint multimodal pre-training, efficient training and inference infrastructure, and post-training adapted to the intended modality. For the VL model, the emphasis is image understanding, task-specific visual instructions and reasoning that connects visual evidence with language. Its training includes supervised fine-tuning and reinforcement learning with verifiable rewards.
Model overview. The configuration lists 54 layers, 64 query attention heads and 8 key/value heads, with separate text and vision expert groups. Each group lists 64 experts and 8 activated experts. The manufacturer’s model table identifies text, image and video as input modalities for this edition and text as the output. Think of the output as an interpretation of the supplied content: a description, an answer to a visual question or a reasoned explanation of what the material supports.
Image understanding. Provide the original image and an explicit question. For a document page, retain labels, column headings and the text surrounding a disputed value, then request selected fields with the page location that supports them. For a diagram, state whether the goal is to explain its components, follow a process or compare it with a written specification. Ask the model to report the visible labels before drawing a conclusion so that you can review the observations separately from the interpretation.
Multimodal reasoning. When several images contribute to the same task, label their roles and explain which details should be compared. A useful request can pair a product photograph with a supplied specification and ask for a list of visible matches, differences and items the picture cannot establish. For time-based material, identify the event or change you want to understand and request a sequence of observations tied to the supplied frames or segments. The final artifact should make the evidence behind a claimed change easy to inspect.
Thinking and direct responses. Baidu describes thinking and non-thinking modes for its vision-language models. Thinking serves tasks that require analysis across visual and textual information; a direct response can serve a straightforward description or a simple visual question. State the needed result clearly, such as a concise answer, a comparison table or an explanation with supporting observations. Mode selection belongs to the generation setup rather than the ordinary wording of an image request.
Prepare material around the question. Use readable pages and relevant views, keep image labels consistent and reserve room for the requested text answer within the context. Ask the model to mark unreadable text and separate inferred properties from visible details. A picture may show a label, shape or arrangement while the answer also needs a supplied rule or specification. Confirm critical extracted values against the original and use an additional view when the evidence leaves an important detail unresolved.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits baidu/ernie-4.5-vl-424b-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 $0.000858 / 1K tokens Output · Output tokens $0.00258 / 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-vl-424b-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-vl-424b-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-vl-424b-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-vl-424b-a47b
Use the method paths shown above.
baidu/ernie-4.5-vl-424b-a47bERNIE 4.5 VL 424B-A47B is Baidu’s vision-language mixture-of-experts model for image understanding and multimodal reasoning. Its published configuration has 424 billion total parameters, 47 billion active per token and a 131,072-token context; answers are generated as text.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
ERNIE 4.5 VL 424B-A47B is Baidu’s vision-language chat model, developed from the corresponding ERNIE 4.5 VL Base model. It combines textual instructions with visual material and generates a text answer. Its mixture-of-experts network has 424 billion parameters in total, with 47 billion activated for each token, and the manufacturer publishes a context length of 131,072 tokens.
ERNIE 4.5 highlights. The family uses a heterogeneous mixture-of-experts design that shares some knowledge across language and vision while preserving modality-specific processing. Baidu describes joint multimodal pre-training, efficient training and inference infrastructure, and post-training adapted to the intended modality. For the VL model, the emphasis is image understanding, task-specific visual instructions and reasoning that connects visual evidence with language. Its training includes supervised fine-tuning and reinforcement learning with verifiable rewards.
Model overview. The configuration lists 54 layers, 64 query attention heads and 8 key/value heads, with separate text and vision expert groups. Each group lists 64 experts and 8 activated experts. The manufacturer’s model table identifies text, image and video as input modalities for this edition and text as the output. Think of the output as an interpretation of the supplied content: a description, an answer to a visual question or a reasoned explanation of what the material supports.
Image understanding. Provide the original image and an explicit question. For a document page, retain labels, column headings and the text surrounding a disputed value, then request selected fields with the page location that supports them. For a diagram, state whether the goal is to explain its components, follow a process or compare it with a written specification. Ask the model to report the visible labels before drawing a conclusion so that you can review the observations separately from the interpretation.
Multimodal reasoning. When several images contribute to the same task, label their roles and explain which details should be compared. A useful request can pair a product photograph with a supplied specification and ask for a list of visible matches, differences and items the picture cannot establish. For time-based material, identify the event or change you want to understand and request a sequence of observations tied to the supplied frames or segments. The final artifact should make the evidence behind a claimed change easy to inspect.
Thinking and direct responses. Baidu describes thinking and non-thinking modes for its vision-language models. Thinking serves tasks that require analysis across visual and textual information; a direct response can serve a straightforward description or a simple visual question. State the needed result clearly, such as a concise answer, a comparison table or an explanation with supporting observations. Mode selection belongs to the generation setup rather than the ordinary wording of an image request.
Prepare material around the question. Use readable pages and relevant views, keep image labels consistent and reserve room for the requested text answer within the context. Ask the model to mark unreadable text and separate inferred properties from visible details. A picture may show a label, shape or arrangement while the answer also needs a supplied rule or specification. Confirm critical extracted values against the original and use an additional view when the evidence leaves an important detail unresolved.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits baidu/ernie-4.5-vl-424b-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 $0.000858 / 1K tokens Output · Output tokens $0.00258 / 1K tokens Input · Cache read $0 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "baidu/ernie-4.5-vl-424b-a47b",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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-vl-424b-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-vl-424b-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-vl-424b-a47b
Use the method paths shown above.
Technical example in English
Check a transcribed approval flow\n\nReview this transcribed process: Draft -> Manager approval -> Publish. A second branch says Draft -> Publish for urgent items. Written rule: every publication needs manager approval, including urgent work. Identify the conflict, cite the relevant labels and propose a revised text sequence that follows the rule.The conflicting branch, a rule-linked explanation and a revised sequence expressed in text.Check that the revision includes manager approval on the urgent path and uses only the supplied transcription.