Granite 4.0 H Micro is IBM’s 3-billion-parameter long-context instruction model, fine-tuned from Granite 4.0 H Micro Base. It is the hybrid dense Micro edition, combining Mamba-2 and attention rather than the pure transformer Micro or the larger mixture-of-experts variants. The model accepts a text instruction and context and returns text, making it a compact building block for enterprise assistants and specific steps within an agent task.
The producer architecture table lists four attention layers and thirty-six Mamba-2 layers, with a 128K sequence length. The instruction model uses supervised fine-tuning, reinforcement-learning alignment and model merging. Its training material includes permissively licensed instruction data, synthetic data and human-curated examples. The hybrid structure is an edition property; it should not be substituted with the parameter or active-expert profile of another Granite model.
The maker lists twelve supported languages and tasks including summarisation, classification, extraction, question answering, retrieval-augmented generation, coding and function calls. Provide the actual source passage and describe the required operation. For extraction, define the fields and how to represent a missing value. For classification, supply the category meanings and a case that illustrates an important boundary.
An illustrative brief is: “Extract each requirement from this passage, retain its identifier and quote the sentence that establishes it.” For a summary, state the audience and the facts that must remain. For translation, identify names and technical terms that should keep their original spelling. A clear final format helps a small instruction model produce the artifact the application needs.
Granite H Micro’s card demonstrates tool definitions with function names, descriptions and parameter schemas. The model returns a function name and JSON arguments in its tool-call representation. The surrounding application executes the selected operation, checks the arguments and returns the result. A lookup task should retain that observation as the evidence used by the answer.
In a retrieval workflow, supply the relevant document material and request an answer grounded in it. Source access belongs to the application; the text model’s answer is generated from the context it receives. Keep document labels and units visible so a result can be traced back to the input.
The model supports code-related tasks and fill-in-the-middle completion. A coding brief should include the relevant implementation, observed behaviour and the behaviour to preserve. For a completion task, identify the surrounding code and the gap to fill. Ask for the resulting code artifact and an explanation tied to the constraints, then inspect the result in the actual development environment.
The 128K context includes the prompt, source, conversation and generated response together; the card does not establish an independent universal maximum answer length. The reference chat template includes a default system instruction for professional, accurate and safe responses. A requested field list or code artifact still needs its own explicit task instructions.
IBM notes that multilingual performance can differ from English because instruction training is predominantly English; a few task-relevant examples may help. It also acknowledges possible inaccurate or biased responses. Check source-derived values and generated code against the input, and return actual observations when a task needs correction. H Micro’s useful output is a focused text or code result with the exact hybrid Micro identity preserved.
", "aboutText": "Granite 4.0 H Micro is IBM’s 3-billion-parameter long-context instruction model, fine-tuned from Granite 4.0 H Micro Base. It is the hybrid dense Micro edition, combining Mamba-2 and attention rather than the pure transformer Micro or the larger mixture-of-experts variants. The model accepts a text instruction and context and returns text, making it a compact building block for enterprise assistants and specific steps within an agent task.\n\n### Model structure and training\n\nThe producer architecture table lists four attention layers and thirty-six Mamba-2 layers, with a 128K sequence length. The instruction model uses supervised fine-tuning, reinforcement-learning alignment and model merging. Its training material includes permissively licensed instruction data, synthetic data and human-curated examples. The hybrid structure is an edition property; it should not be substituted with the parameter or active-expert profile of another Granite model.\n\n### Language and focused tasks\n\nThe maker lists twelve supported languages and tasks including summarisation, classification, extraction, question answering, retrieval-augmented generation, coding and function calls. Provide the actual source passage and describe the required operation. For extraction, define the fields and how to represent a missing value. For classification, supply the category meanings and a case that illustrates an important boundary.\n\nAn illustrative brief is: “Extract each requirement from this passage, retain its identifier and quote the sentence that establishes it.” For a summary, state the audience and the facts that must remain. For translation, identify names and technical terms that should keep their original spelling. A clear final format helps a small instruction model produce the artifact the application needs.\n\n### Tools and source-grounded answers\n\nGranite H Micro’s card demonstrates tool definitions with function names, descriptions and parameter schemas. The model returns a function name and JSON arguments in its tool-call representation. The surrounding application executes the selected operation, checks the arguments and returns the result. A lookup task should retain that observation as the evidence used by the answer.\n\nIn a retrieval workflow, supply the relevant document material and request an answer grounded in it. Source access belongs to the application; the text model’s answer is generated from the context it receives. Keep document labels and units visible so a result can be traced back to the input.\n\n### Coding and completion\n\nThe model supports code-related tasks and fill-in-the-middle completion. A coding brief should include the relevant implementation, observed behaviour and the behaviour to preserve. For a completion task, identify the surrounding code and the gap to fill. Ask for the resulting code artifact and an explanation tied to the constraints, then inspect the result in the actual development environment.\n\n### Context and limitations\n\nThe 128K context includes the prompt, source, conversation and generated response together; the card does not establish an independent universal maximum answer length. The reference chat template includes a default system instruction for professional, accurate and safe responses. A requested field list or code artifact still needs its own explicit task instructions.\n\nIBM notes that multilingual performance can differ from English because instruction training is predominantly English; a few task-relevant examples may help. It also acknowledges possible inaccurate or biased responses. Check source-derived values and generated code against the input, and return actual observations when a task needs correction. H Micro’s useful output is a focused text or code result with the exact hybrid Micro identity preserved.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Extract traceable requirements\n\nExtract requirements from this passage: '[R1] Export filenames must include the report ID. [R2] Reports with no rows must still include column headings. [R3] Files are encoded as UTF-8.' Return a table with requirement ID, implementation requirement and the exact supporting sentence. Keep each requirement separate and add no implementation details absent from the source.A three-row table retaining each ID, requirement and exact source sentence.Check every extracted requirement maps one-to-one to R1, R2 or R3 without added conditions.ibm-granite/granite-4.0-h-microGranite 4.0 H Micro is IBM’s 3B hybrid Mamba-2/transformer text model for focused enterprise tasks. Its 128K context supports summarisation, extraction, questions, coding and function calls, with multilingual dialogue and fill-in-the-middle code completion.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Granite 4.0 H Micro is IBM’s 3-billion-parameter long-context instruction model, fine-tuned from Granite 4.0 H Micro Base. It is the hybrid dense Micro edition, combining Mamba-2 and attention rather than the pure transformer Micro or the larger mixture-of-experts variants. The model accepts a text instruction and context and returns text, making it a compact building block for enterprise assistants and specific steps within an agent task.
The producer architecture table lists four attention layers and thirty-six Mamba-2 layers, with a 128K sequence length. The instruction model uses supervised fine-tuning, reinforcement-learning alignment and model merging. Its training material includes permissively licensed instruction data, synthetic data and human-curated examples. The hybrid structure is an edition property; it should not be substituted with the parameter or active-expert profile of another Granite model.
The maker lists twelve supported languages and tasks including summarisation, classification, extraction, question answering, retrieval-augmented generation, coding and function calls. Provide the actual source passage and describe the required operation. For extraction, define the fields and how to represent a missing value. For classification, supply the category meanings and a case that illustrates an important boundary.
An illustrative brief is: “Extract each requirement from this passage, retain its identifier and quote the sentence that establishes it.” For a summary, state the audience and the facts that must remain. For translation, identify names and technical terms that should keep their original spelling. A clear final format helps a small instruction model produce the artifact the application needs.
Granite H Micro’s card demonstrates tool definitions with function names, descriptions and parameter schemas. The model returns a function name and JSON arguments in its tool-call representation. The surrounding application executes the selected operation, checks the arguments and returns the result. A lookup task should retain that observation as the evidence used by the answer.
In a retrieval workflow, supply the relevant document material and request an answer grounded in it. Source access belongs to the application; the text model’s answer is generated from the context it receives. Keep document labels and units visible so a result can be traced back to the input.
The model supports code-related tasks and fill-in-the-middle completion. A coding brief should include the relevant implementation, observed behaviour and the behaviour to preserve. For a completion task, identify the surrounding code and the gap to fill. Ask for the resulting code artifact and an explanation tied to the constraints, then inspect the result in the actual development environment.
The 128K context includes the prompt, source, conversation and generated response together; the card does not establish an independent universal maximum answer length. The reference chat template includes a default system instruction for professional, accurate and safe responses. A requested field list or code artifact still needs its own explicit task instructions.
IBM notes that multilingual performance can differ from English because instruction training is predominantly English; a few task-relevant examples may help. It also acknowledges possible inaccurate or biased responses. Check source-derived values and generated code against the input, and return actual observations when a task needs correction. H Micro’s useful output is a focused text or code result with the exact hybrid Micro identity preserved.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits ibm-granite/granite-4.0-h-micro | 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 $0.000034 / 1K tokens Output · Output tokens $0.000224 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationRequest-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.000034 / 1K tokens Output · Output tokens $0.000224 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "ibm-granite/granite-4.0-h-micro", "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-4.0-h-micro',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-4.0-h-micro',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-4.0-h-micro
Use the method paths shown above.
ibm-granite/granite-4.0-h-microGranite 4.0 H Micro is IBM’s 3B hybrid Mamba-2/transformer text model for focused enterprise tasks. Its 128K context supports summarisation, extraction, questions, coding and function calls, with multilingual dialogue and fill-in-the-middle code completion.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Granite 4.0 H Micro is IBM’s 3-billion-parameter long-context instruction model, fine-tuned from Granite 4.0 H Micro Base. It is the hybrid dense Micro edition, combining Mamba-2 and attention rather than the pure transformer Micro or the larger mixture-of-experts variants. The model accepts a text instruction and context and returns text, making it a compact building block for enterprise assistants and specific steps within an agent task.
The producer architecture table lists four attention layers and thirty-six Mamba-2 layers, with a 128K sequence length. The instruction model uses supervised fine-tuning, reinforcement-learning alignment and model merging. Its training material includes permissively licensed instruction data, synthetic data and human-curated examples. The hybrid structure is an edition property; it should not be substituted with the parameter or active-expert profile of another Granite model.
The maker lists twelve supported languages and tasks including summarisation, classification, extraction, question answering, retrieval-augmented generation, coding and function calls. Provide the actual source passage and describe the required operation. For extraction, define the fields and how to represent a missing value. For classification, supply the category meanings and a case that illustrates an important boundary.
An illustrative brief is: “Extract each requirement from this passage, retain its identifier and quote the sentence that establishes it.” For a summary, state the audience and the facts that must remain. For translation, identify names and technical terms that should keep their original spelling. A clear final format helps a small instruction model produce the artifact the application needs.
Granite H Micro’s card demonstrates tool definitions with function names, descriptions and parameter schemas. The model returns a function name and JSON arguments in its tool-call representation. The surrounding application executes the selected operation, checks the arguments and returns the result. A lookup task should retain that observation as the evidence used by the answer.
In a retrieval workflow, supply the relevant document material and request an answer grounded in it. Source access belongs to the application; the text model’s answer is generated from the context it receives. Keep document labels and units visible so a result can be traced back to the input.
The model supports code-related tasks and fill-in-the-middle completion. A coding brief should include the relevant implementation, observed behaviour and the behaviour to preserve. For a completion task, identify the surrounding code and the gap to fill. Ask for the resulting code artifact and an explanation tied to the constraints, then inspect the result in the actual development environment.
The 128K context includes the prompt, source, conversation and generated response together; the card does not establish an independent universal maximum answer length. The reference chat template includes a default system instruction for professional, accurate and safe responses. A requested field list or code artifact still needs its own explicit task instructions.
IBM notes that multilingual performance can differ from English because instruction training is predominantly English; a few task-relevant examples may help. It also acknowledges possible inaccurate or biased responses. Check source-derived values and generated code against the input, and return actual observations when a task needs correction. H Micro’s useful output is a focused text or code result with the exact hybrid Micro identity preserved.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits ibm-granite/granite-4.0-h-micro | 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 $0.000034 / 1K tokens Output · Output tokens $0.000224 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationRequest-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.000034 / 1K tokens Output · Output tokens $0.000224 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "ibm-granite/granite-4.0-h-micro",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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-4.0-h-micro', '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-4.0-h-micro', '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-4.0-h-micro
Use the method paths shown above.
Technical example in English
Extract traceable requirements\n\nExtract requirements from this passage: '[R1] Export filenames must include the report ID. [R2] Reports with no rows must still include column headings. [R3] Files are encoded as UTF-8.' Return a table with requirement ID, implementation requirement and the exact supporting sentence. Keep each requirement separate and add no implementation details absent from the source.A three-row table retaining each ID, requirement and exact source sentence.Check every extracted requirement maps one-to-one to R1, R2 or R3 without added conditions.