Mistral Large 4 is Mistral AI's general-purpose multimodal model combining instruction following, reasoning, coding and agentic work. It accepts text and images and produces text, including explanations, code and structured fields. Its granular mixture-of-experts architecture uses selected components for each token rather than activating the entire parameter set at once.
Architecture and context
The current model page lists 1.05 trillion total parameters, 52 billion active parameters and a 1.6-billion-parameter vision encoder. The maker's release page clarifies the counting convention: 49 billion active parameters per token, or 52 billion including embeddings and output layers. These figures describe the model's structure rather than the length of an answer.
The maker documents a one-million-token context window. Use it to bring substantial source material, the conversation and instructions together, while defining the purpose of the final artifact. For a multi-document question, identify each document and its role and request the source location beside each finding. A large context is useful when requirements, diagrams and related explanations must be considered together.
Structured answers and document questions
The model card lists structured outputs, function calling, document question answering, response prefixes, batch submission and agent conversations. Mistral's structured-output documentation distinguishes JSON mode from a custom schema. Specify the required JSON format in the prompt; use a defined schema when the connected interface needs a particular field structure. A record can separate source facts, interpretations and open questions instead of combining them in one paragraph.
Document question answering is a workflow combining document processing with language-model understanding. OCR prepares the text, structure and formatting, after which the model answers a question about that material. A request can locate a requirement, compare statements across documents or summarize the evidence relevant to a decision. Direct image understanding and an OCR-assisted document workflow are related ways to prepare evidence; a document-processing step remains distinct from an image input.
For example, supply a technical specification and drawings, identify the revision under consideration, and request a requirements matrix. Each row can contain the requirement, the supporting document or drawing, the observed difference and the clarification still needed. Retain labels, units and image regions that determine the comparison so that the result remains connected to the source material.
Coding, agents and visual reasoning
The release describes cybersecurity analysis, software engineering, repository understanding and terminal-oriented workflows. For a defensive code review, provide the relevant code path, expected behavior and evidence of the failure. Ask for the cause, a proposed correction and examples that distinguish the old behavior from the intended one. For a repository question, include the modules and call relationships needed to explain the selected behavior.
Function calling connects reasoning to tools supplied by the application. The maker's sequence defines the functions, provides the user's question, lets the model prepare arguments, executes the chosen function in the application and returns its result for the next answer. A proposed call is distinct from execution. The card also lists built-in tools within the maker's agent/conversation interface; they belong to that connected workflow rather than adding a new input or output modality to the model.
Visual understanding includes documents, charts, natural scenes and engineering drawings. A drawing task can ask which labeled component meets a supplied requirement, which dimension or annotation supports the finding and which region needs closer inspection. The release's visual-agent examples combine interpretation with inspection steps; zooming, retrieval and other actions need the surrounding tool environment.
Science, mathematics and professional deliverables
The maker describes scientific coding, data analysis, modeling and mathematical reasoning among the intended applications. Supply the equations, assumptions, units and required result form. A scientific coding request can ask for an implementation, the meaning of each variable and a plan for comparing its output with reference conditions. Producing that implementation is a text result; running the simulation or creating a file requires the application environment.
For professional document work, provide the source reports and define the artifact: a comparison table, explanation, revised passage or spreadsheet content. State the calculation basis and retain supporting document locations. The release also describes multilingual training across more than 160 languages, including all official European Union languages; identify the required output language and terminology when preparing a multilingual task.
Useful boundaries
The documented modalities are text and image input with text output. The maker's one-million-token context is not a separate maximum answer-length specification, and the sources read do not establish an independent hard output limit for this entry. Keep the exact Large 4 edition, prepared evidence and connected tools explicit. A structured record, explanation or proposed action is most useful when its fields, supporting sources and next application step are defined before the request.
", "aboutText": "Mistral Large 4 is Mistral AI's general-purpose multimodal model combining instruction following, reasoning, coding and agentic work. It accepts text and images and produces text, including explanations, code and structured fields. Its granular mixture-of-experts architecture uses selected components for each token rather than activating the entire parameter set at once.\n\nArchitecture and context\n\nThe current model page lists 1.05 trillion total parameters, 52 billion active parameters and a 1.6-billion-parameter vision encoder. The maker's release page clarifies the counting convention: 49 billion active parameters per token, or 52 billion including embeddings and output layers. These figures describe the model's structure rather than the length of an answer.\n\nThe maker documents a one-million-token context window. Use it to bring substantial source material, the conversation and instructions together, while defining the purpose of the final artifact. For a multi-document question, identify each document and its role and request the source location beside each finding. A large context is useful when requirements, diagrams and related explanations must be considered together.\n\nStructured answers and document questions\n\nThe model card lists structured outputs, function calling, document question answering, response prefixes, batch submission and agent conversations. Mistral's structured-output documentation distinguishes JSON mode from a custom schema. Specify the required JSON format in the prompt; use a defined schema when the connected interface needs a particular field structure. A record can separate source facts, interpretations and open questions instead of combining them in one paragraph.\n\nDocument question answering is a workflow combining document processing with language-model understanding. OCR prepares the text, structure and formatting, after which the model answers a question about that material. A request can locate a requirement, compare statements across documents or summarize the evidence relevant to a decision. Direct image understanding and an OCR-assisted document workflow are related ways to prepare evidence; a document-processing step remains distinct from an image input.\n\nFor example, supply a technical specification and drawings, identify the revision under consideration, and request a requirements matrix. Each row can contain the requirement, the supporting document or drawing, the observed difference and the clarification still needed. Retain labels, units and image regions that determine the comparison so that the result remains connected to the source material.\n\nCoding, agents and visual reasoning\n\nThe release describes cybersecurity analysis, software engineering, repository understanding and terminal-oriented workflows. For a defensive code review, provide the relevant code path, expected behavior and evidence of the failure. Ask for the cause, a proposed correction and examples that distinguish the old behavior from the intended one. For a repository question, include the modules and call relationships needed to explain the selected behavior.\n\nFunction calling connects reasoning to tools supplied by the application. The maker's sequence defines the functions, provides the user's question, lets the model prepare arguments, executes the chosen function in the application and returns its result for the next answer. A proposed call is distinct from execution. The card also lists built-in tools within the maker's agent/conversation interface; they belong to that connected workflow rather than adding a new input or output modality to the model.\n\nVisual understanding includes documents, charts, natural scenes and engineering drawings. A drawing task can ask which labeled component meets a supplied requirement, which dimension or annotation supports the finding and which region needs closer inspection. The release's visual-agent examples combine interpretation with inspection steps; zooming, retrieval and other actions need the surrounding tool environment.\n\nScience, mathematics and professional deliverables\n\nThe maker describes scientific coding, data analysis, modeling and mathematical reasoning among the intended applications. Supply the equations, assumptions, units and required result form. A scientific coding request can ask for an implementation, the meaning of each variable and a plan for comparing its output with reference conditions. Producing that implementation is a text result; running the simulation or creating a file requires the application environment.\n\nFor professional document work, provide the source reports and define the artifact: a comparison table, explanation, revised passage or spreadsheet content. State the calculation basis and retain supporting document locations. The release also describes multilingual training across more than 160 languages, including all official European Union languages; identify the required output language and terminology when preparing a multilingual task.\n\nUseful boundaries\n\nThe documented modalities are text and image input with text output. The maker's one-million-token context is not a separate maximum answer-length specification, and the sources read do not establish an independent hard output limit for this entry. Keep the exact Large 4 edition, prepared evidence and connected tools explicit. A structured record, explanation or proposed action is most useful when its fields, supporting sources and next application step are defined before the request.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Build an engineering requirement matrix\n\nCreate a requirements matrix from these text excerpts. Spec S1: the enclosure must fit a 60 mm cable bend radius. Drawing D2: available internal clearance is 45 mm. Note N3: exterior width is 120 mm. For each relevant requirement, show the source evidence, the mismatch and the clarification needed. Do not use exterior width as proof of internal clearance.A source-linked matrix identifying the bend-radius/clearance conflict and the information needed for an engineering decision.The comparison keeps millimetres consistent and does not treat the unrelated exterior dimension as resolving the conflict.mistralai/mistral-large-4-0Mistral Large 4 is a text-and-image model for reasoning, coding, document analysis and tool-driven agents. Its one-million-token maker context supports substantial source collections, with structured answers, function calling and a granular mixture-of-experts architecture.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Mistral Large 4 is Mistral AI's general-purpose multimodal model combining instruction following, reasoning, coding and agentic work. It accepts text and images and produces text, including explanations, code and structured fields. Its granular mixture-of-experts architecture uses selected components for each token rather than activating the entire parameter set at once.
Architecture and context
The current model page lists 1.05 trillion total parameters, 52 billion active parameters and a 1.6-billion-parameter vision encoder. The maker's release page clarifies the counting convention: 49 billion active parameters per token, or 52 billion including embeddings and output layers. These figures describe the model's structure rather than the length of an answer.
The maker documents a one-million-token context window. Use it to bring substantial source material, the conversation and instructions together, while defining the purpose of the final artifact. For a multi-document question, identify each document and its role and request the source location beside each finding. A large context is useful when requirements, diagrams and related explanations must be considered together.
Structured answers and document questions
The model card lists structured outputs, function calling, document question answering, response prefixes, batch submission and agent conversations. Mistral's structured-output documentation distinguishes JSON mode from a custom schema. Specify the required JSON format in the prompt; use a defined schema when the connected interface needs a particular field structure. A record can separate source facts, interpretations and open questions instead of combining them in one paragraph.
Document question answering is a workflow combining document processing with language-model understanding. OCR prepares the text, structure and formatting, after which the model answers a question about that material. A request can locate a requirement, compare statements across documents or summarize the evidence relevant to a decision. Direct image understanding and an OCR-assisted document workflow are related ways to prepare evidence; a document-processing step remains distinct from an image input.
For example, supply a technical specification and drawings, identify the revision under consideration, and request a requirements matrix. Each row can contain the requirement, the supporting document or drawing, the observed difference and the clarification still needed. Retain labels, units and image regions that determine the comparison so that the result remains connected to the source material.
Coding, agents and visual reasoning
The release describes cybersecurity analysis, software engineering, repository understanding and terminal-oriented workflows. For a defensive code review, provide the relevant code path, expected behavior and evidence of the failure. Ask for the cause, a proposed correction and examples that distinguish the old behavior from the intended one. For a repository question, include the modules and call relationships needed to explain the selected behavior.
Function calling connects reasoning to tools supplied by the application. The maker's sequence defines the functions, provides the user's question, lets the model prepare arguments, executes the chosen function in the application and returns its result for the next answer. A proposed call is distinct from execution. The card also lists built-in tools within the maker's agent/conversation interface; they belong to that connected workflow rather than adding a new input or output modality to the model.
Visual understanding includes documents, charts, natural scenes and engineering drawings. A drawing task can ask which labeled component meets a supplied requirement, which dimension or annotation supports the finding and which region needs closer inspection. The release's visual-agent examples combine interpretation with inspection steps; zooming, retrieval and other actions need the surrounding tool environment.
Science, mathematics and professional deliverables
The maker describes scientific coding, data analysis, modeling and mathematical reasoning among the intended applications. Supply the equations, assumptions, units and required result form. A scientific coding request can ask for an implementation, the meaning of each variable and a plan for comparing its output with reference conditions. Producing that implementation is a text result; running the simulation or creating a file requires the application environment.
For professional document work, provide the source reports and define the artifact: a comparison table, explanation, revised passage or spreadsheet content. State the calculation basis and retain supporting document locations. The release also describes multilingual training across more than 160 languages, including all official European Union languages; identify the required output language and terminology when preparing a multilingual task.
Useful boundaries
The documented modalities are text and image input with text output. The maker's one-million-token context is not a separate maximum answer-length specification, and the sources read do not establish an independent hard output limit for this entry. Keep the exact Large 4 edition, prepared evidence and connected tools explicit. A structured record, explanation or proposed action is most useful when its fields, supporting sources and next application step are defined before the request.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits mistralai/mistral-large-4-0 | 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.
Match each charge to the conditions shown. Use one rate for each set of alternative configurations.
| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
|---|---|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.00272 / 1K tokens Output · Output tokens $0.00836 / 1K tokens Input · Cache read $0.00028 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationRequest-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.00272 / 1K tokens Output · Output tokens $0.00836 / 1K tokens Input · Cache read $0.00028 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "mistralai/mistral-large-4-0", "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='mistralai/mistral-large-4-0',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='mistralai/mistral-large-4-0',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 mistralai/mistral-large-4-0
Use the method paths shown above.
mistralai/mistral-large-4-0Mistral Large 4 is a text-and-image model for reasoning, coding, document analysis and tool-driven agents. Its one-million-token maker context supports substantial source collections, with structured answers, function calling and a granular mixture-of-experts architecture.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Mistral Large 4 is Mistral AI's general-purpose multimodal model combining instruction following, reasoning, coding and agentic work. It accepts text and images and produces text, including explanations, code and structured fields. Its granular mixture-of-experts architecture uses selected components for each token rather than activating the entire parameter set at once.
Architecture and context
The current model page lists 1.05 trillion total parameters, 52 billion active parameters and a 1.6-billion-parameter vision encoder. The maker's release page clarifies the counting convention: 49 billion active parameters per token, or 52 billion including embeddings and output layers. These figures describe the model's structure rather than the length of an answer.
The maker documents a one-million-token context window. Use it to bring substantial source material, the conversation and instructions together, while defining the purpose of the final artifact. For a multi-document question, identify each document and its role and request the source location beside each finding. A large context is useful when requirements, diagrams and related explanations must be considered together.
Structured answers and document questions
The model card lists structured outputs, function calling, document question answering, response prefixes, batch submission and agent conversations. Mistral's structured-output documentation distinguishes JSON mode from a custom schema. Specify the required JSON format in the prompt; use a defined schema when the connected interface needs a particular field structure. A record can separate source facts, interpretations and open questions instead of combining them in one paragraph.
Document question answering is a workflow combining document processing with language-model understanding. OCR prepares the text, structure and formatting, after which the model answers a question about that material. A request can locate a requirement, compare statements across documents or summarize the evidence relevant to a decision. Direct image understanding and an OCR-assisted document workflow are related ways to prepare evidence; a document-processing step remains distinct from an image input.
For example, supply a technical specification and drawings, identify the revision under consideration, and request a requirements matrix. Each row can contain the requirement, the supporting document or drawing, the observed difference and the clarification still needed. Retain labels, units and image regions that determine the comparison so that the result remains connected to the source material.
Coding, agents and visual reasoning
The release describes cybersecurity analysis, software engineering, repository understanding and terminal-oriented workflows. For a defensive code review, provide the relevant code path, expected behavior and evidence of the failure. Ask for the cause, a proposed correction and examples that distinguish the old behavior from the intended one. For a repository question, include the modules and call relationships needed to explain the selected behavior.
Function calling connects reasoning to tools supplied by the application. The maker's sequence defines the functions, provides the user's question, lets the model prepare arguments, executes the chosen function in the application and returns its result for the next answer. A proposed call is distinct from execution. The card also lists built-in tools within the maker's agent/conversation interface; they belong to that connected workflow rather than adding a new input or output modality to the model.
Visual understanding includes documents, charts, natural scenes and engineering drawings. A drawing task can ask which labeled component meets a supplied requirement, which dimension or annotation supports the finding and which region needs closer inspection. The release's visual-agent examples combine interpretation with inspection steps; zooming, retrieval and other actions need the surrounding tool environment.
Science, mathematics and professional deliverables
The maker describes scientific coding, data analysis, modeling and mathematical reasoning among the intended applications. Supply the equations, assumptions, units and required result form. A scientific coding request can ask for an implementation, the meaning of each variable and a plan for comparing its output with reference conditions. Producing that implementation is a text result; running the simulation or creating a file requires the application environment.
For professional document work, provide the source reports and define the artifact: a comparison table, explanation, revised passage or spreadsheet content. State the calculation basis and retain supporting document locations. The release also describes multilingual training across more than 160 languages, including all official European Union languages; identify the required output language and terminology when preparing a multilingual task.
Useful boundaries
The documented modalities are text and image input with text output. The maker's one-million-token context is not a separate maximum answer-length specification, and the sources read do not establish an independent hard output limit for this entry. Keep the exact Large 4 edition, prepared evidence and connected tools explicit. A structured record, explanation or proposed action is most useful when its fields, supporting sources and next application step are defined before the request.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits mistralai/mistral-large-4-0 | 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.
Match each charge to the conditions shown. Use one rate for each set of alternative configurations.
| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
|---|---|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.00272 / 1K tokens Output · Output tokens $0.00836 / 1K tokens Input · Cache read $0.00028 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationRequest-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.00272 / 1K tokens Output · Output tokens $0.00836 / 1K tokens Input · Cache read $0.00028 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "mistralai/mistral-large-4-0",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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': 'mistralai/mistral-large-4-0', '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': 'mistralai/mistral-large-4-0', '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 mistralai/mistral-large-4-0
Use the method paths shown above.
Technical example in English
Build an engineering requirement matrix\n\nCreate a requirements matrix from these text excerpts. Spec S1: the enclosure must fit a 60 mm cable bend radius. Drawing D2: available internal clearance is 45 mm. Note N3: exterior width is 120 mm. For each relevant requirement, show the source evidence, the mismatch and the clarification needed. Do not use exterior width as proof of internal clearance.A source-linked matrix identifying the bend-radius/clearance conflict and the information needed for an engineering decision.The comparison keeps millimetres consistent and does not treat the unrelated exterior dimension as resolving the conflict.