Kimi K2 Instruct 0711 is Moonshot AI’s original post-trained K2 text model for general-purpose chat and agent tasks. The manufacturer distinguishes it from K2 Base, which is the foundation model, and describes the instruction edition as reflex-grade without long thinking. It accepts text and generates answers, code and tool-call content, with a 128K context.
K2 is a mixture-of-experts model with one trillion total parameters and 32 billion active parameters. The maker summary uses multi-head latent attention and sparse expert routing, selecting eight of 384 experts per token with a shared expert. Pretraining uses 15.5 trillion tokens and the MuonClip optimisation approach, developed for stable training at the model’s scale.
These are properties of the original K2 family. The instruction release then supplies the behaviour used for chat, coding and autonomous problem-solving with application tools. Its identity remains distinct from the later 0905 context extension, the separate Thinking release and the multimodal K2.5 and K2.6 models.
For a question, supply the context that establishes the answer and identify the response form you need. For a coding task, include the relevant implementation, observed failure, expected behaviour and constraints to preserve. An illustrative request is: “Explain why this input fails, propose the smallest correction and return the changed function with the supporting source condition.”
For document work, name the passages and the criteria for a comparison. Ask the result to preserve proper names, field identifiers and units, and to identify information the material does not contain. The desired artifact should remain explicit through revisions rather than being replaced by broad commentary.
The original producer guide recommends temperature 0.6 and offers a simple assistant system instruction as a default when a specialised role is unnecessary. This profile produces the task response directly rather than imposing the later Thinking model’s extended interleaved reasoning contract. Set the final answer’s language, mandatory details and expected length independently of the sampling recommendation.
K2 Instruct supports functions supplied in each request with names, descriptions and parameter schemas. The model selects when and how to call them. The application parses the proposed JSON arguments and executes the selected operation; returned observations enter the conversation with the matching tool-call identifier and function name. The following response can use those actual results to answer or continue a task.
Define what each tool does and which actions are allowed. A document lookup can return the missing product field, while a development tool can return source code or an observed error. A selected operation is not evidence of execution until its result is available. Retain the observation with the task so a final conclusion can identify what supports it.
The original 128K window contains source text, conversation, tool history and generated content together. Reserve room for the answer and organise a long repository or document collection around the actual question. The model card’s example completion size does not establish a universal hard answer ceiling.
The useful result is a reviewed text, code proposal or source-based analysis. Check values against the supplied material and code in its intended application. Keep the 0711 edition’s direct instruction profile intact instead of assigning it later context, visual input or reasoning-retention features from another K2 release.
", "aboutText": "Kimi K2 Instruct 0711 is Moonshot AI’s original post-trained K2 text model for general-purpose chat and agent tasks. The manufacturer distinguishes it from K2 Base, which is the foundation model, and describes the instruction edition as reflex-grade without long thinking. It accepts text and generates answers, code and tool-call content, with a 128K context.\n\n### Architecture and training\n\nK2 is a mixture-of-experts model with one trillion total parameters and 32 billion active parameters. The maker summary uses multi-head latent attention and sparse expert routing, selecting eight of 384 experts per token with a shared expert. Pretraining uses 15.5 trillion tokens and the MuonClip optimisation approach, developed for stable training at the model’s scale.\n\nThese are properties of the original K2 family. The instruction release then supplies the behaviour used for chat, coding and autonomous problem-solving with application tools. Its identity remains distinct from the later 0905 context extension, the separate Thinking release and the multimodal K2.5 and K2.6 models.\n\n### Prepare the task\n\nFor a question, supply the context that establishes the answer and identify the response form you need. For a coding task, include the relevant implementation, observed failure, expected behaviour and constraints to preserve. An illustrative request is: “Explain why this input fails, propose the smallest correction and return the changed function with the supporting source condition.”\n\nFor document work, name the passages and the criteria for a comparison. Ask the result to preserve proper names, field identifiers and units, and to identify information the material does not contain. The desired artifact should remain explicit through revisions rather than being replaced by broad commentary.\n\n### Chat profile\n\nThe original producer guide recommends temperature 0.6 and offers a simple assistant system instruction as a default when a specialised role is unnecessary. This profile produces the task response directly rather than imposing the later Thinking model’s extended interleaved reasoning contract. Set the final answer’s language, mandatory details and expected length independently of the sampling recommendation.\n\n### Tools and observations\n\nK2 Instruct supports functions supplied in each request with names, descriptions and parameter schemas. The model selects when and how to call them. The application parses the proposed JSON arguments and executes the selected operation; returned observations enter the conversation with the matching tool-call identifier and function name. The following response can use those actual results to answer or continue a task.\n\nDefine what each tool does and which actions are allowed. A document lookup can return the missing product field, while a development tool can return source code or an observed error. A selected operation is not evidence of execution until its result is available. Retain the observation with the task so a final conclusion can identify what supports it.\n\n### Context and result review\n\nThe original 128K window contains source text, conversation, tool history and generated content together. Reserve room for the answer and organise a long repository or document collection around the actual question. The model card’s example completion size does not establish a universal hard answer ceiling.\n\nThe useful result is a reviewed text, code proposal or source-based analysis. Check values against the supplied material and code in its intended application. Keep the 0711 edition’s direct instruction profile intact instead of assigning it later context, visual input or reasoning-retention features from another K2 release.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Fix an empty-input crash\n\nFix this Python function: def first_name(names): return names[0].strip(). For an empty list it must return None; otherwise preserve the existing trimming behavior, including returning an empty string for whitespace-only input. Return a minimal implementation and tests for an empty list, a padded name and a whitespace-only name.A revised first_name function and three tests with explicit expected values.Check that only an empty list returns None and that a whitespace-only first value still returns an empty string.moonshotai/kimi-k2Kimi K2 Instruct 0711 is Moonshot AI’s original post-trained K2 text model for chat, coding and tool-guided agents. Its 128K context and reflex-grade response profile produce answers, code and selected function calls without the later K2 Thinking workflow.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Kimi K2 Instruct 0711 is Moonshot AI’s original post-trained K2 text model for general-purpose chat and agent tasks. The manufacturer distinguishes it from K2 Base, which is the foundation model, and describes the instruction edition as reflex-grade without long thinking. It accepts text and generates answers, code and tool-call content, with a 128K context.
K2 is a mixture-of-experts model with one trillion total parameters and 32 billion active parameters. The maker summary uses multi-head latent attention and sparse expert routing, selecting eight of 384 experts per token with a shared expert. Pretraining uses 15.5 trillion tokens and the MuonClip optimisation approach, developed for stable training at the model’s scale.
These are properties of the original K2 family. The instruction release then supplies the behaviour used for chat, coding and autonomous problem-solving with application tools. Its identity remains distinct from the later 0905 context extension, the separate Thinking release and the multimodal K2.5 and K2.6 models.
For a question, supply the context that establishes the answer and identify the response form you need. For a coding task, include the relevant implementation, observed failure, expected behaviour and constraints to preserve. An illustrative request is: “Explain why this input fails, propose the smallest correction and return the changed function with the supporting source condition.”
For document work, name the passages and the criteria for a comparison. Ask the result to preserve proper names, field identifiers and units, and to identify information the material does not contain. The desired artifact should remain explicit through revisions rather than being replaced by broad commentary.
The original producer guide recommends temperature 0.6 and offers a simple assistant system instruction as a default when a specialised role is unnecessary. This profile produces the task response directly rather than imposing the later Thinking model’s extended interleaved reasoning contract. Set the final answer’s language, mandatory details and expected length independently of the sampling recommendation.
K2 Instruct supports functions supplied in each request with names, descriptions and parameter schemas. The model selects when and how to call them. The application parses the proposed JSON arguments and executes the selected operation; returned observations enter the conversation with the matching tool-call identifier and function name. The following response can use those actual results to answer or continue a task.
Define what each tool does and which actions are allowed. A document lookup can return the missing product field, while a development tool can return source code or an observed error. A selected operation is not evidence of execution until its result is available. Retain the observation with the task so a final conclusion can identify what supports it.
The original 128K window contains source text, conversation, tool history and generated content together. Reserve room for the answer and organise a long repository or document collection around the actual question. The model card’s example completion size does not establish a universal hard answer ceiling.
The useful result is a reviewed text, code proposal or source-based analysis. Check values against the supplied material and code in its intended application. Keep the 0711 edition’s direct instruction profile intact instead of assigning it later context, visual input or reasoning-retention features from another K2 release.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits moonshotai/kimi-k2 | 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 $0.00114 / 1K tokens Output · Output tokens $0.0046 / 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 $0.00114 / 1K tokens Output · Output tokens $0.0046 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "moonshotai/kimi-k2", "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',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',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
Use the method paths shown above.
moonshotai/kimi-k2Kimi K2 Instruct 0711 is Moonshot AI’s original post-trained K2 text model for chat, coding and tool-guided agents. Its 128K context and reflex-grade response profile produce answers, code and selected function calls without the later K2 Thinking workflow.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Kimi K2 Instruct 0711 is Moonshot AI’s original post-trained K2 text model for general-purpose chat and agent tasks. The manufacturer distinguishes it from K2 Base, which is the foundation model, and describes the instruction edition as reflex-grade without long thinking. It accepts text and generates answers, code and tool-call content, with a 128K context.
K2 is a mixture-of-experts model with one trillion total parameters and 32 billion active parameters. The maker summary uses multi-head latent attention and sparse expert routing, selecting eight of 384 experts per token with a shared expert. Pretraining uses 15.5 trillion tokens and the MuonClip optimisation approach, developed for stable training at the model’s scale.
These are properties of the original K2 family. The instruction release then supplies the behaviour used for chat, coding and autonomous problem-solving with application tools. Its identity remains distinct from the later 0905 context extension, the separate Thinking release and the multimodal K2.5 and K2.6 models.
For a question, supply the context that establishes the answer and identify the response form you need. For a coding task, include the relevant implementation, observed failure, expected behaviour and constraints to preserve. An illustrative request is: “Explain why this input fails, propose the smallest correction and return the changed function with the supporting source condition.”
For document work, name the passages and the criteria for a comparison. Ask the result to preserve proper names, field identifiers and units, and to identify information the material does not contain. The desired artifact should remain explicit through revisions rather than being replaced by broad commentary.
The original producer guide recommends temperature 0.6 and offers a simple assistant system instruction as a default when a specialised role is unnecessary. This profile produces the task response directly rather than imposing the later Thinking model’s extended interleaved reasoning contract. Set the final answer’s language, mandatory details and expected length independently of the sampling recommendation.
K2 Instruct supports functions supplied in each request with names, descriptions and parameter schemas. The model selects when and how to call them. The application parses the proposed JSON arguments and executes the selected operation; returned observations enter the conversation with the matching tool-call identifier and function name. The following response can use those actual results to answer or continue a task.
Define what each tool does and which actions are allowed. A document lookup can return the missing product field, while a development tool can return source code or an observed error. A selected operation is not evidence of execution until its result is available. Retain the observation with the task so a final conclusion can identify what supports it.
The original 128K window contains source text, conversation, tool history and generated content together. Reserve room for the answer and organise a long repository or document collection around the actual question. The model card’s example completion size does not establish a universal hard answer ceiling.
The useful result is a reviewed text, code proposal or source-based analysis. Check values against the supplied material and code in its intended application. Keep the 0711 edition’s direct instruction profile intact instead of assigning it later context, visual input or reasoning-retention features from another K2 release.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits moonshotai/kimi-k2 | 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 $0.00114 / 1K tokens Output · Output tokens $0.0046 / 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 $0.00114 / 1K tokens Output · Output tokens $0.0046 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "moonshotai/kimi-k2",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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', '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', '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
Use the method paths shown above.
Technical example in English
Fix an empty-input crash\n\nFix this Python function: def first_name(names): return names[0].strip(). For an empty list it must return None; otherwise preserve the existing trimming behavior, including returning an empty string for whitespace-only input. Return a minimal implementation and tests for an empty list, a padded name and a whitespace-only name.A revised first_name function and three tests with explicit expected values.Check that only an empty list returns None and that a whitespace-only first value still returns an empty string.