Inkling is Thinking Machines Lab’s large general-purpose multimodal model. Its official specification has 975 billion total parameters and 41B active parameters. It accepts text, images and audio and generates UTF-8 text for conversation, coding, instruction-based tasks, retrieval-augmented work and tool-connected applications. It remains distinct from Inkling-Small and separately customized checkpoints.
The model uses 66 decoder layers, with each token routed to six of 256 experts plus two shared experts. Local and global attention are combined. The producer’s release describes pretraining on 45 trillion tokens spanning text, images, audio and video, with further data processing and post-training. Separate BF16 and NVFP4 releases are distinct precision artifacts.
The model supports up to a 1M context, while the producer’s training service offers 64K and 256K configurations. Input and output need to fit the context used for the task, with space for reasoning as well as the final answer. A long-context assignment should identify the question and the material that affects it instead of treating all available text as equally important.
Thinking effort is continuous in the manufacturer’s renderer: a finite value from 0.0 up to, but not including, 1.0. Named starting points map none to 0.0, minimal to 0.1, low to 0.2, medium to 0.7, high to 0.9 and xhigh to 0.99; the renderer defaults to high. Zero encourages no reasoning without enforcing a hard prohibition. Effort and generation length are separate controls, so thinking must leave room for the final answer.
For images, the card recommends dimensions ideally between 40 and 4096 pixels. Audio should be WAV at 16 kHz and ideally shorter than twenty minutes. These are optimal-input recommendations. Supply the image or recording with a clear question and any vocabulary or background needed to interpret it. The text output can explain the material or organize the relevant findings; it is not generated speech or video.
For code or an agent task, provide the source, the objective and the observations from current checks. The model proposes tool interactions, and the application executes them and returns results. Preserve that history so follow-up steps use the actual evidence. A useful final artifact states the proposed change or conclusion and what still needs an observation to establish it.
The producer releases Inkling for research and customization and documents multimodal safety evaluations and remaining limitations, including uneven language coverage and degradation in long conversations. Keep a customized model separate from its original checkpoint, and evaluate the actual text or code against the task’s evidence and requirements.
", "aboutText": "Inkling is Thinking Machines Lab’s large general-purpose multimodal model. Its official specification has 975 billion total parameters and 41B active parameters. It accepts text, images and audio and generates UTF-8 text for conversation, coding, instruction-based tasks, retrieval-augmented work and tool-connected applications. It remains distinct from Inkling-Small and separately customized checkpoints.\n\nThe model uses 66 decoder layers, with each token routed to six of 256 experts plus two shared experts. Local and global attention are combined. The producer’s release describes pretraining on 45 trillion tokens spanning text, images, audio and video, with further data processing and post-training. Separate BF16 and NVFP4 releases are distinct precision artifacts.\n\nThe model supports up to a 1M context, while the producer’s training service offers 64K and 256K configurations. Input and output need to fit the context used for the task, with space for reasoning as well as the final answer. A long-context assignment should identify the question and the material that affects it instead of treating all available text as equally important.\n\nThinking effort is continuous in the manufacturer’s renderer: a finite value from 0.0 up to, but not including, 1.0. Named starting points map none to 0.0, minimal to 0.1, low to 0.2, medium to 0.7, high to 0.9 and xhigh to 0.99; the renderer defaults to high. Zero encourages no reasoning without enforcing a hard prohibition. Effort and generation length are separate controls, so thinking must leave room for the final answer.\n\nFor images, the card recommends dimensions ideally between 40 and 4096 pixels. Audio should be WAV at 16 kHz and ideally shorter than twenty minutes. These are optimal-input recommendations. Supply the image or recording with a clear question and any vocabulary or background needed to interpret it. The text output can explain the material or organize the relevant findings; it is not generated speech or video.\n\nFor code or an agent task, provide the source, the objective and the observations from current checks. The model proposes tool interactions, and the application executes them and returns results. Preserve that history so follow-up steps use the actual evidence. A useful final artifact states the proposed change or conclusion and what still needs an observation to establish it.\n\nThe producer releases Inkling for research and customization and documents multimodal safety evaluations and remaining limitations, including uneven language coverage and degradation in long conversations. Keep a customized model separate from its original checkpoint, and evaluate the actual text or code against the task’s evidence and requirements.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Assess a code proposal from a check result\n\nReview this Python proposal and supplied check: def normalize(name): return name.strip().lower(). Requirement: preserve letter case but remove surrounding spaces. Check result C1: normalize(' Ada ') returned 'ada', expected 'Ada'. Return the smallest proposed correction, cite C1 and add a second boundary test. Do not claim that you ran either test.A focused code correction and two source-connected test cases, with execution status explicit.The proposal must remove the lowercasing while preserving whitespace trimming.thinkingmachines/inklingThinking Machines Lab’s Inkling is a 975B MoE model with 41B active parameters for text, image and audio reasoning. It generates text, supports tool-oriented and coding applications, and exposes continuous thinking effort with a 1M model context.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Inkling is Thinking Machines Lab’s large general-purpose multimodal model. Its official specification has 975 billion total parameters and 41B active parameters. It accepts text, images and audio and generates UTF-8 text for conversation, coding, instruction-based tasks, retrieval-augmented work and tool-connected applications. It remains distinct from Inkling-Small and separately customized checkpoints.
The model uses 66 decoder layers, with each token routed to six of 256 experts plus two shared experts. Local and global attention are combined. The producer’s release describes pretraining on 45 trillion tokens spanning text, images, audio and video, with further data processing and post-training. Separate BF16 and NVFP4 releases are distinct precision artifacts.
The model supports up to a 1M context, while the producer’s training service offers 64K and 256K configurations. Input and output need to fit the context used for the task, with space for reasoning as well as the final answer. A long-context assignment should identify the question and the material that affects it instead of treating all available text as equally important.
Thinking effort is continuous in the manufacturer’s renderer: a finite value from 0.0 up to, but not including, 1.0. Named starting points map none to 0.0, minimal to 0.1, low to 0.2, medium to 0.7, high to 0.9 and xhigh to 0.99; the renderer defaults to high. Zero encourages no reasoning without enforcing a hard prohibition. Effort and generation length are separate controls, so thinking must leave room for the final answer.
For images, the card recommends dimensions ideally between 40 and 4096 pixels. Audio should be WAV at 16 kHz and ideally shorter than twenty minutes. These are optimal-input recommendations. Supply the image or recording with a clear question and any vocabulary or background needed to interpret it. The text output can explain the material or organize the relevant findings; it is not generated speech or video.
For code or an agent task, provide the source, the objective and the observations from current checks. The model proposes tool interactions, and the application executes them and returns results. Preserve that history so follow-up steps use the actual evidence. A useful final artifact states the proposed change or conclusion and what still needs an observation to establish it.
The producer releases Inkling for research and customization and documents multimodal safety evaluations and remaining limitations, including uneven language coverage and degradation in long conversations. Keep a customized model separate from its original checkpoint, and evaluate the actual text or code against the task’s evidence and requirements.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits thinkingmachines/inkling | 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 $0.0019 / 1K tokens Output · Output tokens $0.0081 / 1K tokens Input · Cache read $0.00032 / 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 $0.0019 / 1K tokens Output · Output tokens $0.0081 / 1K tokens Input · Cache read $0.00032 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "thinkingmachines/inkling", "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='thinkingmachines/inkling',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='thinkingmachines/inkling',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 thinkingmachines/inkling
Use the method paths shown above.
thinkingmachines/inklingThinking Machines Lab’s Inkling is a 975B MoE model with 41B active parameters for text, image and audio reasoning. It generates text, supports tool-oriented and coding applications, and exposes continuous thinking effort with a 1M model context.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Inkling is Thinking Machines Lab’s large general-purpose multimodal model. Its official specification has 975 billion total parameters and 41B active parameters. It accepts text, images and audio and generates UTF-8 text for conversation, coding, instruction-based tasks, retrieval-augmented work and tool-connected applications. It remains distinct from Inkling-Small and separately customized checkpoints.
The model uses 66 decoder layers, with each token routed to six of 256 experts plus two shared experts. Local and global attention are combined. The producer’s release describes pretraining on 45 trillion tokens spanning text, images, audio and video, with further data processing and post-training. Separate BF16 and NVFP4 releases are distinct precision artifacts.
The model supports up to a 1M context, while the producer’s training service offers 64K and 256K configurations. Input and output need to fit the context used for the task, with space for reasoning as well as the final answer. A long-context assignment should identify the question and the material that affects it instead of treating all available text as equally important.
Thinking effort is continuous in the manufacturer’s renderer: a finite value from 0.0 up to, but not including, 1.0. Named starting points map none to 0.0, minimal to 0.1, low to 0.2, medium to 0.7, high to 0.9 and xhigh to 0.99; the renderer defaults to high. Zero encourages no reasoning without enforcing a hard prohibition. Effort and generation length are separate controls, so thinking must leave room for the final answer.
For images, the card recommends dimensions ideally between 40 and 4096 pixels. Audio should be WAV at 16 kHz and ideally shorter than twenty minutes. These are optimal-input recommendations. Supply the image or recording with a clear question and any vocabulary or background needed to interpret it. The text output can explain the material or organize the relevant findings; it is not generated speech or video.
For code or an agent task, provide the source, the objective and the observations from current checks. The model proposes tool interactions, and the application executes them and returns results. Preserve that history so follow-up steps use the actual evidence. A useful final artifact states the proposed change or conclusion and what still needs an observation to establish it.
The producer releases Inkling for research and customization and documents multimodal safety evaluations and remaining limitations, including uneven language coverage and degradation in long conversations. Keep a customized model separate from its original checkpoint, and evaluate the actual text or code against the task’s evidence and requirements.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits thinkingmachines/inkling | 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 $0.0019 / 1K tokens Output · Output tokens $0.0081 / 1K tokens Input · Cache read $0.00032 / 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 $0.0019 / 1K tokens Output · Output tokens $0.0081 / 1K tokens Input · Cache read $0.00032 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "thinkingmachines/inkling",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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': 'thinkingmachines/inkling', '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': 'thinkingmachines/inkling', '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 thinkingmachines/inkling
Use the method paths shown above.
Technical example in English
Assess a code proposal from a check result\n\nReview this Python proposal and supplied check: def normalize(name): return name.strip().lower(). Requirement: preserve letter case but remove surrounding spaces. Check result C1: normalize(' Ada ') returned 'ada', expected 'Ada'. Return the smallest proposed correction, cite C1 and add a second boundary test. Do not claim that you ran either test.A focused code correction and two source-connected test cases, with execution status explicit.The proposal must remove the lowercasing while preserving whitespace trimming.