Kimi K2 Instruct 0905 is Moonshot AI’s September instruction-model update to Kimi K2. It is a text model for knowledge, reasoning, coding and tool-guided tasks, with one trillion total mixture-of-experts parameters and 32 billion active parameters. The exact 0905 edition improves agentic coding and frontend work and extends the context from the original release’s 128K to 256K tokens.
The manufacturer emphasises both the practical behaviour and appearance of frontend code, alongside improvements in real-world coding-agent tasks. Prepare a software brief with the relevant implementation, observed behaviour and the requirements it must satisfy. For an interface, identify the content, visible states and interactions, as well as the design features that matter. A useful result is code tied to those criteria rather than a general discussion of how an interface could work.
An illustrative instruction is: “Update this component to match the described form flow, preserve existing field names and explain the required error and success states.” For debugging, provide a representative input and ask the model to identify the first incorrect condition before returning a focused patch. Feed actual rendered or validation observations into the next revision.
The 0905 summary describes multi-head latent attention and a sparse mixture of experts, selecting eight of 384 experts per token alongside a shared expert. The 256K context supports a larger task record than the original K2 edition, while still containing the source, conversation, tool observations and generated answer together. A larger window should not be read as an independent maximum output allowance.
Organise repository excerpts by file and document material by section. State the final artifact and conditions that must remain unchanged through follow-ups. For a comparison, request the passage or code fragment supporting each conclusion. Keep the selected 0905 identity when the extended context and coding update are important to the task.
The maker recommends temperature 0.6 and provides a simple assistant system instruction for tasks that do not need a specialised role. Define the answer language and form separately, such as an explanation, a source-backed comparison or code only. This keeps the desired final result visible even when the application uses several model steps.
The exact card documents available tools supplied in each request. Functions have names, descriptions and parameter schemas; the model decides when and how to call them. The application parses the selected JSON arguments, performs the operation and returns a tool result associated with the call identifier. The next response can then use the actual observation or continue the task.
A generated patch, chosen operation or search plan is a proposal until the surrounding application performs it. Keep the result of that operation as the evidence for the next step and the final handoff. Check extracted values against source material and code against the requested behaviour.
K2 Instruct 0905 remains separate from K2 Thinking and the later multimodal K2.5 and K2.6 editions. Their image/video inputs, native INT4 thinking-checkpoint properties and preserve-thinking controls should not be inferred for this named text update. The useful output is a focused text or code artifact grounded in the task and the observations actually returned.
", "aboutText": "Kimi K2 Instruct 0905 is Moonshot AI’s September instruction-model update to Kimi K2. It is a text model for knowledge, reasoning, coding and tool-guided tasks, with one trillion total mixture-of-experts parameters and 32 billion active parameters. The exact 0905 edition improves agentic coding and frontend work and extends the context from the original release’s 128K to 256K tokens.\n\n### What changes in this edition\n\nThe manufacturer emphasises both the practical behaviour and appearance of frontend code, alongside improvements in real-world coding-agent tasks. Prepare a software brief with the relevant implementation, observed behaviour and the requirements it must satisfy. For an interface, identify the content, visible states and interactions, as well as the design features that matter. A useful result is code tied to those criteria rather than a general discussion of how an interface could work.\n\nAn illustrative instruction is: “Update this component to match the described form flow, preserve existing field names and explain the required error and success states.” For debugging, provide a representative input and ask the model to identify the first incorrect condition before returning a focused patch. Feed actual rendered or validation observations into the next revision.\n\n### Model profile and long context\n\nThe 0905 summary describes multi-head latent attention and a sparse mixture of experts, selecting eight of 384 experts per token alongside a shared expert. The 256K context supports a larger task record than the original K2 edition, while still containing the source, conversation, tool observations and generated answer together. A larger window should not be read as an independent maximum output allowance.\n\nOrganise repository excerpts by file and document material by section. State the final artifact and conditions that must remain unchanged through follow-ups. For a comparison, request the passage or code fragment supporting each conclusion. Keep the selected 0905 identity when the extended context and coding update are important to the task.\n\n### Chat and function calling\n\nThe maker recommends temperature 0.6 and provides a simple assistant system instruction for tasks that do not need a specialised role. Define the answer language and form separately, such as an explanation, a source-backed comparison or code only. This keeps the desired final result visible even when the application uses several model steps.\n\nThe exact card documents available tools supplied in each request. Functions have names, descriptions and parameter schemas; the model decides when and how to call them. The application parses the selected JSON arguments, performs the operation and returns a tool result associated with the call identifier. The next response can then use the actual observation or continue the task.\n\n### Reviewable results\n\nA generated patch, chosen operation or search plan is a proposal until the surrounding application performs it. Keep the result of that operation as the evidence for the next step and the final handoff. Check extracted values against source material and code against the requested behaviour.\n\nK2 Instruct 0905 remains separate from K2 Thinking and the later multimodal K2.5 and K2.6 editions. Their image/video inputs, native INT4 thinking-checkpoint properties and preserve-thinking controls should not be inferred for this named text update. The useful output is a focused text or code artifact grounded in the task and the observations actually returned.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Specify an accessible form correction\n\nPropose a focused HTML change for this form: <input id="email"><span>Email required</span><button>Send</button>. Requirements: a visible label must name the field, the error must be programmatically associated and the button must submit the form. Return the revised fragment and checks for label association and error text, preserving the email field ID.A revised HTML form fragment and two focused accessibility checks, with email still the field ID.Inspect label for/id and the error association; do not describe keyboard or screen-reader checks as already executed.moonshotai/kimi-k2-0905Kimi K2 Instruct 0905 is Moonshot AI’s updated text model for coding, frontend implementation and agents. It extends the original K2 context from 128K to 256K and returns answers, code and function-call content based on the task and observations supplied by the application.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Kimi K2 Instruct 0905 is Moonshot AI’s September instruction-model update to Kimi K2. It is a text model for knowledge, reasoning, coding and tool-guided tasks, with one trillion total mixture-of-experts parameters and 32 billion active parameters. The exact 0905 edition improves agentic coding and frontend work and extends the context from the original release’s 128K to 256K tokens.
The manufacturer emphasises both the practical behaviour and appearance of frontend code, alongside improvements in real-world coding-agent tasks. Prepare a software brief with the relevant implementation, observed behaviour and the requirements it must satisfy. For an interface, identify the content, visible states and interactions, as well as the design features that matter. A useful result is code tied to those criteria rather than a general discussion of how an interface could work.
An illustrative instruction is: “Update this component to match the described form flow, preserve existing field names and explain the required error and success states.” For debugging, provide a representative input and ask the model to identify the first incorrect condition before returning a focused patch. Feed actual rendered or validation observations into the next revision.
The 0905 summary describes multi-head latent attention and a sparse mixture of experts, selecting eight of 384 experts per token alongside a shared expert. The 256K context supports a larger task record than the original K2 edition, while still containing the source, conversation, tool observations and generated answer together. A larger window should not be read as an independent maximum output allowance.
Organise repository excerpts by file and document material by section. State the final artifact and conditions that must remain unchanged through follow-ups. For a comparison, request the passage or code fragment supporting each conclusion. Keep the selected 0905 identity when the extended context and coding update are important to the task.
The maker recommends temperature 0.6 and provides a simple assistant system instruction for tasks that do not need a specialised role. Define the answer language and form separately, such as an explanation, a source-backed comparison or code only. This keeps the desired final result visible even when the application uses several model steps.
The exact card documents available tools supplied in each request. Functions have names, descriptions and parameter schemas; the model decides when and how to call them. The application parses the selected JSON arguments, performs the operation and returns a tool result associated with the call identifier. The next response can then use the actual observation or continue the task.
A generated patch, chosen operation or search plan is a proposal until the surrounding application performs it. Keep the result of that operation as the evidence for the next step and the final handoff. Check extracted values against source material and code against the requested behaviour.
K2 Instruct 0905 remains separate from K2 Thinking and the later multimodal K2.5 and K2.6 editions. Their image/video inputs, native INT4 thinking-checkpoint properties and preserve-thinking controls should not be inferred for this named text update. The useful output is a focused text or code artifact grounded in the task and the observations actually returned.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits moonshotai/kimi-k2-0905 | 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 / 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 / 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-k2-0905", "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-k2-0905',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-k2-0905',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-k2-0905
Use the method paths shown above.
moonshotai/kimi-k2-0905Kimi K2 Instruct 0905 is Moonshot AI’s updated text model for coding, frontend implementation and agents. It extends the original K2 context from 128K to 256K and returns answers, code and function-call content based on the task and observations supplied by the application.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Kimi K2 Instruct 0905 is Moonshot AI’s September instruction-model update to Kimi K2. It is a text model for knowledge, reasoning, coding and tool-guided tasks, with one trillion total mixture-of-experts parameters and 32 billion active parameters. The exact 0905 edition improves agentic coding and frontend work and extends the context from the original release’s 128K to 256K tokens.
The manufacturer emphasises both the practical behaviour and appearance of frontend code, alongside improvements in real-world coding-agent tasks. Prepare a software brief with the relevant implementation, observed behaviour and the requirements it must satisfy. For an interface, identify the content, visible states and interactions, as well as the design features that matter. A useful result is code tied to those criteria rather than a general discussion of how an interface could work.
An illustrative instruction is: “Update this component to match the described form flow, preserve existing field names and explain the required error and success states.” For debugging, provide a representative input and ask the model to identify the first incorrect condition before returning a focused patch. Feed actual rendered or validation observations into the next revision.
The 0905 summary describes multi-head latent attention and a sparse mixture of experts, selecting eight of 384 experts per token alongside a shared expert. The 256K context supports a larger task record than the original K2 edition, while still containing the source, conversation, tool observations and generated answer together. A larger window should not be read as an independent maximum output allowance.
Organise repository excerpts by file and document material by section. State the final artifact and conditions that must remain unchanged through follow-ups. For a comparison, request the passage or code fragment supporting each conclusion. Keep the selected 0905 identity when the extended context and coding update are important to the task.
The maker recommends temperature 0.6 and provides a simple assistant system instruction for tasks that do not need a specialised role. Define the answer language and form separately, such as an explanation, a source-backed comparison or code only. This keeps the desired final result visible even when the application uses several model steps.
The exact card documents available tools supplied in each request. Functions have names, descriptions and parameter schemas; the model decides when and how to call them. The application parses the selected JSON arguments, performs the operation and returns a tool result associated with the call identifier. The next response can then use the actual observation or continue the task.
A generated patch, chosen operation or search plan is a proposal until the surrounding application performs it. Keep the result of that operation as the evidence for the next step and the final handoff. Check extracted values against source material and code against the requested behaviour.
K2 Instruct 0905 remains separate from K2 Thinking and the later multimodal K2.5 and K2.6 editions. Their image/video inputs, native INT4 thinking-checkpoint properties and preserve-thinking controls should not be inferred for this named text update. The useful output is a focused text or code artifact grounded in the task and the observations actually returned.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits moonshotai/kimi-k2-0905 | 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 / 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 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "moonshotai/kimi-k2-0905",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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-k2-0905', '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-k2-0905', '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-k2-0905
Use the method paths shown above.
Technical example in English
Specify an accessible form correction\n\nPropose a focused HTML change for this form: <input id="email"><span>Email required</span><button>Send</button>. Requirements: a visible label must name the field, the error must be programmatically associated and the button must submit the form. Return the revised fragment and checks for label association and error text, preserving the email field ID.A revised HTML form fragment and two focused accessibility checks, with email still the field ID.Inspect label for/id and the error association; do not describe keyboard or screen-reader checks as already executed.