Kimi K2 Thinking is Moonshot AI’s reasoning-agent edition developed from Kimi K2. It works through a task while choosing functions supplied by the surrounding application, joining intermediate analysis with tool observations before producing the final answer. Its published mixture-of-experts profile has one trillion total parameters, 32 billion active parameters and a 256K context. The documented task input and answer are text.
The manufacturer develops K2 Thinking for research, coding and writing workflows that require many steps. The defining feature is interleaving reasoning with function calls, rather than treating thinking and action as two unrelated stages. A useful task brief states the question, the sources or tools available, permitted actions and the result that marks completion.
For research, provide the criteria for a relevant source and require the conclusion to cite the evidence obtained. For coding, include the relevant implementation, failing behaviour and constraints, then request the final patch and supporting observations. An illustrative prompt is: “Use the supplied code and tool results to identify the cause, propose a focused change and distinguish completed validation from a check that still needs to run.”
K2 Thinking uses quantization-aware training during post-training, applying native INT4 weight-only quantization to mixture-of-experts components. This is a producer checkpoint distinction, not a reason to assign the model another K2 edition’s precision or modality. The native model format remains separate from how any particular application executes it.
The exact card uses the K2 Instruct tool-call settings. Supply available function names, descriptions and parameter schemas in each request. The model decides when and how to call them. The application parses the proposed arguments, executes the chosen function and returns its result in a tool message with the corresponding identifier and name. The next model step can use that observation or choose another operation.
Keep the original observations in the conversation and describe what counts as a completed result. A selected search call is not a retrieved source until the application returns it, and generated code is not a successful execution. For a structured result, check both its fields and their agreement with the supplied evidence.
The producer recommends temperature 1.0 and provides a simple assistant system instruction as a default when no special instruction is needed. Specify the final answer’s language and form separately: a concise conclusion, an analysis with source references or a code artifact. The thinking content and final response have different purposes and should remain distinguishable.
The 256K context must hold instructions, source material, conversation, reasoning and tool returns. A long tool-guided task can accumulate more context than its original question suggests. Keep the evidence relevant and preserve the required outcome through follow-ups. The card’s different evaluation thinking budgets and example completion size are not universal hard output caps.
A useful final answer connects its conclusion to the actual sources or observations and identifies information that remains unresolved. K2 Thinking is a separate text reasoning edition; image/video inputs and instant-mode or preserve-thinking controls described for later K2.5 and K2.6 releases should not be assumed from the shared family name.
", "aboutText": "Kimi K2 Thinking is Moonshot AI’s reasoning-agent edition developed from Kimi K2. It works through a task while choosing functions supplied by the surrounding application, joining intermediate analysis with tool observations before producing the final answer. Its published mixture-of-experts profile has one trillion total parameters, 32 billion active parameters and a 256K context. The documented task input and answer are text.\n\n### Deep reasoning and long tasks\n\nThe manufacturer develops K2 Thinking for research, coding and writing workflows that require many steps. The defining feature is interleaving reasoning with function calls, rather than treating thinking and action as two unrelated stages. A useful task brief states the question, the sources or tools available, permitted actions and the result that marks completion.\n\nFor research, provide the criteria for a relevant source and require the conclusion to cite the evidence obtained. For coding, include the relevant implementation, failing behaviour and constraints, then request the final patch and supporting observations. An illustrative prompt is: “Use the supplied code and tool results to identify the cause, propose a focused change and distinguish completed validation from a check that still needs to run.”\n\n### Producer checkpoint and quantization\n\nK2 Thinking uses quantization-aware training during post-training, applying native INT4 weight-only quantization to mixture-of-experts components. This is a producer checkpoint distinction, not a reason to assign the model another K2 edition’s precision or modality. The native model format remains separate from how any particular application executes it.\n\n### Tool-calling workflow\n\nThe exact card uses the K2 Instruct tool-call settings. Supply available function names, descriptions and parameter schemas in each request. The model decides when and how to call them. The application parses the proposed arguments, executes the chosen function and returns its result in a tool message with the corresponding identifier and name. The next model step can use that observation or choose another operation.\n\nKeep the original observations in the conversation and describe what counts as a completed result. A selected search call is not a retrieved source until the application returns it, and generated code is not a successful execution. For a structured result, check both its fields and their agreement with the supplied evidence.\n\n### Prompting and response budgets\n\nThe producer recommends temperature 1.0 and provides a simple assistant system instruction as a default when no special instruction is needed. Specify the final answer’s language and form separately: a concise conclusion, an analysis with source references or a code artifact. The thinking content and final response have different purposes and should remain distinguishable.\n\nThe 256K context must hold instructions, source material, conversation, reasoning and tool returns. A long tool-guided task can accumulate more context than its original question suggests. Keep the evidence relevant and preserve the required outcome through follow-ups. The card’s different evaluation thinking budgets and example completion size are not universal hard output caps.\n\nA useful final answer connects its conclusion to the actual sources or observations and identifies information that remains unresolved. K2 Thinking is a separate text reasoning edition; image/video inputs and instant-mode or preserve-thinking controls described for later K2.5 and K2.6 releases should not be assumed from the shared family name.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Continue debugging from a real observation\n\nUse this supplied development observation: a test expected rows ordered by created_at, but equal timestamps appeared in different orders across runs. Query text is 'ORDER BY created_at'. Propose a deterministic tie-breaker using the unique id field, explain its effect and specify the next test. Distinguish the reported test result from checks still proposed.A focused query change, causal explanation and a test for rows sharing the same timestamp.The revised ordering includes a unique tie-breaker, and the answer does not claim the new test has run.moonshotai/kimi-k2-thinkingKimi K2 Thinking is Moonshot AI’s text reasoning agent that interleaves analysis with function calls. Its 256K context and native INT4 producer checkpoint support multi-step research, coding and writing, with final answers grounded in the observations returned by supplied tools.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Kimi K2 Thinking is Moonshot AI’s reasoning-agent edition developed from Kimi K2. It works through a task while choosing functions supplied by the surrounding application, joining intermediate analysis with tool observations before producing the final answer. Its published mixture-of-experts profile has one trillion total parameters, 32 billion active parameters and a 256K context. The documented task input and answer are text.
The manufacturer develops K2 Thinking for research, coding and writing workflows that require many steps. The defining feature is interleaving reasoning with function calls, rather than treating thinking and action as two unrelated stages. A useful task brief states the question, the sources or tools available, permitted actions and the result that marks completion.
For research, provide the criteria for a relevant source and require the conclusion to cite the evidence obtained. For coding, include the relevant implementation, failing behaviour and constraints, then request the final patch and supporting observations. An illustrative prompt is: “Use the supplied code and tool results to identify the cause, propose a focused change and distinguish completed validation from a check that still needs to run.”
K2 Thinking uses quantization-aware training during post-training, applying native INT4 weight-only quantization to mixture-of-experts components. This is a producer checkpoint distinction, not a reason to assign the model another K2 edition’s precision or modality. The native model format remains separate from how any particular application executes it.
The exact card uses the K2 Instruct tool-call settings. Supply available function names, descriptions and parameter schemas in each request. The model decides when and how to call them. The application parses the proposed arguments, executes the chosen function and returns its result in a tool message with the corresponding identifier and name. The next model step can use that observation or choose another operation.
Keep the original observations in the conversation and describe what counts as a completed result. A selected search call is not a retrieved source until the application returns it, and generated code is not a successful execution. For a structured result, check both its fields and their agreement with the supplied evidence.
The producer recommends temperature 1.0 and provides a simple assistant system instruction as a default when no special instruction is needed. Specify the final answer’s language and form separately: a concise conclusion, an analysis with source references or a code artifact. The thinking content and final response have different purposes and should remain distinguishable.
The 256K context must hold instructions, source material, conversation, reasoning and tool returns. A long tool-guided task can accumulate more context than its original question suggests. Keep the evidence relevant and preserve the required outcome through follow-ups. The card’s different evaluation thinking budgets and example completion size are not universal hard output caps.
A useful final answer connects its conclusion to the actual sources or observations and identifies information that remains unresolved. K2 Thinking is a separate text reasoning edition; image/video inputs and instant-mode or preserve-thinking controls described for later K2.5 and K2.6 releases should not be assumed from the shared family name.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits moonshotai/kimi-k2-thinking | 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 $0.0012 / 1K tokens Output · Output tokens $0.005 / 1K tokens Input · Cache read $0.0003 / 1K tokens Input · Cache write $0 / 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 $0.0012 / 1K tokens Output · Output tokens $0.005 / 1K tokens Input · Cache read $0.0003 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "moonshotai/kimi-k2-thinking", "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='moonshotai/kimi-k2-thinking',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='moonshotai/kimi-k2-thinking',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 moonshotai/kimi-k2-thinking
Use the method paths shown above.
moonshotai/kimi-k2-thinkingKimi K2 Thinking is Moonshot AI’s text reasoning agent that interleaves analysis with function calls. Its 256K context and native INT4 producer checkpoint support multi-step research, coding and writing, with final answers grounded in the observations returned by supplied tools.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Kimi K2 Thinking is Moonshot AI’s reasoning-agent edition developed from Kimi K2. It works through a task while choosing functions supplied by the surrounding application, joining intermediate analysis with tool observations before producing the final answer. Its published mixture-of-experts profile has one trillion total parameters, 32 billion active parameters and a 256K context. The documented task input and answer are text.
The manufacturer develops K2 Thinking for research, coding and writing workflows that require many steps. The defining feature is interleaving reasoning with function calls, rather than treating thinking and action as two unrelated stages. A useful task brief states the question, the sources or tools available, permitted actions and the result that marks completion.
For research, provide the criteria for a relevant source and require the conclusion to cite the evidence obtained. For coding, include the relevant implementation, failing behaviour and constraints, then request the final patch and supporting observations. An illustrative prompt is: “Use the supplied code and tool results to identify the cause, propose a focused change and distinguish completed validation from a check that still needs to run.”
K2 Thinking uses quantization-aware training during post-training, applying native INT4 weight-only quantization to mixture-of-experts components. This is a producer checkpoint distinction, not a reason to assign the model another K2 edition’s precision or modality. The native model format remains separate from how any particular application executes it.
The exact card uses the K2 Instruct tool-call settings. Supply available function names, descriptions and parameter schemas in each request. The model decides when and how to call them. The application parses the proposed arguments, executes the chosen function and returns its result in a tool message with the corresponding identifier and name. The next model step can use that observation or choose another operation.
Keep the original observations in the conversation and describe what counts as a completed result. A selected search call is not a retrieved source until the application returns it, and generated code is not a successful execution. For a structured result, check both its fields and their agreement with the supplied evidence.
The producer recommends temperature 1.0 and provides a simple assistant system instruction as a default when no special instruction is needed. Specify the final answer’s language and form separately: a concise conclusion, an analysis with source references or a code artifact. The thinking content and final response have different purposes and should remain distinguishable.
The 256K context must hold instructions, source material, conversation, reasoning and tool returns. A long tool-guided task can accumulate more context than its original question suggests. Keep the evidence relevant and preserve the required outcome through follow-ups. The card’s different evaluation thinking budgets and example completion size are not universal hard output caps.
A useful final answer connects its conclusion to the actual sources or observations and identifies information that remains unresolved. K2 Thinking is a separate text reasoning edition; image/video inputs and instant-mode or preserve-thinking controls described for later K2.5 and K2.6 releases should not be assumed from the shared family name.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits moonshotai/kimi-k2-thinking | 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 $0.0012 / 1K tokens Output · Output tokens $0.005 / 1K tokens Input · Cache read $0.0003 / 1K tokens Input · Cache write $0 / 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 $0.0012 / 1K tokens Output · Output tokens $0.005 / 1K tokens Input · Cache read $0.0003 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "moonshotai/kimi-k2-thinking",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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': 'moonshotai/kimi-k2-thinking', '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': 'moonshotai/kimi-k2-thinking', '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 moonshotai/kimi-k2-thinking
Use the method paths shown above.
Technical example in English
Continue debugging from a real observation\n\nUse this supplied development observation: a test expected rows ordered by created_at, but equal timestamps appeared in different orders across runs. Query text is 'ORDER BY created_at'. Propose a deterministic tie-breaker using the unique id field, explain its effect and specify the next test. Distinguish the reported test result from checks still proposed.A focused query change, causal explanation and a test for rows sharing the same timestamp.The revised ordering includes a unique tie-breaker, and the answer does not claim the new test has run.