Grok 3 is xAI’s model family for language work, general knowledge, coding and problem solving. The launch description distinguishes the normally responding model from the family’s explicit Think variants, which use additional reasoning before the final answer. The named grok-3 entry described here is the text-chat edition: the producer lists text input, text output and no separate reasoning feature for that entry.
The family’s pretraining is intended to support a broad range of questions and instructions. xAI highlights mathematics, coding, knowledge and stylistic control in its release description. For a writing task, that gives a useful basis for asking the model to revise an explanation for a particular reader, preserve specified facts or develop a coherent draft from a set of points. For a technical assistant, provide the relevant material and state the question the answer must resolve rather than relying only on a general request to discuss the topic.
An illustrative document task is: “Compare these two descriptions of the workflow. List agreement, contradiction and missing information, then write a short explanation for a new team member.” Keep the source sections labelled so that the response can associate each observation with the right passage. A code task can include the function, expected behaviour and a concrete input where the current result is wrong. Ask for a proposed correction and explain which examples should be used to check it. These examples use the documented language and coding task families and do not imply that generated code has already been executed.
The distinction from Think is important. Grok 3’s family announcement also describes Grok 3 Think and Grok 3 mini Think, trained to devote additional work to reasoning. Their extended-thinking behaviour should be described as their own mode or model choice. The ordinary text entry can give explanations and solve questions, but that should not be confused with selecting an explicitly documented extended-reasoning configuration.
The producer’s named-model metadata example gives a maximum prompt length of 131,072 tokens for grok-3 and records support for structured outputs and function calling. The prompt-length field describes the published input budget in that example; it is not a separate output-token ceiling. The family announcement discusses a larger long-context configuration, so keep the precise named-model specification and the broader family description distinct when preparing a request. Include the context needed for the question, and determine the answer’s format and length explicitly.
Structured output is useful when a conversation should end with fields the application can process, such as a summary, extracted facts and questions that still need clarification. Function calling allows an application to offer permitted operations and receive proposed arguments. The application carries out the operation and returns the result for a subsequent answer. This is different from a model independently having access to an arbitrary database, browser or code interpreter.
The launch article discusses DeepSearch and tool-equipped agents as systems built around the Grok family. Their search, execution and report-making workflows are an integration context, rather than a reason to transfer every application feature to the bare grok-3 text entry. For a useful task, say which supplied material or returned tool data the model should use, distinguish facts from requested interpretations, and ask it to mark missing information. Finish with a concrete artifact: a revised document, a code proposal, an extraction record or an explanation that can be checked against the original inputs.
", "aboutText": "Grok 3 is xAI’s model family for language work, general knowledge, coding and problem solving. The launch description distinguishes the normally responding model from the family’s explicit Think variants, which use additional reasoning before the final answer. The named grok-3 entry described here is the text-chat edition: the producer lists text input, text output and no separate reasoning feature for that entry.\n\nThe family’s pretraining is intended to support a broad range of questions and instructions. xAI highlights mathematics, coding, knowledge and stylistic control in its release description. For a writing task, that gives a useful basis for asking the model to revise an explanation for a particular reader, preserve specified facts or develop a coherent draft from a set of points. For a technical assistant, provide the relevant material and state the question the answer must resolve rather than relying only on a general request to discuss the topic.\n\nAn illustrative document task is: “Compare these two descriptions of the workflow. List agreement, contradiction and missing information, then write a short explanation for a new team member.” Keep the source sections labelled so that the response can associate each observation with the right passage. A code task can include the function, expected behaviour and a concrete input where the current result is wrong. Ask for a proposed correction and explain which examples should be used to check it. These examples use the documented language and coding task families and do not imply that generated code has already been executed.\n\nThe distinction from Think is important. Grok 3’s family announcement also describes Grok 3 Think and Grok 3 mini Think, trained to devote additional work to reasoning. Their extended-thinking behaviour should be described as their own mode or model choice. The ordinary text entry can give explanations and solve questions, but that should not be confused with selecting an explicitly documented extended-reasoning configuration.\n\nThe producer’s named-model metadata example gives a maximum prompt length of 131,072 tokens for grok-3 and records support for structured outputs and function calling. The prompt-length field describes the published input budget in that example; it is not a separate output-token ceiling. The family announcement discusses a larger long-context configuration, so keep the precise named-model specification and the broader family description distinct when preparing a request. Include the context needed for the question, and determine the answer’s format and length explicitly.\n\nStructured output is useful when a conversation should end with fields the application can process, such as a summary, extracted facts and questions that still need clarification. Function calling allows an application to offer permitted operations and receive proposed arguments. The application carries out the operation and returns the result for a subsequent answer. This is different from a model independently having access to an arbitrary database, browser or code interpreter.\n\nThe launch article discusses DeepSearch and tool-equipped agents as systems built around the Grok family. Their search, execution and report-making workflows are an integration context, rather than a reason to transfer every application feature to the bare grok-3 text entry. For a useful task, say which supplied material or returned tool data the model should use, distinguish facts from requested interpretations, and ask it to mark missing information. Finish with a concrete artifact: a revised document, a code proposal, an extraction record or an explanation that can be checked against the original inputs.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Revise a technical explanation\n\nRewrite this for a nontechnical office manager in at most 75 words: 'The synchronisation job retries transient transport failures using exponential backoff; repeated requests carry the same operation key to prevent duplicate entries.' Preserve the difference between retrying a failed connection and creating a second record. Use one everyday comparison and no unsupported guarantees.A concise plain-language explanation with one comparison and both retry and duplicate-prevention concepts intact.The rewrite does not imply that every failure is recoverable or that retries always succeed.grok-3Grok 3 is xAI’s text-chat edition for explanations, writing, coding and questions that draw on supplied material. The named model entry supports structured outputs and function calling and is distinct from the family’s explicit Think models.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Grok 3 is xAI’s model family for language work, general knowledge, coding and problem solving. The launch description distinguishes the normally responding model from the family’s explicit Think variants, which use additional reasoning before the final answer. The named grok-3 entry described here is the text-chat edition: the producer lists text input, text output and no separate reasoning feature for that entry.
The family’s pretraining is intended to support a broad range of questions and instructions. xAI highlights mathematics, coding, knowledge and stylistic control in its release description. For a writing task, that gives a useful basis for asking the model to revise an explanation for a particular reader, preserve specified facts or develop a coherent draft from a set of points. For a technical assistant, provide the relevant material and state the question the answer must resolve rather than relying only on a general request to discuss the topic.
An illustrative document task is: “Compare these two descriptions of the workflow. List agreement, contradiction and missing information, then write a short explanation for a new team member.” Keep the source sections labelled so that the response can associate each observation with the right passage. A code task can include the function, expected behaviour and a concrete input where the current result is wrong. Ask for a proposed correction and explain which examples should be used to check it. These examples use the documented language and coding task families and do not imply that generated code has already been executed.
The distinction from Think is important. Grok 3’s family announcement also describes Grok 3 Think and Grok 3 mini Think, trained to devote additional work to reasoning. Their extended-thinking behaviour should be described as their own mode or model choice. The ordinary text entry can give explanations and solve questions, but that should not be confused with selecting an explicitly documented extended-reasoning configuration.
The producer’s named-model metadata example gives a maximum prompt length of 131,072 tokens for grok-3 and records support for structured outputs and function calling. The prompt-length field describes the published input budget in that example; it is not a separate output-token ceiling. The family announcement discusses a larger long-context configuration, so keep the precise named-model specification and the broader family description distinct when preparing a request. Include the context needed for the question, and determine the answer’s format and length explicitly.
Structured output is useful when a conversation should end with fields the application can process, such as a summary, extracted facts and questions that still need clarification. Function calling allows an application to offer permitted operations and receive proposed arguments. The application carries out the operation and returns the result for a subsequent answer. This is different from a model independently having access to an arbitrary database, browser or code interpreter.
The launch article discusses DeepSearch and tool-equipped agents as systems built around the Grok family. Their search, execution and report-making workflows are an integration context, rather than a reason to transfer every application feature to the bare grok-3 text entry. For a useful task, say which supplied material or returned tool data the model should use, distinguish facts from requested interpretations, and ask it to mark missing information. Finish with a concrete artifact: a revised document, a code proposal, an extraction record or an explanation that can be checked against the original inputs.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits grok-3 | Default— |
Fieldmessages | Typemessage[] | RequirementRequired | Values & limits Minimum items: 1 | Default— |
Fieldmessages[].role | Typestring | RequirementRequired | Values & limits Examples: system, user, assistant, tool, function Conditions: These roles are explicitly represented by Source compatibility types; the exact model role set remains model-specific. Model-specific | Default— |
Fieldmessages[].content | Typestring|content_part[]|null | RequirementOptional | Values & limits | Default— |
Fieldmessages[].tool_calls | Typetool_call[] | RequirementOptional | Values & limits | Default— |
Fieldmessages[].tool_call_id | Typestring | RequirementOptional | Values & limits Applies when: role=tool; use actual returned ID | Default— |
Fieldmessages[].name | Typestring | RequirementOptional | Values & limits | Default— |
Fieldmessages[].reasoning_content | Typestring | RequirementOptional | Values & limits Applies when: Round-trip actual returned reasoning where this model uses it | Default— |
Fieldmessages[].reasoning_details | Typeobject|array | RequirementOptional | Values & limits Model-specific | Default— |
Fieldmax_tokens | Typeinteger | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
Fieldmax_completion_tokens | Typeinteger | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
Fieldstream_options.include_usage | Typeboolean | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtemperature | Typenumber | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtop_p | Typenumber | RequirementOptional | Values & limits Model-specific | Default— |
Fieldstop | Typestring|string[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtools | Typefunction_tool[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtools[].type | Typestring | RequirementOptional | Values & limits function Model-specific | Default— |
Fieldtools[].function.name | Typestring | RequirementRequired | Values & limits Applies when: function tool supplied | Default— |
Fieldtools[].function.description | Typestring | RequirementOptional | Values & limits | Default— |
Fieldtools[].function.parameters | TypeJSON_schema | RequirementOptional | Values & limits | Default— |
Fieldtool_choice | Typestring|object | RequirementOptional | Values & limits Model-specific | Default— |
Fieldparallel_tool_calls | Typeboolean | RequirementOptional | Values & limits Model-specific | Default— |
Fieldresponse_format | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Fieldreasoning_effort | Typestring | RequirementOptional | Values & limits Model-specific | Default— |
Fieldreasoning | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Fieldservice_tier | Typestring | RequirementOptional | Values & limits Model-specific | Default— |
Fieldinstructions | Typestring | RequirementOptional | Values & limits Compatibility field | Default— |
Fieldfunctions | Typefunction[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldfunction_call | Typestring|object | RequirementOptional | Values & limits Model-specific | Default— |
Fieldprompt_cache_options | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Fieldmodalities | Typestring[] | RequirementOptional | Values & limits text | Default— |
Fieldprovider | Typeobject | RequirementOptional | Values & limits Conditions: provider.options is rejected on this Ultra text route | Default— |
Fieldcache_control.ttl | Typestring | RequirementOptional | Values & limits Conditions: 1h is rejected in actual prompt-cache locations | Default— |
Text · UTF8 text
messages[].content
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, messages |
Parametermaterial_types | Contracttext |
Parametermessages | Contractmessage array with role/content shape |
Parameterfile_material | Contractactual UTF-8 document inserted as literal text; no file ID inferred |
Parameteroptional_controls | Contractstream, temperature, top_p, stop, max_tokens, max_completion_tokens, reasoning, response_format, tools, tool_choice |
Parametercontrol_scope | Contractmodel-specific; user function tools differ from hosted tools |
Parameteroutput_modalities | Contracttext |
Parameterhosted_operations | Contractfalse |
Parametermultimodal_input_binding | Contractnull |
Lifecycle: synchronous_or_streamed
Send exact model ID with messages.
Context length is not an output cap.
A text file may supply literal text; image/audio/file-object inputs need exact binding.
Tariff references do not add request options. Supported parameters are listed for the selected method.
| Configuration | Rate schedule | Charge |
|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Charge Input · Input tokens $0.006 / 1K tokens Output · Output tokens $0.03 / 1K tokens Input · Cache read $0 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "grok-3", "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='grok-3',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='grok-3',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 grok-3
Use the method paths shown above.
grok-3Grok 3 is xAI’s text-chat edition for explanations, writing, coding and questions that draw on supplied material. The named model entry supports structured outputs and function calling and is distinct from the family’s explicit Think models.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Grok 3 is xAI’s model family for language work, general knowledge, coding and problem solving. The launch description distinguishes the normally responding model from the family’s explicit Think variants, which use additional reasoning before the final answer. The named grok-3 entry described here is the text-chat edition: the producer lists text input, text output and no separate reasoning feature for that entry.
The family’s pretraining is intended to support a broad range of questions and instructions. xAI highlights mathematics, coding, knowledge and stylistic control in its release description. For a writing task, that gives a useful basis for asking the model to revise an explanation for a particular reader, preserve specified facts or develop a coherent draft from a set of points. For a technical assistant, provide the relevant material and state the question the answer must resolve rather than relying only on a general request to discuss the topic.
An illustrative document task is: “Compare these two descriptions of the workflow. List agreement, contradiction and missing information, then write a short explanation for a new team member.” Keep the source sections labelled so that the response can associate each observation with the right passage. A code task can include the function, expected behaviour and a concrete input where the current result is wrong. Ask for a proposed correction and explain which examples should be used to check it. These examples use the documented language and coding task families and do not imply that generated code has already been executed.
The distinction from Think is important. Grok 3’s family announcement also describes Grok 3 Think and Grok 3 mini Think, trained to devote additional work to reasoning. Their extended-thinking behaviour should be described as their own mode or model choice. The ordinary text entry can give explanations and solve questions, but that should not be confused with selecting an explicitly documented extended-reasoning configuration.
The producer’s named-model metadata example gives a maximum prompt length of 131,072 tokens for grok-3 and records support for structured outputs and function calling. The prompt-length field describes the published input budget in that example; it is not a separate output-token ceiling. The family announcement discusses a larger long-context configuration, so keep the precise named-model specification and the broader family description distinct when preparing a request. Include the context needed for the question, and determine the answer’s format and length explicitly.
Structured output is useful when a conversation should end with fields the application can process, such as a summary, extracted facts and questions that still need clarification. Function calling allows an application to offer permitted operations and receive proposed arguments. The application carries out the operation and returns the result for a subsequent answer. This is different from a model independently having access to an arbitrary database, browser or code interpreter.
The launch article discusses DeepSearch and tool-equipped agents as systems built around the Grok family. Their search, execution and report-making workflows are an integration context, rather than a reason to transfer every application feature to the bare grok-3 text entry. For a useful task, say which supplied material or returned tool data the model should use, distinguish facts from requested interpretations, and ask it to mark missing information. Finish with a concrete artifact: a revised document, a code proposal, an extraction record or an explanation that can be checked against the original inputs.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits grok-3 | Default— |
Fieldmessages | Typemessage[] | RequirementRequired | Values & limits | Default— |
Fieldmessages[].role | Typestring | RequirementRequired | Values & limits user, assistant | Default— |
Fieldmessages[].content | Typestring | RequirementRequired | Values & limits | Default— |
Fieldmax_tokens | Typeinteger | RequirementRequired | Values & limits | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
Text · UTF-8 text
messages[].content string
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, messages, max_tokens |
Parameteroptional_controls | Contractstream |
Parametermaterial_types | Contracttext |
Parametertext_file_material | ContractRead the actual UTF-8 document and put its text in the indicated input or message content string. |
Lifecycle: synchronous_or_streamed
Tariff references do not add request options. Supported parameters are listed for the selected method.
| Configuration | Rate schedule | Charge |
|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Charge Input · Input tokens $0.006 / 1K tokens Output · Output tokens $0.03 / 1K tokens Input · Cache read $0 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "grok-3",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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': 'grok-3', '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': 'grok-3', '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 grok-3
Use the method paths shown above.
Technical example in English
Revise a technical explanation\n\nRewrite this for a nontechnical office manager in at most 75 words: 'The synchronisation job retries transient transport failures using exponential backoff; repeated requests carry the same operation key to prevent duplicate entries.' Preserve the difference between retrying a failed connection and creating a second record. Use one everyday comparison and no unsupported guarantees.A concise plain-language explanation with one comparison and both retry and duplicate-prevention concepts intact.The rewrite does not imply that every failure is recoverable or that retries always succeed.