Mistral Large is Mistral AI’s general-purpose multimodal family for complex document work, software engineering and agentic tasks. Large 4 combines instruction-following, reasoning and tool use with native visual understanding. Its granular mixture-of-experts architecture has 1.05 trillion total parameters and 52 billion active parameters, alongside a 1.6-billion-parameter vision encoder. The Large 4 context window is 1M tokens. Large 3 is a separate edition with 675 billion total parameters, 41 billion active parameters and a 256K context window.
The model works with written tasks and visual material to produce text, code or structured results. In the Large 4 reasoning workflow, a minimal-effort setting returns the answer directly, while high effort includes a reasoning segment before the final answer. Complete assistant messages preserve continuity over follow-up turns. Structured output can use JSON or a custom schema, and the application can provide a prefix for a controlled opening of the response.
Function calling links an analytical task with external information and actions. Provide the function descriptions, input fields and the user’s objective. The model chooses a function and prepares arguments; the application executes it, returns the result and continues the conversation. The workflow may involve successive calls or several calls in parallel. Document question answering combines document extraction with language understanding, while batch processing handles collections of requests asynchronously. Tool availability and execution are supplied by the application around the model.
Large 4’s capability areas begin with security analysis: the manufacturer describes malware triage, prioritizing vulnerabilities and preparing detection rules for defensive work. In agentic coding, the focus is repository understanding, software changes and complex terminal workflows. A useful coding assignment identifies the affected behavior, the files and dependencies involved, and the checks that will establish a correct result.
For general agent workflows, the model can gather material, use connected tools and assemble deliverables such as documents, spreadsheets and slide content. Its multimodal work covers charts, complex pages, natural scenes and technical drawings. Visual grounding links a question to an object or region; an engineering task can inspect the supplied drawing, compare visible parts and return an explanation tied to the evidence. In document analysis, ask for the specific page, table or passage that supports each conclusion.
Scientific and mathematical applications include data analysis, modeling, simulation code and extended applied-mathematics tasks. Knowledge work includes editing documents and spreadsheets and comparing information from multiple sources. An Ailoot API task can specify an editable report outline, a structured set of findings or code for the application to execute and verify. These are distinct outputs: an explanation answers a question, a structured result passes data onward, and a tool-assisted workflow uses the application to create or update the final artifact.
Large 4’s training includes multilingual material spanning more than 160 languages, including all official languages of the European Union. Its post-training combines supervised fine-tuning with reinforcement learning across reasoning, scientific work, tool use, factuality and safety alignment. The safety work addresses indirect prompt injection and malicious cybersecurity requests. The family selection remains an updated model line: the numerical architectures, context windows and reasoning behavior above belong to the explicitly named editions, which stay distinct when choosing a fixed version.
", "aboutText": "Mistral Large is Mistral AI’s general-purpose multimodal family for complex document work, software engineering and agentic tasks. Large 4 combines instruction-following, reasoning and tool use with native visual understanding. Its granular mixture-of-experts architecture has 1.05 trillion total parameters and 52 billion active parameters, alongside a 1.6-billion-parameter vision encoder. The Large 4 context window is 1M tokens. Large 3 is a separate edition with 675 billion total parameters, 41 billion active parameters and a 256K context window.\n\nThe model works with written tasks and visual material to produce text, code or structured results. In the Large 4 reasoning workflow, a minimal-effort setting returns the answer directly, while high effort includes a reasoning segment before the final answer. Complete assistant messages preserve continuity over follow-up turns. Structured output can use JSON or a custom schema, and the application can provide a prefix for a controlled opening of the response.\n\nFunction calling links an analytical task with external information and actions. Provide the function descriptions, input fields and the user’s objective. The model chooses a function and prepares arguments; the application executes it, returns the result and continues the conversation. The workflow may involve successive calls or several calls in parallel. Document question answering combines document extraction with language understanding, while batch processing handles collections of requests asynchronously. Tool availability and execution are supplied by the application around the model.\n\nLarge 4’s capability areas begin with security analysis: the manufacturer describes malware triage, prioritizing vulnerabilities and preparing detection rules for defensive work. In agentic coding, the focus is repository understanding, software changes and complex terminal workflows. A useful coding assignment identifies the affected behavior, the files and dependencies involved, and the checks that will establish a correct result.\n\nFor general agent workflows, the model can gather material, use connected tools and assemble deliverables such as documents, spreadsheets and slide content. Its multimodal work covers charts, complex pages, natural scenes and technical drawings. Visual grounding links a question to an object or region; an engineering task can inspect the supplied drawing, compare visible parts and return an explanation tied to the evidence. In document analysis, ask for the specific page, table or passage that supports each conclusion.\n\nScientific and mathematical applications include data analysis, modeling, simulation code and extended applied-mathematics tasks. Knowledge work includes editing documents and spreadsheets and comparing information from multiple sources. An Ailoot API task can specify an editable report outline, a structured set of findings or code for the application to execute and verify. These are distinct outputs: an explanation answers a question, a structured result passes data onward, and a tool-assisted workflow uses the application to create or update the final artifact.\n\nLarge 4’s training includes multilingual material spanning more than 160 languages, including all official languages of the European Union. Its post-training combines supervised fine-tuning with reinforcement learning across reasoning, scientific work, tool use, factuality and safety alignment. The safety work addresses indirect prompt injection and malicious cybersecurity requests. The family selection remains an updated model line: the numerical architectures, context windows and reasoning behavior above belong to the explicitly named editions, which stay distinct when choosing a fixed version.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Find a report inconsistency\n\nReview these report sections. [Summary] The pilot covered 120 orders and had 6 returns. [Table] Delivered: 114; returned: 6; cancelled before dispatch: 5. Identify which totals can be reconciled and which scope is unclear. Draft a correction question for the report author, retaining section labels and avoiding an invented denominator.A source-linked finding table and a precise question about the order population and cancellations.Ensure the five cancellations are not silently added to or removed from the stated 120-order pilot.mistral-large-latestMistral AI’s Large family combines document and image understanding with reasoning, coding and tool-based workflows. Published Large editions support structured responses and long-context work, with architecture and context sizes tied to each named version.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Mistral Large is Mistral AI’s general-purpose multimodal family for complex document work, software engineering and agentic tasks. Large 4 combines instruction-following, reasoning and tool use with native visual understanding. Its granular mixture-of-experts architecture has 1.05 trillion total parameters and 52 billion active parameters, alongside a 1.6-billion-parameter vision encoder. The Large 4 context window is 1M tokens. Large 3 is a separate edition with 675 billion total parameters, 41 billion active parameters and a 256K context window.
The model works with written tasks and visual material to produce text, code or structured results. In the Large 4 reasoning workflow, a minimal-effort setting returns the answer directly, while high effort includes a reasoning segment before the final answer. Complete assistant messages preserve continuity over follow-up turns. Structured output can use JSON or a custom schema, and the application can provide a prefix for a controlled opening of the response.
Function calling links an analytical task with external information and actions. Provide the function descriptions, input fields and the user’s objective. The model chooses a function and prepares arguments; the application executes it, returns the result and continues the conversation. The workflow may involve successive calls or several calls in parallel. Document question answering combines document extraction with language understanding, while batch processing handles collections of requests asynchronously. Tool availability and execution are supplied by the application around the model.
Large 4’s capability areas begin with security analysis: the manufacturer describes malware triage, prioritizing vulnerabilities and preparing detection rules for defensive work. In agentic coding, the focus is repository understanding, software changes and complex terminal workflows. A useful coding assignment identifies the affected behavior, the files and dependencies involved, and the checks that will establish a correct result.
For general agent workflows, the model can gather material, use connected tools and assemble deliverables such as documents, spreadsheets and slide content. Its multimodal work covers charts, complex pages, natural scenes and technical drawings. Visual grounding links a question to an object or region; an engineering task can inspect the supplied drawing, compare visible parts and return an explanation tied to the evidence. In document analysis, ask for the specific page, table or passage that supports each conclusion.
Scientific and mathematical applications include data analysis, modeling, simulation code and extended applied-mathematics tasks. Knowledge work includes editing documents and spreadsheets and comparing information from multiple sources. An Ailoot API task can specify an editable report outline, a structured set of findings or code for the application to execute and verify. These are distinct outputs: an explanation answers a question, a structured result passes data onward, and a tool-assisted workflow uses the application to create or update the final artifact.
Large 4’s training includes multilingual material spanning more than 160 languages, including all official languages of the European Union. Its post-training combines supervised fine-tuning with reinforcement learning across reasoning, scientific work, tool use, factuality and safety alignment. The safety work addresses indirect prompt injection and malicious cybersecurity requests. The family selection remains an updated model line: the numerical architectures, context windows and reasoning behavior above belong to the explicitly named editions, which stay distinct when choosing a fixed version.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits mistral-large-latest | 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 $0.0044 / 1K tokens Output · Output tokens $0.0132 / 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": "mistral-large-latest", "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='mistral-large-latest',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='mistral-large-latest',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 mistral-large-latest
Use the method paths shown above.
mistral-large-latestMistral AI’s Large family combines document and image understanding with reasoning, coding and tool-based workflows. Published Large editions support structured responses and long-context work, with architecture and context sizes tied to each named version.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Mistral Large is Mistral AI’s general-purpose multimodal family for complex document work, software engineering and agentic tasks. Large 4 combines instruction-following, reasoning and tool use with native visual understanding. Its granular mixture-of-experts architecture has 1.05 trillion total parameters and 52 billion active parameters, alongside a 1.6-billion-parameter vision encoder. The Large 4 context window is 1M tokens. Large 3 is a separate edition with 675 billion total parameters, 41 billion active parameters and a 256K context window.
The model works with written tasks and visual material to produce text, code or structured results. In the Large 4 reasoning workflow, a minimal-effort setting returns the answer directly, while high effort includes a reasoning segment before the final answer. Complete assistant messages preserve continuity over follow-up turns. Structured output can use JSON or a custom schema, and the application can provide a prefix for a controlled opening of the response.
Function calling links an analytical task with external information and actions. Provide the function descriptions, input fields and the user’s objective. The model chooses a function and prepares arguments; the application executes it, returns the result and continues the conversation. The workflow may involve successive calls or several calls in parallel. Document question answering combines document extraction with language understanding, while batch processing handles collections of requests asynchronously. Tool availability and execution are supplied by the application around the model.
Large 4’s capability areas begin with security analysis: the manufacturer describes malware triage, prioritizing vulnerabilities and preparing detection rules for defensive work. In agentic coding, the focus is repository understanding, software changes and complex terminal workflows. A useful coding assignment identifies the affected behavior, the files and dependencies involved, and the checks that will establish a correct result.
For general agent workflows, the model can gather material, use connected tools and assemble deliverables such as documents, spreadsheets and slide content. Its multimodal work covers charts, complex pages, natural scenes and technical drawings. Visual grounding links a question to an object or region; an engineering task can inspect the supplied drawing, compare visible parts and return an explanation tied to the evidence. In document analysis, ask for the specific page, table or passage that supports each conclusion.
Scientific and mathematical applications include data analysis, modeling, simulation code and extended applied-mathematics tasks. Knowledge work includes editing documents and spreadsheets and comparing information from multiple sources. An Ailoot API task can specify an editable report outline, a structured set of findings or code for the application to execute and verify. These are distinct outputs: an explanation answers a question, a structured result passes data onward, and a tool-assisted workflow uses the application to create or update the final artifact.
Large 4’s training includes multilingual material spanning more than 160 languages, including all official languages of the European Union. Its post-training combines supervised fine-tuning with reinforcement learning across reasoning, scientific work, tool use, factuality and safety alignment. The safety work addresses indirect prompt injection and malicious cybersecurity requests. The family selection remains an updated model line: the numerical architectures, context windows and reasoning behavior above belong to the explicitly named editions, which stay distinct when choosing a fixed version.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits mistral-large-latest | 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 $0.0044 / 1K tokens Output · Output tokens $0.0132 / 1K tokens Input · Cache read $0 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "mistral-large-latest",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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': 'mistral-large-latest', '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': 'mistral-large-latest', '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 mistral-large-latest
Use the method paths shown above.
Technical example in English
Find a report inconsistency\n\nReview these report sections. [Summary] The pilot covered 120 orders and had 6 returns. [Table] Delivered: 114; returned: 6; cancelled before dispatch: 5. Identify which totals can be reconciled and which scope is unclear. Draft a correction question for the report author, retaining section labels and avoiding an invented denominator.A source-linked finding table and a precise question about the order population and cancellations.Ensure the five cancellations are not silently added to or removed from the stated 120-order pilot.