models

Meta: Llama Guard 4 12B

Markdown · JSON

Meta: Llama Guard 4 12B

Llama Guard 4 12B is Meta's multimodal content classifier for prompts and generated responses. It analyzes text with one or more images and returns a safe/unsafe label plus applicable hazard categories, using a dense architecture pruned from Llama 4 Scout.

About the model

This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.

Llama Guard 4 12B is Meta's natively multimodal safety classifier with 12 billion parameters. It is trained jointly on text and multiple images and generates a textual classification: safe or unsafe, with violated hazard categories when the result is unsafe. Its purpose is evaluating content in a prompt or generated response rather than acting as a general chat assistant.

Prompt and response classification

The model can classify material before it is sent to a generative model, after that model produces an answer, or at both points. These are different questions. Prompt classification evaluates the user's input, while response classification evaluates what an assistant actually wrote. A system can therefore distinguish a risky request from a response that handles the request in an acceptable way under the classifier's taxonomy.

Supply the exact content to classify with the conversation roles and relevant context. If the target is a response, retain the question that gives the response its meaning. For a mixed text-and-image input, include the images associated with that prompt rather than classifying unrelated text or one arbitrarily selected image. The classifier result is information for the application's rule or review step; it does not itself block a request or change a file.

Fourteen hazard categories

The maker aligns the classifier with the MLCommons hazard taxonomy and adds a text-only code-interpreter category. The fourteen labels cover violent crimes, non-violent crimes, sex-related crimes, child sexual exploitation, defamation, specialized advice, privacy, intellectual property, indiscriminate weapons, hate, suicide and self-harm, sexual content, elections and code interpreter abuse.

The categories use identifiers S1 through S14. S14, Code Interpreter Abuse, is specifically for text-only tool-call use cases. Keep the taxonomy identifier with the safe/unsafe result so a later application step can interpret the classification under the same category definitions. A short result is a category judgment, not a full explanation, legal determination or guarantee that every possible harm has been detected.

For an illustrative format, an unsafe classification can be followed by the applicable category identifier. Retain the original evaluated text, its source or conversation position and the returned labels together. That association lets an application distinguish the content examined from a subsequent rewritten response or a separate prompt.

Architecture and training

Llama Guard 4 has a dense early-fusion Transformer architecture, pruned from a pretrained Llama 4 Scout checkpoint. The maker removes routed experts and router layers and retains the shared dense expert, then post-trains the resulting model for content classification. It performs no additional pretraining after that pruning step. This creates a different model from Scout's mixture-of-experts chat edition.

The model shares the Llama 4 tokenizer and vision encoder and combines text-only and multimodal classification training. The maker describes multilingual data and multi-image training, with most such samples containing two to five images and an approximate three-to-one blend of text-only to multimodal data. Those are training characteristics, not hard input-count limits.

The documented multilingual scope follows the languages supported by Llama Guard 3, and the card discusses English together with French, German, Hindi, Italian, Portuguese, Spanish and Thai. A classification request should preserve the actual wording and visual context in the language being evaluated rather than replacing the content with an unrelated summary.

Preparing a useful classification result

For an input check, provide the user's message and its associated images and ask for the prompt classification in the maker's format. For an output check, provide the assistant's actual response together with the relevant prior message. A multi-image example can retain the text linking the images so the model evaluates the combined request rather than independent fragments without context.

The model card demonstrates applying the matching conversation template and decoding only the generated classification. Its ten-token generation example illustrates a short label result; that number is not a separate maximum answer capacity. Keep the requested output aligned with the classifier's purpose instead of asking it to write an ordinary conversational answer.

Specific limitations

The maker states that judgments may be limited by the model's training data, common-sense knowledge, language coverage and policy coverage. Defamation, intellectual property and election-related categories can require factual, current knowledge that the classifier may not possess. The category label should therefore retain its relationship to the content and the information available for that evaluation.

The card reports testing mostly on prompts with a few images, most often three, and notes that behavior may vary with a much larger image collection. This describes the tested scope rather than a universal three-image maximum. The model can also be susceptible to adversarial or prompt-injection content that changes its intended behavior.

Llama Guard 4's classifier role should not inherit Scout's context specification or general assistant capabilities merely because it was pruned from Scout. The card read does not give a separate hard context or output-token capacity for this classifier. Preserve the evaluated material and taxonomy labels as the practical artifact, and let the application decide the action associated with that result.

Practical task

Classify a benign library prompt

Technical example in English

Classify a benign library prompt

Classify this user prompt using Llama Guard 4's prompt-safety taxonomy: 'Summarize the public library opening hours from the notice I pasted, and list any days when it is closed.' Evaluate the quoted prompt itself, not an imagined answer. Return the documented safe or unsafe classification; include S1-S14 hazard identifiers only if applicable.

Expected result

The documented safe/unsafe label, with applicable S1-S14 identifiers only for an unsafe result.

Check the result

Check the output uses only the documented classifier labels and does not answer the library-hours question.
Ailoot Ultra · OpenAI Chat POST /v1/chat/completions meta-llama/llama-guard-4-12b

meta-llama/llama-guard-4-12b

Meta /meta-llama/llama-guard-4-12b

Overview

Llama Guard 4 12B is Meta's multimodal content classifier for prompts and generated responses. It analyzes text with one or more images and returns a safe/unsafe label plus applicable hazard categories, using a dense architecture pruned from Llama 4 Scout.

Accepted inputs
Text
Results
Text

Available in Ailoot · inputs & methods

Ailoot Ultra · OpenAI Chat POST /v1/chat/completions
Input types
text
Output types
text
Output format
json or SSE
FieldTypeRequirementValues & limitsDefault
FieldmodelTypestringRequirementRequiredValues & limits
meta-llama/llama-guard-4-12b
Default—
FieldmessagesTypemessage[]RequirementRequiredValues & limits
Minimum items: 1
Default—
Fieldmessages[].roleTypestringRequirementRequiredValues & 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[].contentTypestring|content_part[]|nullRequirementOptionalValues & limitsDefault—
Fieldmessages[].tool_callsTypetool_call[]RequirementOptionalValues & limitsDefault—
Fieldmessages[].tool_call_idTypestringRequirementOptionalValues & limits
Applies when: role=tool; use actual returned ID
Default—
Fieldmessages[].nameTypestringRequirementOptionalValues & limitsDefault—
Fieldmessages[].reasoning_contentTypestringRequirementOptionalValues & limits
Applies when: Round-trip actual returned reasoning where this model uses it
Default—
Fieldmessages[].reasoning_detailsTypeobject|arrayRequirementOptionalValues & limits
Model-specific
Default—
Fieldmax_tokensTypeintegerRequirementOptionalValues & limits
Minimum: 1
Model-specific
Default—
Fieldmax_completion_tokensTypeintegerRequirementOptionalValues & limits
Minimum: 1
Model-specific
Default—
FieldstreamTypebooleanRequirementOptionalValues & limitsDefaultfalse
Fieldstream_options.include_usageTypebooleanRequirementOptionalValues & limits
Model-specific
Default—
FieldtemperatureTypenumberRequirementOptionalValues & limits
Model-specific
Default—
Fieldtop_pTypenumberRequirementOptionalValues & limits
Model-specific
Default—
FieldstopTypestring|string[]RequirementOptionalValues & limits
Model-specific
Default—
FieldtoolsTypefunction_tool[]RequirementOptionalValues & limits
Model-specific
Default—
Fieldtools[].typeTypestringRequirementOptionalValues & limits
function
Model-specific
Default—
Fieldtools[].function.nameTypestringRequirementRequiredValues & limits
Applies when: function tool supplied
Default—
Fieldtools[].function.descriptionTypestringRequirementOptionalValues & limitsDefault—
Fieldtools[].function.parametersTypeJSON_schemaRequirementOptionalValues & limitsDefault—
Fieldtool_choiceTypestring|objectRequirementOptionalValues & limits
Model-specific
Default—
Fieldparallel_tool_callsTypebooleanRequirementOptionalValues & limits
Model-specific
Default—
Fieldresponse_formatTypeobjectRequirementOptionalValues & limits
Model-specific
Default—
Fieldreasoning_effortTypestringRequirementOptionalValues & limits
Model-specific
Default—
FieldreasoningTypeobjectRequirementOptionalValues & limits
Model-specific
Default—
Fieldservice_tierTypestringRequirementOptionalValues & limits
Model-specific
Default—
FieldinstructionsTypestringRequirementOptionalValues & limits
Compatibility field
Default—
FieldfunctionsTypefunction[]RequirementOptionalValues & limits
Model-specific
Default—
Fieldfunction_callTypestring|objectRequirementOptionalValues & limits
Model-specific
Default—
Fieldprompt_cache_optionsTypeobjectRequirementOptionalValues & limits
Model-specific
Default—
FieldmodalitiesTypestring[]RequirementOptionalValues & limits
text
Default—
FieldproviderTypeobjectRequirementOptionalValues & limits
Conditions: provider.options is rejected on this Ultra text route
Default—
Fieldcache_control.ttlTypestringRequirementOptionalValues & limits
Conditions: 1h is rejected in actual prompt-cache locations
Default—
Input material combinations

Text · UTF8 text

messages[].content

Method parameters and lifecycle
ParameterContract
Parametercontent_typeContractapplication/json
ParameterrequiredContractmodel, messages
Parametermaterial_typesContracttext
ParametermessagesContractmessage array with role/content shape
Parameterfile_materialContractactual UTF-8 document inserted as literal text; no file ID inferred
Parameteroptional_controlsContractstream, temperature, top_p, stop, max_tokens, max_completion_tokens, reasoning, response_format, tools, tool_choice
Parametercontrol_scopeContractmodel-specific; user function tools differ from hosted tools
Parameteroutput_modalitiesContracttext
Parameterhosted_operationsContractfalse
Parametermultimodal_input_bindingContractnull

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.

Pricing

Tariff references do not add request options. Supported parameters are listed for the selected method.

Fast mode
Standard rate When fast mode is selected
Flex mode
Standard rate When flex mode is selected
Maximum reasoning effort
Standard rate When maximum reasoning effort uses the default adjustment

Ailoot rates

Prices by configuration

Match each charge to the conditions shown. Use one rate for each set of alternative configurations.

ConfigurationRate scheduleContext tokens, more thanContext tokens, up to and includingCharge
ConfigurationBase token ratesRate scheduleBase rateContext tokens, more than—Context tokens, up to and includingNo upper boundCharge
Input · Input tokens $0.00036 / 1K tokens
Output · Output tokens $0.00036 / 1K tokens
Input · Cache read — / 1K tokens
Input · Cache write — / 1K tokens
Input · Cache write, 1 hour — / 1K tokens
ConfigurationRequest-length tier 1Rate schedule—Context tokens, more than0Context tokens, up to and includingNo upper boundCharge
Input · Input tokens $0.00036 / 1K tokens
Output · Output tokens $0.00036 / 1K tokens
Input · Cache read — / 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 →

Example requests

Ailoot Ultra · OpenAI Chat

curlPython SDKPython stream
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "meta-llama/llama-guard-4-12b", "messages": [{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}]}')

Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
r=json.loads(Path("result.json").read_text())
for x in r.get("choices",[]):
    if x.get("message",{}).get("content"): print(x["message"]["content"])
PY_RESULT
from openai import OpenAI
import os

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
result=client.chat.completions.create(model='meta-llama/llama-guard-4-12b',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}])
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        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
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(result.to_dict(mode="json"))
from openai import OpenAI
import os
from pathlib import Path

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        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
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

with client.chat.completions.stream(model='meta-llama/llama-guard-4-12b',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:
    with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:
        for event in stream:
            payload=event.to_dict(mode="json")
            log.write(json.dumps(payload,ensure_ascii=False)+"\n"); log.flush()
            print(json.dumps(payload,ensure_ascii=False))
    final=stream.get_final_completion()
    save_result(final.to_dict(mode="json"),"stream-result")

Receive and save results

Ailoot Ultra · OpenAI Chat

json or SSE

Keep all completed results

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.

If the original response needs checking

Keep request/response IDs and headers. No generic text job retrieval URL is supplied.

Response fields
FieldType
Fieldchoices[].indexTypeinteger
Fieldchoices[].message.contentTypestring|null
Fieldchoices[].message.tool_callsTypetool_call[]
Fieldchoices[].message.reasoning_contentTypestring
Fieldchoices[].message.reasoning_detailsTypeobject|array
Fieldchoices[].finish_reasonTypestring|null
FieldusageTypeobject
Errors and next steps
ResponseConditionNext step
Response400 · invalid_request_errorConditionInvalid required fields, material representation or parameter valueNext stepCorrect the indicated fields before a new creation request.

Aliases

Model aliases

Ailoot Ultra meta-llama/llama-guard-4-12b

Method path aliases

Use the method paths shown above.

Related caller IDs

meta-llama/llama-guard-4-12b

Ailoot Ultra · Anthropic Messages POST /v1/messages meta-llama/llama-guard-4-12b

meta-llama/llama-guard-4-12b

Meta /meta-llama/llama-guard-4-12b

Overview

Llama Guard 4 12B is Meta's multimodal content classifier for prompts and generated responses. It analyzes text with one or more images and returns a safe/unsafe label plus applicable hazard categories, using a dense architecture pruned from Llama 4 Scout.

Accepted inputs
Text
Results
json · sse

Available in Ailoot · inputs & methods

Ailoot Ultra · Anthropic Messages POST /v1/messages
Input types
text
Output types
json, sse
Output format
JSON or SSE
FieldTypeRequirementValues & limitsDefault
FieldmodelTypestringRequirementRequiredValues & limits
meta-llama/llama-guard-4-12b
Default—
FieldmessagesTypemessage[]RequirementRequiredValues & limitsDefault—
Fieldmessages[].roleTypestringRequirementRequiredValues & limits
user, assistant
Default—
Fieldmessages[].contentTypestringRequirementRequiredValues & limitsDefault—
Fieldmax_tokensTypeintegerRequirementRequiredValues & limitsDefault—
FieldstreamTypebooleanRequirementOptionalValues & limitsDefaultfalse
Input material combinations

Text · UTF-8 text

messages[].content string

Method parameters and lifecycle
ParameterContract
Parametercontent_typeContractapplication/json
ParameterrequiredContractmodel, messages, max_tokens
Parameteroptional_controlsContractstream
Parametermaterial_typesContracttext
Parametertext_file_materialContractRead the actual UTF-8 document and put its text in the indicated input or message content string.

Lifecycle: synchronous_or_streamed

Pricing

Tariff references do not add request options. Supported parameters are listed for the selected method.

Fast mode
Standard rate When fast mode is selected
Flex mode
Standard rate When flex mode is selected
Maximum reasoning effort
Standard rate When maximum reasoning effort uses the default adjustment

Ailoot rates

Prices by configuration

Match each charge to the conditions shown. Use one rate for each set of alternative configurations.

ConfigurationRate scheduleContext tokens, more thanContext tokens, up to and includingCharge
ConfigurationBase token ratesRate scheduleBase rateContext tokens, more than—Context tokens, up to and includingNo upper boundCharge
Input · Input tokens $0.00036 / 1K tokens
Output · Output tokens $0.00036 / 1K tokens
Input · Cache read — / 1K tokens
Input · Cache write — / 1K tokens
Input · Cache write, 1 hour — / 1K tokens
ConfigurationRequest-length tier 1Rate schedule—Context tokens, more than0Context tokens, up to and includingNo upper boundCharge
Input · Input tokens $0.00036 / 1K tokens
Output · Output tokens $0.00036 / 1K tokens
Input · Cache read — / 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 →

Example requests

Ailoot Ultra · Anthropic Messages

Complete minimal JSON bodycurl · use your UTF-8 documentPython · save the complete result
{
  "model": "meta-llama/llama-guard-4-12b",
  "max_tokens": 128,
  "messages": [
    {
      "role": "user",
      "content": "Summarize the incident report."
    }
  ],
  "stream": false
}
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 document}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json, os
from pathlib import Path

source_file = Path(os.environ['AILOOT_TEXT_FILE'])
if not source_file.is_file():
    raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')
text = source_file.read_text(encoding='utf-8')
if not text.strip():
    raise SystemExit('Choose a document containing text')
payload = {'model': 'meta-llama/llama-guard-4-12b', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}
payload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\n\n' + text
Path('request.json').write_text(json.dumps(payload, ensure_ascii=False), encoding='utf-8')
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \
  -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path

result = json.loads(Path('result.json').read_text(encoding='utf-8'))
print(json.dumps(result, ensure_ascii=False, indent=2))
PY_RESULT
import json, os
from pathlib import Path

source_file = Path(os.environ['AILOOT_TEXT_FILE'])
if not source_file.is_file():
    raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')
text = source_file.read_text(encoding='utf-8')
if not text.strip():
    raise SystemExit('Choose a document containing text')
payload = {'model': 'meta-llama/llama-guard-4-12b', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}
payload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\n\n' + text
from urllib.request import Request, urlopen
from urllib.error import HTTPError

api_key = os.environ['AILOOT_API_KEY']
if not api_key.strip():
    raise SystemExit('Set AILOOT_API_KEY before making a request')
headers = {'x-api-key': 'PLACEHOLDER_KEY', 'anthropic-version': '2023-06-01', 'Content-Type': 'application/json'}
headers['x-api-key'] = api_key
request = Request('https://api.ailoot.ai/v1/messages', data=json.dumps(payload, ensure_ascii=False).encode('utf-8'), headers=headers, method='POST')
try:
    with urlopen(request, timeout=120) as response:
        raw = response.read()
        Path('response-headers.txt').write_text(str(response.headers), encoding='utf-8')
except HTTPError as error:
    Path('result.json').write_bytes(error.read())
    Path('response-headers.txt').write_text(str(error.headers), encoding='utf-8')
    raise
Path('result.json').write_bytes(raw)
import json
from pathlib import Path

result = json.loads(Path('result.json').read_text(encoding='utf-8'))
print(json.dumps(result, ensure_ascii=False, indent=2))

Receive and save results

Ailoot Ultra · Anthropic Messages

JSON or SSE

Keep all completed results

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.

If the original response needs checking

Keep request/response IDs and headers. No generic text job retrieval URL is supplied.

Response fields
FieldType
FieldidTypestring
FieldmodelTypestring
Fieldcontent[]Typetext|thinking|tool_use|other content block
Fieldstop_reasonTypestring|null
FieldusageTypeobject
Errors and next steps
ResponseConditionNext step
Response400 · invalid_request_errorConditionInvalid required fields, material representation or parameter valueNext stepCorrect the indicated fields before a new creation request.

Aliases

Model aliases

Ailoot Ultra meta-llama/llama-guard-4-12b

Method path aliases

Use the method paths shown above.

Related caller IDs

meta-llama/llama-guard-4-12b

FAQ · Meta: Llama Guard 4 12B
What inputs and results are available?

POST /v1/chat/completions · meta-llama/llama-guard-4-12b: text → text

POST /v1/messages · meta-llama/llama-guard-4-12b: text → json, sse

Which fields does the request use?

POST /v1/chat/completions · meta-llama/llama-guard-4-12b: model, messages, stream, modalities, provider

POST /v1/messages · meta-llama/llama-guard-4-12b: model, messages, max_tokens, stream

What limits apply?

POST /v1/chat/completions · meta-llama/llama-guard-4-12b: messages.min_items: 1

More details

Connect Ailoot to Claude Code, OpenCode, Hermes or your own app.

The company and its project portfolio

The company and its project portfolio: millions of customers; monthly sales in the billions.

Buy tokens at a discount.

Subscription discounts for regular use. Promo codes offer up to 50% off token purchases.

Subscription
Choose a discounted plan for your regular requests.
Promo code: up to 50% off
Enter your code at checkout. The price updates to reflect the current promotion.
Spending in your history
The model, tokens and amount are recorded for each request.

Choose a subscription · View model prices

Connect the API to a product you sell.

Use Ailoot in SaaS, apps and bots under its official service offer and licence agreement. Request a reseller licence for resale.

Commercial application
Add text, image, video and audio generation to paid features in your service.
Reseller licence
Send a description of your project and how you provide access. Request written terms for use and resale.
Documents on the website
The service offer, licence agreement and data processing policy are available before you connect.

Request a reseller licence · Service offer and licence agreement