Pixtral Large is Mistral AI’s multimodal model built on Mistral Large 2. It combines a 123-billion-parameter multimodal decoder with a one-billion-parameter vision encoder, for a 124-billion-parameter model. The purpose is to retain substantial language capability while understanding the visual evidence needed for an answer: a document page, a chart, a photograph or a screenshot. Inputs can combine text and images; the result is text.
Mistral describes a 128K-token context window and says it can accommodate at least 30 high-resolution images. That statement describes context capacity rather than a universal per-request image-count setting. The practical value is being able to relate several visual sources to one question. A useful comparison task might provide labelled pages from two reports and ask which figures, labels and conclusions differ. Keep the text of the question, the role of each image and the required answer structure together.
The manufacturer illustrates multilingual text reading, document questions, chart interpretation and ordinary image understanding. For a document assistant, ask for visible field names and values, a description of the page layout, or an explanation that connects the wording to a table or figure. For a chart, specify the axes, series or interval you want examined. An illustrative request is: “Compare these charts. Separate values you can read directly from interpretations, identify the change being shown, and list the information needed to check the conclusion.” The result could be a field table, a set of observations or a written explanation.
The model card gives particular attention to the system prompt. Mistral recommends including an instruction that states the assistant’s purpose, even if it is short. This is useful for a visual task because the same image can support different jobs: extract entries, describe a scene, explain a diagram or compare it with a written requirement. State the job and the rules for uncertain or unreadable details. When supplying multiple images, label them and identify their order or relationship so that the answer can connect observations to the correct material.
Mistral’s model page lists document question answering, structured outputs and function calling. The manufacturer interface also supports batch processing. Its structured-output guidance distinguishes a JSON-object format from a custom schema; the JSON mode still calls for an explicit instruction to produce JSON. For extraction, define the fields, the treatment of missing values and the difference between transcribed text and a conclusion. A structured answer is useful when an application needs to process the result, while a free-form explanation is useful when a person needs to understand the reasoning behind it.
For function calling, the application supplies tool definitions and the model proposes a function with arguments. Mistral’s workflow then has the application execute the operation and send its result back before the model writes the follow-up answer. A document workflow could use a tool to look up an identifier that was read from an image, then ask for an explanation using the returned record. The visual model does not gain arbitrary access to external data merely because an image mentions a record: the permitted operation and its result come from the application.
The producer also lists predicted-output and prefix features. Predicted outputs let a caller provide expected text when regenerating a document or code file with a small change; a prefix defines the starting text of the answer. These are distinct preparation controls, rather than extra visual modalities. The useful output remains a textual description, extraction or explanation, not a newly rendered image. Choose clear source images, specify what must be preserved and check critical readings against the original page.
The latest label is a family alias, whereas Pixtral-Large-Instruct-2411 is the fixed manufacturer release documented by the model card. Keep those names distinct when preparing a repeatable task. The published context figure describes the producer’s model; the read pages do not establish a separate universal output-token ceiling. Select the image set, textual question and desired answer length together, and keep version-specific request limits separate from the general visual capabilities described here.
", "aboutText": "Pixtral Large is Mistral AI’s multimodal model built on Mistral Large 2. It combines a 123-billion-parameter multimodal decoder with a one-billion-parameter vision encoder, for a 124-billion-parameter model. The purpose is to retain substantial language capability while understanding the visual evidence needed for an answer: a document page, a chart, a photograph or a screenshot. Inputs can combine text and images; the result is text.\n\nMistral describes a 128K-token context window and says it can accommodate at least 30 high-resolution images. That statement describes context capacity rather than a universal per-request image-count setting. The practical value is being able to relate several visual sources to one question. A useful comparison task might provide labelled pages from two reports and ask which figures, labels and conclusions differ. Keep the text of the question, the role of each image and the required answer structure together.\n\nThe manufacturer illustrates multilingual text reading, document questions, chart interpretation and ordinary image understanding. For a document assistant, ask for visible field names and values, a description of the page layout, or an explanation that connects the wording to a table or figure. For a chart, specify the axes, series or interval you want examined. An illustrative request is: “Compare these charts. Separate values you can read directly from interpretations, identify the change being shown, and list the information needed to check the conclusion.” The result could be a field table, a set of observations or a written explanation.\n\nThe model card gives particular attention to the system prompt. Mistral recommends including an instruction that states the assistant’s purpose, even if it is short. This is useful for a visual task because the same image can support different jobs: extract entries, describe a scene, explain a diagram or compare it with a written requirement. State the job and the rules for uncertain or unreadable details. When supplying multiple images, label them and identify their order or relationship so that the answer can connect observations to the correct material.\n\nMistral’s model page lists document question answering, structured outputs and function calling. The manufacturer interface also supports batch processing. Its structured-output guidance distinguishes a JSON-object format from a custom schema; the JSON mode still calls for an explicit instruction to produce JSON. For extraction, define the fields, the treatment of missing values and the difference between transcribed text and a conclusion. A structured answer is useful when an application needs to process the result, while a free-form explanation is useful when a person needs to understand the reasoning behind it.\n\nFor function calling, the application supplies tool definitions and the model proposes a function with arguments. Mistral’s workflow then has the application execute the operation and send its result back before the model writes the follow-up answer. A document workflow could use a tool to look up an identifier that was read from an image, then ask for an explanation using the returned record. The visual model does not gain arbitrary access to external data merely because an image mentions a record: the permitted operation and its result come from the application.\n\nThe producer also lists predicted-output and prefix features. Predicted outputs let a caller provide expected text when regenerating a document or code file with a small change; a prefix defines the starting text of the answer. These are distinct preparation controls, rather than extra visual modalities. The useful output remains a textual description, extraction or explanation, not a newly rendered image. Choose clear source images, specify what must be preserved and check critical readings against the original page.\n\nThe latest label is a family alias, whereas Pixtral-Large-Instruct-2411 is the fixed manufacturer release documented by the model card. Keep those names distinct when preparing a repeatable task. The published context figure describes the producer’s model; the read pages do not establish a separate universal output-token ceiling. Select the image set, textual question and desired answer length together, and keep version-specific request limits separate from the general visual capabilities described here.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Compare transcribed report charts\n\nCompare these chart transcriptions. Report A: online 40 orders, retail 60; total 100. Report B: online 55 orders, retail 45; total 100. Describe the channel mix change and distinguish order-count change from percentage-point change. Provide a short report caption without inventing chart colors, revenue or causes.A channel comparison table and a two-sentence caption with units distinguishing orders from percentage points.Check that both totals stay 100 and changes are labelled with the correct units rather than relative percent.pixtral-large-latestPixtral Large combines Mistral’s language capabilities with image understanding for documents, charts and photographs. It produces text answers and supports structured results and application-defined tools in the manufacturer’s documented interfaces.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Pixtral Large is Mistral AI’s multimodal model built on Mistral Large 2. It combines a 123-billion-parameter multimodal decoder with a one-billion-parameter vision encoder, for a 124-billion-parameter model. The purpose is to retain substantial language capability while understanding the visual evidence needed for an answer: a document page, a chart, a photograph or a screenshot. Inputs can combine text and images; the result is text.
Mistral describes a 128K-token context window and says it can accommodate at least 30 high-resolution images. That statement describes context capacity rather than a universal per-request image-count setting. The practical value is being able to relate several visual sources to one question. A useful comparison task might provide labelled pages from two reports and ask which figures, labels and conclusions differ. Keep the text of the question, the role of each image and the required answer structure together.
The manufacturer illustrates multilingual text reading, document questions, chart interpretation and ordinary image understanding. For a document assistant, ask for visible field names and values, a description of the page layout, or an explanation that connects the wording to a table or figure. For a chart, specify the axes, series or interval you want examined. An illustrative request is: “Compare these charts. Separate values you can read directly from interpretations, identify the change being shown, and list the information needed to check the conclusion.” The result could be a field table, a set of observations or a written explanation.
The model card gives particular attention to the system prompt. Mistral recommends including an instruction that states the assistant’s purpose, even if it is short. This is useful for a visual task because the same image can support different jobs: extract entries, describe a scene, explain a diagram or compare it with a written requirement. State the job and the rules for uncertain or unreadable details. When supplying multiple images, label them and identify their order or relationship so that the answer can connect observations to the correct material.
Mistral’s model page lists document question answering, structured outputs and function calling. The manufacturer interface also supports batch processing. Its structured-output guidance distinguishes a JSON-object format from a custom schema; the JSON mode still calls for an explicit instruction to produce JSON. For extraction, define the fields, the treatment of missing values and the difference between transcribed text and a conclusion. A structured answer is useful when an application needs to process the result, while a free-form explanation is useful when a person needs to understand the reasoning behind it.
For function calling, the application supplies tool definitions and the model proposes a function with arguments. Mistral’s workflow then has the application execute the operation and send its result back before the model writes the follow-up answer. A document workflow could use a tool to look up an identifier that was read from an image, then ask for an explanation using the returned record. The visual model does not gain arbitrary access to external data merely because an image mentions a record: the permitted operation and its result come from the application.
The producer also lists predicted-output and prefix features. Predicted outputs let a caller provide expected text when regenerating a document or code file with a small change; a prefix defines the starting text of the answer. These are distinct preparation controls, rather than extra visual modalities. The useful output remains a textual description, extraction or explanation, not a newly rendered image. Choose clear source images, specify what must be preserved and check critical readings against the original page.
The latest label is a family alias, whereas Pixtral-Large-Instruct-2411 is the fixed manufacturer release documented by the model card. Keep those names distinct when preparing a repeatable task. The published context figure describes the producer’s model; the read pages do not establish a separate universal output-token ceiling. Select the image set, textual question and desired answer length together, and keep version-specific request limits separate from the general visual capabilities described here.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits pixtral-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": "pixtral-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='pixtral-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='pixtral-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 pixtral-large-latest
Use the method paths shown above.
pixtral-large-latestPixtral Large combines Mistral’s language capabilities with image understanding for documents, charts and photographs. It produces text answers and supports structured results and application-defined tools in the manufacturer’s documented interfaces.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Pixtral Large is Mistral AI’s multimodal model built on Mistral Large 2. It combines a 123-billion-parameter multimodal decoder with a one-billion-parameter vision encoder, for a 124-billion-parameter model. The purpose is to retain substantial language capability while understanding the visual evidence needed for an answer: a document page, a chart, a photograph or a screenshot. Inputs can combine text and images; the result is text.
Mistral describes a 128K-token context window and says it can accommodate at least 30 high-resolution images. That statement describes context capacity rather than a universal per-request image-count setting. The practical value is being able to relate several visual sources to one question. A useful comparison task might provide labelled pages from two reports and ask which figures, labels and conclusions differ. Keep the text of the question, the role of each image and the required answer structure together.
The manufacturer illustrates multilingual text reading, document questions, chart interpretation and ordinary image understanding. For a document assistant, ask for visible field names and values, a description of the page layout, or an explanation that connects the wording to a table or figure. For a chart, specify the axes, series or interval you want examined. An illustrative request is: “Compare these charts. Separate values you can read directly from interpretations, identify the change being shown, and list the information needed to check the conclusion.” The result could be a field table, a set of observations or a written explanation.
The model card gives particular attention to the system prompt. Mistral recommends including an instruction that states the assistant’s purpose, even if it is short. This is useful for a visual task because the same image can support different jobs: extract entries, describe a scene, explain a diagram or compare it with a written requirement. State the job and the rules for uncertain or unreadable details. When supplying multiple images, label them and identify their order or relationship so that the answer can connect observations to the correct material.
Mistral’s model page lists document question answering, structured outputs and function calling. The manufacturer interface also supports batch processing. Its structured-output guidance distinguishes a JSON-object format from a custom schema; the JSON mode still calls for an explicit instruction to produce JSON. For extraction, define the fields, the treatment of missing values and the difference between transcribed text and a conclusion. A structured answer is useful when an application needs to process the result, while a free-form explanation is useful when a person needs to understand the reasoning behind it.
For function calling, the application supplies tool definitions and the model proposes a function with arguments. Mistral’s workflow then has the application execute the operation and send its result back before the model writes the follow-up answer. A document workflow could use a tool to look up an identifier that was read from an image, then ask for an explanation using the returned record. The visual model does not gain arbitrary access to external data merely because an image mentions a record: the permitted operation and its result come from the application.
The producer also lists predicted-output and prefix features. Predicted outputs let a caller provide expected text when regenerating a document or code file with a small change; a prefix defines the starting text of the answer. These are distinct preparation controls, rather than extra visual modalities. The useful output remains a textual description, extraction or explanation, not a newly rendered image. Choose clear source images, specify what must be preserved and check critical readings against the original page.
The latest label is a family alias, whereas Pixtral-Large-Instruct-2411 is the fixed manufacturer release documented by the model card. Keep those names distinct when preparing a repeatable task. The published context figure describes the producer’s model; the read pages do not establish a separate universal output-token ceiling. Select the image set, textual question and desired answer length together, and keep version-specific request limits separate from the general visual capabilities described here.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits pixtral-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 $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "pixtral-large-latest",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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': 'pixtral-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': 'pixtral-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 pixtral-large-latest
Use the method paths shown above.
Technical example in English
Compare transcribed report charts\n\nCompare these chart transcriptions. Report A: online 40 orders, retail 60; total 100. Report B: online 55 orders, retail 45; total 100. Describe the channel mix change and distinguish order-count change from percentage-point change. Provide a short report caption without inventing chart colors, revenue or causes.A channel comparison table and a two-sentence caption with units distinguishing orders from percentage points.Check that both totals stay 100 and changes are labelled with the correct units rather than relative percent.