Llama 3.1 8B Instruct is Meta's eight-billion-parameter text model for multilingual dialogue and instruction-based assistants. It accepts written conversation and source material and produces text or code. It is the Instruct edition of the 8B size, distinct from its pretrained base and the family's 70B and 405B models.
Architecture, context and languages
The model uses an autoregressive Transformer architecture with grouped-query attention. The instruction-tuned family uses supervised fine-tuning and reinforcement learning with human feedback to align its conversational responses. The maker documents a 128k context for this text release; it is not the vision or long-context specification of a later Llama 4 model.
The eight officially supported languages are English, German, French, Italian, Portuguese, Hindi, Spanish and Thai. The pretraining data spans a broader collection, which differs from the languages explicitly supported by the card. State the final language and any names, variable identifiers or terms that should remain unchanged in a multilingual result.
The family is pretrained on approximately fifteen trillion tokens, with a December 2023 data cutoff. Fine-tuning includes instruction material and more than twenty-five million synthetic examples. This describes the model's training, not access to a private knowledge base or live information when a new question arrives.
Defined text operations
A support-oriented request can supply the user's message and relevant reference passages, then ask for the answer and its supporting condition. A compact record can separate the issue, information already supplied and next required step. Define the field names and missing-value handling when an application needs to process that result.
For summarization, provide the actual passage or exchange and specify the audience, length and facts to retain. Ask for the decisions or unresolved questions relevant to one topic instead of an undirected summary of unrelated material. A follow-up can request a shorter reply or a clearer explanation of one condition while preserving the same source facts.
For editing, specify the reader and tone and identify the meaning that must remain unchanged. A practical task might request a clearer message followed by a short list of alterations, or the revised message alone if it will be used directly. A classification task should supply permitted labels and the distinction between them, rather than relying on a label name to define the rule.
Code and example generation
The documented output also includes code. Supply the language, required inputs and expected result before requesting a function. For an explanation, give the existing function and a concrete input and ask which steps determine its return value. For a correction, include the observed failure and the intended behavior, retaining the interface that must stay compatible.
A useful output can separate the proposed code, its assumptions and example inputs. The application or developer performs the actual compilation, execution or repository change. Written source code is an artifact to inspect, not a completed external operation simply because the model returned it.
The family also supports using generated output for synthetic examples and distillation. A defined text request can produce variations under supplied rules and in a specified format. Preserve the rules and labels so each example can be inspected; generated examples do not independently establish a training dataset's correctness.
Conversation roles and tool use
The model card demonstrates a chat template with separate system and user messages. Define the assistant's role and response requirements in the system context, then provide the question and source material as the task. Keep relevant previous messages when asking a follow-up or supplying new evidence that changes the result.
Llama 3.1 documents multiple tool-use formats. The application describes a function, the model generates the proposed call and arguments, the application executes it and returns the result with the tool role. The next answer can then use the returned information. Keep the originating operation and result connected through the conversation.
For example, a lookup can return the current reference value missing from a passage, or a computation tool can provide the numerical result required by the explanation. A tool-enabled assistant needs those operations supplied by the environment. The model's text behavior does not itself create a connection to an external source or complete a side effect.
Practical boundaries
The maker's 128k context label should be kept with the exact 8B Instruct release and applicable configuration. The 256-token generation example is only a usage choice; the sources read do not state a separate hard maximum answer capacity. The 8B size should not inherit another member's parameter count or a separate family's named reasoning controls.
This is a text-only model. Visual input, audio understanding and speech generation require separately specified components. Define the final artifact before supplying the material: a concise reply, extracted record, revised passage, explanation or code proposal. Retain the source information needed to inspect the meaning and format of that artifact.
", "aboutText": "Llama 3.1 8B Instruct is Meta's eight-billion-parameter text model for multilingual dialogue and instruction-based assistants. It accepts written conversation and source material and produces text or code. It is the Instruct edition of the 8B size, distinct from its pretrained base and the family's 70B and 405B models.\n\nArchitecture, context and languages\n\nThe model uses an autoregressive Transformer architecture with grouped-query attention. The instruction-tuned family uses supervised fine-tuning and reinforcement learning with human feedback to align its conversational responses. The maker documents a 128k context for this text release; it is not the vision or long-context specification of a later Llama 4 model.\n\nThe eight officially supported languages are English, German, French, Italian, Portuguese, Hindi, Spanish and Thai. The pretraining data spans a broader collection, which differs from the languages explicitly supported by the card. State the final language and any names, variable identifiers or terms that should remain unchanged in a multilingual result.\n\nThe family is pretrained on approximately fifteen trillion tokens, with a December 2023 data cutoff. Fine-tuning includes instruction material and more than twenty-five million synthetic examples. This describes the model's training, not access to a private knowledge base or live information when a new question arrives.\n\nDefined text operations\n\nA support-oriented request can supply the user's message and relevant reference passages, then ask for the answer and its supporting condition. A compact record can separate the issue, information already supplied and next required step. Define the field names and missing-value handling when an application needs to process that result.\n\nFor summarization, provide the actual passage or exchange and specify the audience, length and facts to retain. Ask for the decisions or unresolved questions relevant to one topic instead of an undirected summary of unrelated material. A follow-up can request a shorter reply or a clearer explanation of one condition while preserving the same source facts.\n\nFor editing, specify the reader and tone and identify the meaning that must remain unchanged. A practical task might request a clearer message followed by a short list of alterations, or the revised message alone if it will be used directly. A classification task should supply permitted labels and the distinction between them, rather than relying on a label name to define the rule.\n\nCode and example generation\n\nThe documented output also includes code. Supply the language, required inputs and expected result before requesting a function. For an explanation, give the existing function and a concrete input and ask which steps determine its return value. For a correction, include the observed failure and the intended behavior, retaining the interface that must stay compatible.\n\nA useful output can separate the proposed code, its assumptions and example inputs. The application or developer performs the actual compilation, execution or repository change. Written source code is an artifact to inspect, not a completed external operation simply because the model returned it.\n\nThe family also supports using generated output for synthetic examples and distillation. A defined text request can produce variations under supplied rules and in a specified format. Preserve the rules and labels so each example can be inspected; generated examples do not independently establish a training dataset's correctness.\n\nConversation roles and tool use\n\nThe model card demonstrates a chat template with separate system and user messages. Define the assistant's role and response requirements in the system context, then provide the question and source material as the task. Keep relevant previous messages when asking a follow-up or supplying new evidence that changes the result.\n\nLlama 3.1 documents multiple tool-use formats. The application describes a function, the model generates the proposed call and arguments, the application executes it and returns the result with the tool role. The next answer can then use the returned information. Keep the originating operation and result connected through the conversation.\n\nFor example, a lookup can return the current reference value missing from a passage, or a computation tool can provide the numerical result required by the explanation. A tool-enabled assistant needs those operations supplied by the environment. The model's text behavior does not itself create a connection to an external source or complete a side effect.\n\nPractical boundaries\n\nThe maker's 128k context label should be kept with the exact 8B Instruct release and applicable configuration. The 256-token generation example is only a usage choice; the sources read do not state a separate hard maximum answer capacity. The 8B size should not inherit another member's parameter count or a separate family's named reasoning controls.\n\nThis is a text-only model. Visual input, audio understanding and speech generation require separately specified components. Define the final artifact before supplying the material: a concise reply, extracted record, revised passage, explanation or code proposal. Retain the source information needed to inspect the meaning and format of that artifact.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Translate a delivery notice into German\n\nTranslate this customer notice into German: 'Order BN-42 will leave our warehouse on Thursday. Delivery normally takes three business days. We will send tracking details after dispatch.' Preserve BN-42, distinguish dispatch from delivery and use a polite professional tone. Return only the translation; do not turn the normal transit time into a guaranteed arrival date.One German customer notice preserving the identifier, event sequence and qualified transit time.The translation distinguishes warehouse dispatch from delivery and retains the word's sense of a normal estimate.meta-llama/llama-3.1-8b-instructLlama 3.1 8B Instruct is Meta's smaller text instruction model for multilingual dialogue, summaries and source-conditioned answers. It has an 8B parameter size, a 128k maker context, grouped-query attention and documented tool-use formats, returning text or code.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Llama 3.1 8B Instruct is Meta's eight-billion-parameter text model for multilingual dialogue and instruction-based assistants. It accepts written conversation and source material and produces text or code. It is the Instruct edition of the 8B size, distinct from its pretrained base and the family's 70B and 405B models.
Architecture, context and languages
The model uses an autoregressive Transformer architecture with grouped-query attention. The instruction-tuned family uses supervised fine-tuning and reinforcement learning with human feedback to align its conversational responses. The maker documents a 128k context for this text release; it is not the vision or long-context specification of a later Llama 4 model.
The eight officially supported languages are English, German, French, Italian, Portuguese, Hindi, Spanish and Thai. The pretraining data spans a broader collection, which differs from the languages explicitly supported by the card. State the final language and any names, variable identifiers or terms that should remain unchanged in a multilingual result.
The family is pretrained on approximately fifteen trillion tokens, with a December 2023 data cutoff. Fine-tuning includes instruction material and more than twenty-five million synthetic examples. This describes the model's training, not access to a private knowledge base or live information when a new question arrives.
Defined text operations
A support-oriented request can supply the user's message and relevant reference passages, then ask for the answer and its supporting condition. A compact record can separate the issue, information already supplied and next required step. Define the field names and missing-value handling when an application needs to process that result.
For summarization, provide the actual passage or exchange and specify the audience, length and facts to retain. Ask for the decisions or unresolved questions relevant to one topic instead of an undirected summary of unrelated material. A follow-up can request a shorter reply or a clearer explanation of one condition while preserving the same source facts.
For editing, specify the reader and tone and identify the meaning that must remain unchanged. A practical task might request a clearer message followed by a short list of alterations, or the revised message alone if it will be used directly. A classification task should supply permitted labels and the distinction between them, rather than relying on a label name to define the rule.
Code and example generation
The documented output also includes code. Supply the language, required inputs and expected result before requesting a function. For an explanation, give the existing function and a concrete input and ask which steps determine its return value. For a correction, include the observed failure and the intended behavior, retaining the interface that must stay compatible.
A useful output can separate the proposed code, its assumptions and example inputs. The application or developer performs the actual compilation, execution or repository change. Written source code is an artifact to inspect, not a completed external operation simply because the model returned it.
The family also supports using generated output for synthetic examples and distillation. A defined text request can produce variations under supplied rules and in a specified format. Preserve the rules and labels so each example can be inspected; generated examples do not independently establish a training dataset's correctness.
Conversation roles and tool use
The model card demonstrates a chat template with separate system and user messages. Define the assistant's role and response requirements in the system context, then provide the question and source material as the task. Keep relevant previous messages when asking a follow-up or supplying new evidence that changes the result.
Llama 3.1 documents multiple tool-use formats. The application describes a function, the model generates the proposed call and arguments, the application executes it and returns the result with the tool role. The next answer can then use the returned information. Keep the originating operation and result connected through the conversation.
For example, a lookup can return the current reference value missing from a passage, or a computation tool can provide the numerical result required by the explanation. A tool-enabled assistant needs those operations supplied by the environment. The model's text behavior does not itself create a connection to an external source or complete a side effect.
Practical boundaries
The maker's 128k context label should be kept with the exact 8B Instruct release and applicable configuration. The 256-token generation example is only a usage choice; the sources read do not state a separate hard maximum answer capacity. The 8B size should not inherit another member's parameter count or a separate family's named reasoning controls.
This is a text-only model. Visual input, audio understanding and speech generation require separately specified components. Define the final artifact before supplying the material: a concise reply, extracted record, revised passage, explanation or code proposal. Retain the source information needed to inspect the meaning and format of that artifact.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits meta-llama/llama-3.1-8b-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 $0.00044 / 1K tokens Output · Output tokens $0.00044 / 1K tokens Input · Cache read $0.00044 / 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 $0.00044 / 1K tokens Output · Output tokens $0.00044 / 1K tokens Input · Cache read $0.00044 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${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-3.1-8b-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-3.1-8b-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-3.1-8b-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-3.1-8b-instruct
Use the method paths shown above.
meta-llama/llama-3.1-8b-instructLlama 3.1 8B Instruct is Meta's smaller text instruction model for multilingual dialogue, summaries and source-conditioned answers. It has an 8B parameter size, a 128k maker context, grouped-query attention and documented tool-use formats, returning text or code.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Llama 3.1 8B Instruct is Meta's eight-billion-parameter text model for multilingual dialogue and instruction-based assistants. It accepts written conversation and source material and produces text or code. It is the Instruct edition of the 8B size, distinct from its pretrained base and the family's 70B and 405B models.
Architecture, context and languages
The model uses an autoregressive Transformer architecture with grouped-query attention. The instruction-tuned family uses supervised fine-tuning and reinforcement learning with human feedback to align its conversational responses. The maker documents a 128k context for this text release; it is not the vision or long-context specification of a later Llama 4 model.
The eight officially supported languages are English, German, French, Italian, Portuguese, Hindi, Spanish and Thai. The pretraining data spans a broader collection, which differs from the languages explicitly supported by the card. State the final language and any names, variable identifiers or terms that should remain unchanged in a multilingual result.
The family is pretrained on approximately fifteen trillion tokens, with a December 2023 data cutoff. Fine-tuning includes instruction material and more than twenty-five million synthetic examples. This describes the model's training, not access to a private knowledge base or live information when a new question arrives.
Defined text operations
A support-oriented request can supply the user's message and relevant reference passages, then ask for the answer and its supporting condition. A compact record can separate the issue, information already supplied and next required step. Define the field names and missing-value handling when an application needs to process that result.
For summarization, provide the actual passage or exchange and specify the audience, length and facts to retain. Ask for the decisions or unresolved questions relevant to one topic instead of an undirected summary of unrelated material. A follow-up can request a shorter reply or a clearer explanation of one condition while preserving the same source facts.
For editing, specify the reader and tone and identify the meaning that must remain unchanged. A practical task might request a clearer message followed by a short list of alterations, or the revised message alone if it will be used directly. A classification task should supply permitted labels and the distinction between them, rather than relying on a label name to define the rule.
Code and example generation
The documented output also includes code. Supply the language, required inputs and expected result before requesting a function. For an explanation, give the existing function and a concrete input and ask which steps determine its return value. For a correction, include the observed failure and the intended behavior, retaining the interface that must stay compatible.
A useful output can separate the proposed code, its assumptions and example inputs. The application or developer performs the actual compilation, execution or repository change. Written source code is an artifact to inspect, not a completed external operation simply because the model returned it.
The family also supports using generated output for synthetic examples and distillation. A defined text request can produce variations under supplied rules and in a specified format. Preserve the rules and labels so each example can be inspected; generated examples do not independently establish a training dataset's correctness.
Conversation roles and tool use
The model card demonstrates a chat template with separate system and user messages. Define the assistant's role and response requirements in the system context, then provide the question and source material as the task. Keep relevant previous messages when asking a follow-up or supplying new evidence that changes the result.
Llama 3.1 documents multiple tool-use formats. The application describes a function, the model generates the proposed call and arguments, the application executes it and returns the result with the tool role. The next answer can then use the returned information. Keep the originating operation and result connected through the conversation.
For example, a lookup can return the current reference value missing from a passage, or a computation tool can provide the numerical result required by the explanation. A tool-enabled assistant needs those operations supplied by the environment. The model's text behavior does not itself create a connection to an external source or complete a side effect.
Practical boundaries
The maker's 128k context label should be kept with the exact 8B Instruct release and applicable configuration. The 256-token generation example is only a usage choice; the sources read do not state a separate hard maximum answer capacity. The 8B size should not inherit another member's parameter count or a separate family's named reasoning controls.
This is a text-only model. Visual input, audio understanding and speech generation require separately specified components. Define the final artifact before supplying the material: a concise reply, extracted record, revised passage, explanation or code proposal. Retain the source information needed to inspect the meaning and format of that artifact.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits meta-llama/llama-3.1-8b-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 $0.00044 / 1K tokens Output · Output tokens $0.00044 / 1K tokens Input · Cache read $0.00044 / 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 $0.00044 / 1K tokens Output · Output tokens $0.00044 / 1K tokens Input · Cache read $0.00044 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "meta-llama/llama-3.1-8b-instruct",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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-3.1-8b-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-3.1-8b-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-3.1-8b-instruct
Use the method paths shown above.
Technical example in English
Translate a delivery notice into German\n\nTranslate this customer notice into German: 'Order BN-42 will leave our warehouse on Thursday. Delivery normally takes three business days. We will send tracking details after dispatch.' Preserve BN-42, distinguish dispatch from delivery and use a polite professional tone. Return only the translation; do not turn the normal transit time into a guaranteed arrival date.One German customer notice preserving the identifier, event sequence and qualified transit time.The translation distinguishes warehouse dispatch from delivery and retains the word's sense of a normal estimate.