Granite 4.2 8B is IBM’s mid-size reasoning model in the Granite 4.2 family. The 8-billion-parameter dense decoder-only transformer is post-trained from Granite 4.1 8B Base for reasoning, code generation, instruction following and tool-guided work. It takes text and produces text, with an intermediate thinking block in reasoning mode and a separate final answer.
The manufacturer describes grouped-query attention, rotary position encoding, SwiGLU feed-forward layers and RMS normalisation. The model natively supports 128K context and documents a long-context extension to 512K. Those are distinct configurations: the extended figure should not replace the native setting in a task that uses the standard profile. Conversation, source material, tool results and generated content need to fit within the selected context.
Full thinking is the producer default and develops analysis before the answer. Non-thinking returns a direct answer. Low-effort mode uses a shorter reasoning process for simpler questions. The maker’s template represents these choices differently and separates content inside the thinking markers from the final conclusion.
For mathematics or code analysis, supply the complete condition, definitions and constraints, then specify the final result you need. A practical brief is: “Determine why this function fails for the supplied input, explain the responsible condition and propose a focused correction.” A routine extraction task can instead request only the required fields. Choose a mode appropriate to the task’s depth without allowing intermediate analysis to replace the requested artifact.
IBM recommends temperature 1.0 and top-p 0.95 across its reference modes and tasks. Its example generation budgets are 8,192 new tokens for thinking and 2,048 for direct responses; the card explicitly allows a larger budget for complex reasoning. These examples are configuration guidance, not independently established hard output ceilings.
The default multi-turn template strips thinking from previous assistant turns to conserve context. The producer also documents preserving it when full reasoning history is needed. Keep the final answers and useful observations clear so a follow-up can revise the relevant part without confusing an earlier intermediate thought with an accepted finding.
The model can reason about which supplied functions to call and return structured tool-call content. Define tools with meaningful names, descriptions and parameter schemas. The application executes the selected operation and returns the observation; a continuing task should use that actual result. For a coding agent, identify the permitted files and the behaviour that completes the change, then request the implementation and its supporting validation observations.
The card lists twelve tested languages. Set the answer language and preserve proper names or code identifiers. Training is primarily English with multilingual data, so performance in another language can vary; a few relevant examples can clarify the intended task and output style.
IBM notes that the model can still produce inaccurate or biased answers and that thinking content may include unpolished, intermediate ideas. Review the final response against the supplied sources, check numerical extraction and inspect code in its intended application. The useful result is an answer, code artifact or analytical record with its evidence and unresolved information made explicit, while retaining the exact 4.2 8B edition and its mode distinctions.
", "aboutText": "Granite 4.2 8B is IBM’s mid-size reasoning model in the Granite 4.2 family. The 8-billion-parameter dense decoder-only transformer is post-trained from Granite 4.1 8B Base for reasoning, code generation, instruction following and tool-guided work. It takes text and produces text, with an intermediate thinking block in reasoning mode and a separate final answer.\n\n### Model design and context\n\nThe manufacturer describes grouped-query attention, rotary position encoding, SwiGLU feed-forward layers and RMS normalisation. The model natively supports 128K context and documents a long-context extension to 512K. Those are distinct configurations: the extended figure should not replace the native setting in a task that uses the standard profile. Conversation, source material, tool results and generated content need to fit within the selected context.\n\n### Three thinking modes\n\nFull thinking is the producer default and develops analysis before the answer. Non-thinking returns a direct answer. Low-effort mode uses a shorter reasoning process for simpler questions. The maker’s template represents these choices differently and separates content inside the thinking markers from the final conclusion.\n\nFor mathematics or code analysis, supply the complete condition, definitions and constraints, then specify the final result you need. A practical brief is: “Determine why this function fails for the supplied input, explain the responsible condition and propose a focused correction.” A routine extraction task can instead request only the required fields. Choose a mode appropriate to the task’s depth without allowing intermediate analysis to replace the requested artifact.\n\n### Conversation and generation guidance\n\nIBM recommends temperature 1.0 and top-p 0.95 across its reference modes and tasks. Its example generation budgets are 8,192 new tokens for thinking and 2,048 for direct responses; the card explicitly allows a larger budget for complex reasoning. These examples are configuration guidance, not independently established hard output ceilings.\n\nThe default multi-turn template strips thinking from previous assistant turns to conserve context. The producer also documents preserving it when full reasoning history is needed. Keep the final answers and useful observations clear so a follow-up can revise the relevant part without confusing an earlier intermediate thought with an accepted finding.\n\n### Tool calling and practical artifacts\n\nThe model can reason about which supplied functions to call and return structured tool-call content. Define tools with meaningful names, descriptions and parameter schemas. The application executes the selected operation and returns the observation; a continuing task should use that actual result. For a coding agent, identify the permitted files and the behaviour that completes the change, then request the implementation and its supporting validation observations.\n\nThe card lists twelve tested languages. Set the answer language and preserve proper names or code identifiers. Training is primarily English with multilingual data, so performance in another language can vary; a few relevant examples can clarify the intended task and output style.\n\n### Limits and interpretation\n\nIBM notes that the model can still produce inaccurate or biased answers and that thinking content may include unpolished, intermediate ideas. Review the final response against the supplied sources, check numerical extraction and inspect code in its intended application. The useful result is an answer, code artifact or analytical record with its evidence and unresolved information made explicit, while retaining the exact 4.2 8B edition and its mode distinctions.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Fix a mutable default argument\n\nExplain why this Python function shares results across calls and propose a correction: def collect(value, items=[]): items.append(value); return items. The caller may supply an existing list and expects it to be updated. Include tests for two omitted-list calls and one explicitly supplied list. Preserve the function name and calling convention.A corrected collect function, a brief cause explanation and tests distinguishing default-list isolation from explicit-list mutation.Check that omitted-list calls return independent lists while an explicitly supplied list is still updated.ibm-granite/granite-4.2-8bGranite 4.2 8B is IBM’s dense reasoning text model for mathematics, coding, multilingual dialogue and tool-guided agents. It offers full, direct and low-effort response modes, with a native 128K context and a separately documented long-context extension.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Granite 4.2 8B is IBM’s mid-size reasoning model in the Granite 4.2 family. The 8-billion-parameter dense decoder-only transformer is post-trained from Granite 4.1 8B Base for reasoning, code generation, instruction following and tool-guided work. It takes text and produces text, with an intermediate thinking block in reasoning mode and a separate final answer.
The manufacturer describes grouped-query attention, rotary position encoding, SwiGLU feed-forward layers and RMS normalisation. The model natively supports 128K context and documents a long-context extension to 512K. Those are distinct configurations: the extended figure should not replace the native setting in a task that uses the standard profile. Conversation, source material, tool results and generated content need to fit within the selected context.
Full thinking is the producer default and develops analysis before the answer. Non-thinking returns a direct answer. Low-effort mode uses a shorter reasoning process for simpler questions. The maker’s template represents these choices differently and separates content inside the thinking markers from the final conclusion.
For mathematics or code analysis, supply the complete condition, definitions and constraints, then specify the final result you need. A practical brief is: “Determine why this function fails for the supplied input, explain the responsible condition and propose a focused correction.” A routine extraction task can instead request only the required fields. Choose a mode appropriate to the task’s depth without allowing intermediate analysis to replace the requested artifact.
IBM recommends temperature 1.0 and top-p 0.95 across its reference modes and tasks. Its example generation budgets are 8,192 new tokens for thinking and 2,048 for direct responses; the card explicitly allows a larger budget for complex reasoning. These examples are configuration guidance, not independently established hard output ceilings.
The default multi-turn template strips thinking from previous assistant turns to conserve context. The producer also documents preserving it when full reasoning history is needed. Keep the final answers and useful observations clear so a follow-up can revise the relevant part without confusing an earlier intermediate thought with an accepted finding.
The model can reason about which supplied functions to call and return structured tool-call content. Define tools with meaningful names, descriptions and parameter schemas. The application executes the selected operation and returns the observation; a continuing task should use that actual result. For a coding agent, identify the permitted files and the behaviour that completes the change, then request the implementation and its supporting validation observations.
The card lists twelve tested languages. Set the answer language and preserve proper names or code identifiers. Training is primarily English with multilingual data, so performance in another language can vary; a few relevant examples can clarify the intended task and output style.
IBM notes that the model can still produce inaccurate or biased answers and that thinking content may include unpolished, intermediate ideas. Review the final response against the supplied sources, check numerical extraction and inspect code in its intended application. The useful result is an answer, code artifact or analytical record with its evidence and unresolved information made explicit, while retaining the exact 4.2 8B edition and its mode distinctions.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits ibm-granite/granite-4.2-8b | 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 $0.0002 / 1K tokens Output · Output tokens $0.0003 / 1K tokens Input · Cache read $0.0001 / 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 $0.0002 / 1K tokens Output · Output tokens $0.0003 / 1K tokens Input · Cache read $0.0001 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "ibm-granite/granite-4.2-8b", "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='ibm-granite/granite-4.2-8b',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='ibm-granite/granite-4.2-8b',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 ibm-granite/granite-4.2-8b
Use the method paths shown above.
ibm-granite/granite-4.2-8bGranite 4.2 8B is IBM’s dense reasoning text model for mathematics, coding, multilingual dialogue and tool-guided agents. It offers full, direct and low-effort response modes, with a native 128K context and a separately documented long-context extension.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Granite 4.2 8B is IBM’s mid-size reasoning model in the Granite 4.2 family. The 8-billion-parameter dense decoder-only transformer is post-trained from Granite 4.1 8B Base for reasoning, code generation, instruction following and tool-guided work. It takes text and produces text, with an intermediate thinking block in reasoning mode and a separate final answer.
The manufacturer describes grouped-query attention, rotary position encoding, SwiGLU feed-forward layers and RMS normalisation. The model natively supports 128K context and documents a long-context extension to 512K. Those are distinct configurations: the extended figure should not replace the native setting in a task that uses the standard profile. Conversation, source material, tool results and generated content need to fit within the selected context.
Full thinking is the producer default and develops analysis before the answer. Non-thinking returns a direct answer. Low-effort mode uses a shorter reasoning process for simpler questions. The maker’s template represents these choices differently and separates content inside the thinking markers from the final conclusion.
For mathematics or code analysis, supply the complete condition, definitions and constraints, then specify the final result you need. A practical brief is: “Determine why this function fails for the supplied input, explain the responsible condition and propose a focused correction.” A routine extraction task can instead request only the required fields. Choose a mode appropriate to the task’s depth without allowing intermediate analysis to replace the requested artifact.
IBM recommends temperature 1.0 and top-p 0.95 across its reference modes and tasks. Its example generation budgets are 8,192 new tokens for thinking and 2,048 for direct responses; the card explicitly allows a larger budget for complex reasoning. These examples are configuration guidance, not independently established hard output ceilings.
The default multi-turn template strips thinking from previous assistant turns to conserve context. The producer also documents preserving it when full reasoning history is needed. Keep the final answers and useful observations clear so a follow-up can revise the relevant part without confusing an earlier intermediate thought with an accepted finding.
The model can reason about which supplied functions to call and return structured tool-call content. Define tools with meaningful names, descriptions and parameter schemas. The application executes the selected operation and returns the observation; a continuing task should use that actual result. For a coding agent, identify the permitted files and the behaviour that completes the change, then request the implementation and its supporting validation observations.
The card lists twelve tested languages. Set the answer language and preserve proper names or code identifiers. Training is primarily English with multilingual data, so performance in another language can vary; a few relevant examples can clarify the intended task and output style.
IBM notes that the model can still produce inaccurate or biased answers and that thinking content may include unpolished, intermediate ideas. Review the final response against the supplied sources, check numerical extraction and inspect code in its intended application. The useful result is an answer, code artifact or analytical record with its evidence and unresolved information made explicit, while retaining the exact 4.2 8B edition and its mode distinctions.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits ibm-granite/granite-4.2-8b | 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 $0.0002 / 1K tokens Output · Output tokens $0.0003 / 1K tokens Input · Cache read $0.0001 / 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 $0.0002 / 1K tokens Output · Output tokens $0.0003 / 1K tokens Input · Cache read $0.0001 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "ibm-granite/granite-4.2-8b",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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': 'ibm-granite/granite-4.2-8b', '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': 'ibm-granite/granite-4.2-8b', '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 ibm-granite/granite-4.2-8b
Use the method paths shown above.
Technical example in English
Fix a mutable default argument\n\nExplain why this Python function shares results across calls and propose a correction: def collect(value, items=[]): items.append(value); return items. The caller may supply an existing list and expects it to be updated. Include tests for two omitted-list calls and one explicitly supplied list. Preserve the function name and calling convention.A corrected collect function, a brief cause explanation and tests distinguishing default-list isolation from explicit-list mutation.Check that omitted-list calls return independent lists while an explicitly supplied list is still updated.