Meta Llama 3.2 3B Instruct is an instruction-tuned text model designed for multilingual assistant conversations, retrieval-grounded work and summarization. The maker’s model table identifies a 3B class with 3.21B parameters. It accepts text and produces text or code. Its development combines model pruning and knowledge distillation with instruction tuning, creating a small model profile for focused writing and assistant tasks.
Give the model the source material, the question and the expected form of the answer. A writing-assistance request can specify the audience, tone and details that must remain. A summary can identify the sections to cover and the length or structure desired. For a short knowledge-base answer, supply the relevant passage and ask for an explanation grounded in that source.
The maker names knowledge retrieval, summarization, mobile writing assistants, query rewriting and prompt rewriting among the intended uses of the instruction-tuned text models. A retrieval application can provide the passages it found and ask the model to compose the answer. Keep the passage identifiers with the result so a reader or another component can inspect the evidence.
For query rewriting, preserve the original question and ask for a concise search formulation that retains its intent. For a document summary, ask for the main claims and the qualifications that affect them. Review the actual output for omitted conditions, changed numbers or invented information, especially when a short answer compresses a larger source.
English, German, French, Italian, Portuguese, Hindi, Spanish and Thai are the eight officially supported languages. State the desired output language and retain the spelling of names or specialist terminology that must remain unchanged. A multilingual task should carry enough source context to judge the meaning of the returned wording, rather than rely only on fluency.
The standard Llama 3.2 text checkpoint has a 128K-token context window. Use that budget for relevant source material, conversation history and the generated result. Preserve earlier decisions needed for continuation and leave space for the reply. The pretraining-data cutoff is December 2023, so later information needs evidence supplied with the task or by the surrounding retrieval application.
This is the Instruct checkpoint, prepared for assistant-like dialogue. The model card describes supervised fine-tuning and human-preference alignment, with additional distillation during development of the small models. Its use examples provide system and user messages through a chat format. A system instruction can define the role and output expectations, while the user message supplies the current task and sources.
Keep the conversation format appropriate to the selected release when using its checkpoint directly. Define the result clearly and inspect the generated response, including its relation to the supplied evidence. For a structured textual artifact, specify the fields or headings required and validate the actual output before an application consumes it; a written format request is not a guarantee that every value is correct.
The maker distinguishes the standard text model from separately published quantized Llama 3.2 text profiles. Its model table lists an 8K context for those quantized profiles, distinct from the standard 128K window. Select the model and working budget together rather than assume that every deployment labeled 3B preserves the same context allowance.
The 3B Instruct model is also separate from Llama 3.2’s larger vision models. For this text profile, prepare textual source material or text obtained by the surrounding application. Use the model for a focused answer, rewrite, summary or short code explanation. Retain the selected checkpoint, prompt and source with the result, then make a next instruction specific to the missing detail or observed error.
", "aboutText": "Meta Llama 3.2 3B Instruct is an instruction-tuned text model designed for multilingual assistant conversations, retrieval-grounded work and summarization. The maker’s model table identifies a 3B class with 3.21B parameters. It accepts text and produces text or code. Its development combines model pruning and knowledge distillation with instruction tuning, creating a small model profile for focused writing and assistant tasks.\n\n### Define a bounded textual result\n\nGive the model the source material, the question and the expected form of the answer. A writing-assistance request can specify the audience, tone and details that must remain. A summary can identify the sections to cover and the length or structure desired. For a short knowledge-base answer, supply the relevant passage and ask for an explanation grounded in that source.\n\nThe maker names knowledge retrieval, summarization, mobile writing assistants, query rewriting and prompt rewriting among the intended uses of the instruction-tuned text models. A retrieval application can provide the passages it found and ask the model to compose the answer. Keep the passage identifiers with the result so a reader or another component can inspect the evidence.\n\nFor query rewriting, preserve the original question and ask for a concise search formulation that retains its intent. For a document summary, ask for the main claims and the qualifications that affect them. Review the actual output for omitted conditions, changed numbers or invented information, especially when a short answer compresses a larger source.\n\n### Languages and context\n\nEnglish, German, French, Italian, Portuguese, Hindi, Spanish and Thai are the eight officially supported languages. State the desired output language and retain the spelling of names or specialist terminology that must remain unchanged. A multilingual task should carry enough source context to judge the meaning of the returned wording, rather than rely only on fluency.\n\nThe standard Llama 3.2 text checkpoint has a 128K-token context window. Use that budget for relevant source material, conversation history and the generated result. Preserve earlier decisions needed for continuation and leave space for the reply. The pretraining-data cutoff is December 2023, so later information needs evidence supplied with the task or by the surrounding retrieval application.\n\n### Instruction tuning and conversation format\n\nThis is the Instruct checkpoint, prepared for assistant-like dialogue. The model card describes supervised fine-tuning and human-preference alignment, with additional distillation during development of the small models. Its use examples provide system and user messages through a chat format. A system instruction can define the role and output expectations, while the user message supplies the current task and sources.\n\nKeep the conversation format appropriate to the selected release when using its checkpoint directly. Define the result clearly and inspect the generated response, including its relation to the supplied evidence. For a structured textual artifact, specify the fields or headings required and validate the actual output before an application consumes it; a written format request is not a guarantee that every value is correct.\n\n### Standard, quantized and vision profiles\n\nThe maker distinguishes the standard text model from separately published quantized Llama 3.2 text profiles. Its model table lists an 8K context for those quantized profiles, distinct from the standard 128K window. Select the model and working budget together rather than assume that every deployment labeled 3B preserves the same context allowance.\n\nThe 3B Instruct model is also separate from Llama 3.2’s larger vision models. For this text profile, prepare textual source material or text obtained by the surrounding application. Use the model for a focused answer, rewrite, summary or short code explanation. Retain the selected checkpoint, prompt and source with the result, then make a next instruction specific to the missing detail or observed error.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Rewrite a knowledge-base query\n\nRewrite this support question into one concise search query: 'I changed my work email yesterday and now the old address still gets export notifications, even though I log in with the new one.' Preserve the distinction between login identity and notification destination. Return the query and two key concepts it must retain; do not answer the question.One search query plus two retained concepts covering changed login email and stale export-notification address.The rewrite keeps the notification problem and does not collapse it into a login failure.meta-llama/llama-3.2-3b-instructMeta Llama 3.2 3B Instruct is a compact text model for multilingual chat, retrieval-grounded summaries and writing assistance. Its standard checkpoint has a 128K context; separately published quantized variants have a different working window.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Meta Llama 3.2 3B Instruct is an instruction-tuned text model designed for multilingual assistant conversations, retrieval-grounded work and summarization. The maker’s model table identifies a 3B class with 3.21B parameters. It accepts text and produces text or code. Its development combines model pruning and knowledge distillation with instruction tuning, creating a small model profile for focused writing and assistant tasks.
Give the model the source material, the question and the expected form of the answer. A writing-assistance request can specify the audience, tone and details that must remain. A summary can identify the sections to cover and the length or structure desired. For a short knowledge-base answer, supply the relevant passage and ask for an explanation grounded in that source.
The maker names knowledge retrieval, summarization, mobile writing assistants, query rewriting and prompt rewriting among the intended uses of the instruction-tuned text models. A retrieval application can provide the passages it found and ask the model to compose the answer. Keep the passage identifiers with the result so a reader or another component can inspect the evidence.
For query rewriting, preserve the original question and ask for a concise search formulation that retains its intent. For a document summary, ask for the main claims and the qualifications that affect them. Review the actual output for omitted conditions, changed numbers or invented information, especially when a short answer compresses a larger source.
English, German, French, Italian, Portuguese, Hindi, Spanish and Thai are the eight officially supported languages. State the desired output language and retain the spelling of names or specialist terminology that must remain unchanged. A multilingual task should carry enough source context to judge the meaning of the returned wording, rather than rely only on fluency.
The standard Llama 3.2 text checkpoint has a 128K-token context window. Use that budget for relevant source material, conversation history and the generated result. Preserve earlier decisions needed for continuation and leave space for the reply. The pretraining-data cutoff is December 2023, so later information needs evidence supplied with the task or by the surrounding retrieval application.
This is the Instruct checkpoint, prepared for assistant-like dialogue. The model card describes supervised fine-tuning and human-preference alignment, with additional distillation during development of the small models. Its use examples provide system and user messages through a chat format. A system instruction can define the role and output expectations, while the user message supplies the current task and sources.
Keep the conversation format appropriate to the selected release when using its checkpoint directly. Define the result clearly and inspect the generated response, including its relation to the supplied evidence. For a structured textual artifact, specify the fields or headings required and validate the actual output before an application consumes it; a written format request is not a guarantee that every value is correct.
The maker distinguishes the standard text model from separately published quantized Llama 3.2 text profiles. Its model table lists an 8K context for those quantized profiles, distinct from the standard 128K window. Select the model and working budget together rather than assume that every deployment labeled 3B preserves the same context allowance.
The 3B Instruct model is also separate from Llama 3.2’s larger vision models. For this text profile, prepare textual source material or text obtained by the surrounding application. Use the model for a focused answer, rewrite, summary or short code explanation. Retain the selected checkpoint, prompt and source with the result, then make a next instruction specific to the missing detail or observed error.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits meta-llama/llama-3.2-3b-instruct | 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 $0.0001 / 1K tokens Output · Output tokens $0.00066 / 1K tokens Input · Cache read — / 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 $0.0001 / 1K tokens Output · Output tokens $0.00066 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "meta-llama/llama-3.2-3b-instruct", "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='meta-llama/llama-3.2-3b-instruct',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='meta-llama/llama-3.2-3b-instruct',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 meta-llama/llama-3.2-3b-instruct
Use the method paths shown above.
meta-llama/llama-3.2-3b-instructMeta Llama 3.2 3B Instruct is a compact text model for multilingual chat, retrieval-grounded summaries and writing assistance. Its standard checkpoint has a 128K context; separately published quantized variants have a different working window.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Meta Llama 3.2 3B Instruct is an instruction-tuned text model designed for multilingual assistant conversations, retrieval-grounded work and summarization. The maker’s model table identifies a 3B class with 3.21B parameters. It accepts text and produces text or code. Its development combines model pruning and knowledge distillation with instruction tuning, creating a small model profile for focused writing and assistant tasks.
Give the model the source material, the question and the expected form of the answer. A writing-assistance request can specify the audience, tone and details that must remain. A summary can identify the sections to cover and the length or structure desired. For a short knowledge-base answer, supply the relevant passage and ask for an explanation grounded in that source.
The maker names knowledge retrieval, summarization, mobile writing assistants, query rewriting and prompt rewriting among the intended uses of the instruction-tuned text models. A retrieval application can provide the passages it found and ask the model to compose the answer. Keep the passage identifiers with the result so a reader or another component can inspect the evidence.
For query rewriting, preserve the original question and ask for a concise search formulation that retains its intent. For a document summary, ask for the main claims and the qualifications that affect them. Review the actual output for omitted conditions, changed numbers or invented information, especially when a short answer compresses a larger source.
English, German, French, Italian, Portuguese, Hindi, Spanish and Thai are the eight officially supported languages. State the desired output language and retain the spelling of names or specialist terminology that must remain unchanged. A multilingual task should carry enough source context to judge the meaning of the returned wording, rather than rely only on fluency.
The standard Llama 3.2 text checkpoint has a 128K-token context window. Use that budget for relevant source material, conversation history and the generated result. Preserve earlier decisions needed for continuation and leave space for the reply. The pretraining-data cutoff is December 2023, so later information needs evidence supplied with the task or by the surrounding retrieval application.
This is the Instruct checkpoint, prepared for assistant-like dialogue. The model card describes supervised fine-tuning and human-preference alignment, with additional distillation during development of the small models. Its use examples provide system and user messages through a chat format. A system instruction can define the role and output expectations, while the user message supplies the current task and sources.
Keep the conversation format appropriate to the selected release when using its checkpoint directly. Define the result clearly and inspect the generated response, including its relation to the supplied evidence. For a structured textual artifact, specify the fields or headings required and validate the actual output before an application consumes it; a written format request is not a guarantee that every value is correct.
The maker distinguishes the standard text model from separately published quantized Llama 3.2 text profiles. Its model table lists an 8K context for those quantized profiles, distinct from the standard 128K window. Select the model and working budget together rather than assume that every deployment labeled 3B preserves the same context allowance.
The 3B Instruct model is also separate from Llama 3.2’s larger vision models. For this text profile, prepare textual source material or text obtained by the surrounding application. Use the model for a focused answer, rewrite, summary or short code explanation. Retain the selected checkpoint, prompt and source with the result, then make a next instruction specific to the missing detail or observed error.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits meta-llama/llama-3.2-3b-instruct | 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 $0.0001 / 1K tokens Output · Output tokens $0.00066 / 1K tokens Input · Cache read — / 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 $0.0001 / 1K tokens Output · Output tokens $0.00066 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "meta-llama/llama-3.2-3b-instruct",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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': 'meta-llama/llama-3.2-3b-instruct', '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': 'meta-llama/llama-3.2-3b-instruct', '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 meta-llama/llama-3.2-3b-instruct
Use the method paths shown above.
Technical example in English
Rewrite a knowledge-base query\n\nRewrite this support question into one concise search query: 'I changed my work email yesterday and now the old address still gets export notifications, even though I log in with the new one.' Preserve the distinction between login identity and notification destination. Return the query and two key concepts it must retain; do not answer the question.One search query plus two retained concepts covering changed login email and stale export-notification address.The rewrite keeps the notification problem and does not collapse it into a login failure.