Claude 3.7 Sonnet Thinking describes the extended-thinking mode of Claude 3.7 Sonnet, rather than a separate generation of the base model. Anthropic combines ordinary responses and deeper reasoning in one hybrid model. The Thinking variant is useful when a task contains interacting constraints and the answer benefits from working through them before presenting a conclusion.
The model spends additional reasoning tokens on the problem before returning its final answer. Anthropic highlights mathematics, physics, complex instruction following and programming, while placing emphasis on real business tasks rather than competition puzzles alone. The manufacturer documents control over reasoning effort through a thinking-token budget; the budget and the final response share the available output allowance. More reasoning takes additional time, so reserve this mode for work where the extra analysis matters.
For an analytical task, provide the evidence, the question to resolve and the criteria for comparing alternatives. Ask for a conclusion followed by its supporting facts, assumptions and unresolved questions. This gives the final answer a usable shape without treating the length of its reasoning as evidence that the conclusion is correct.
Anthropic places particular emphasis on code changes, navigating complex projects and building web interfaces. A useful brief includes the relevant code, expected behaviour, the observed failure and the parts that must remain unchanged. Request a coherent patch and an explanation of how to verify it. For an interface, specify the user actions, loading and error states, responsive behaviour and the output you need, such as a component or a set of page changes.
These examples describe tasks to give the model. Executing commands, reading a repository and editing files require tools supplied by the surrounding application. The model’s coding ability and an application’s permission to run code are separate parts of the workflow.
Claude’s visual understanding supports reasoning about material such as screenshots, charts and illustrated documents, alongside written instructions. Supply a legible image and state which detail matters: a labelled axis, a layout problem or a relationship between objects. For exact figures in a chart, include the underlying values where possible. The result is a text explanation, analysis or code, rather than a generated image.
For an Ailoot API project, define the expected final artifact explicitly: an implementation, a reviewed argument, a comparison table or a diagnostic explanation. Provide the relevant material together with that requirement instead of asking the model to guess missing project context.
Anthropic identifies October 2024 as this base model’s reliable knowledge cutoff. Supply current documents when your question depends on later events or changing technical details. Its system card also records a coding failure pattern in which repeated unsuccessful attempts can lead to test-specific shortcuts. Ask for a general solution and inspect changes to tests as carefully as changes to application code. A detailed reasoning trace can help inspect an answer, but Anthropic’s research does not establish it as a complete or infallible account of how a decision was made.
", "aboutText": "Claude 3.7 Sonnet Thinking describes the extended-thinking mode of Claude 3.7 Sonnet, rather than a separate generation of the base model. Anthropic combines ordinary responses and deeper reasoning in one hybrid model. The Thinking variant is useful when a task contains interacting constraints and the answer benefits from working through them before presenting a conclusion.\n\n### Extended reasoning for practical problems\n\nThe model spends additional reasoning tokens on the problem before returning its final answer. Anthropic highlights mathematics, physics, complex instruction following and programming, while placing emphasis on real business tasks rather than competition puzzles alone. The manufacturer documents control over reasoning effort through a thinking-token budget; the budget and the final response share the available output allowance. More reasoning takes additional time, so reserve this mode for work where the extra analysis matters.\n\nFor an analytical task, provide the evidence, the question to resolve and the criteria for comparing alternatives. Ask for a conclusion followed by its supporting facts, assumptions and unresolved questions. This gives the final answer a usable shape without treating the length of its reasoning as evidence that the conclusion is correct.\n\n### Coding and front-end development\n\nAnthropic places particular emphasis on code changes, navigating complex projects and building web interfaces. A useful brief includes the relevant code, expected behaviour, the observed failure and the parts that must remain unchanged. Request a coherent patch and an explanation of how to verify it. For an interface, specify the user actions, loading and error states, responsive behaviour and the output you need, such as a component or a set of page changes.\n\nThese examples describe tasks to give the model. Executing commands, reading a repository and editing files require tools supplied by the surrounding application. The model’s coding ability and an application’s permission to run code are separate parts of the workflow.\n\n### Text, images and the final artifact\n\nClaude’s visual understanding supports reasoning about material such as screenshots, charts and illustrated documents, alongside written instructions. Supply a legible image and state which detail matters: a labelled axis, a layout problem or a relationship between objects. For exact figures in a chart, include the underlying values where possible. The result is a text explanation, analysis or code, rather than a generated image.\n\nFor an Ailoot API project, define the expected final artifact explicitly: an implementation, a reviewed argument, a comparison table or a diagnostic explanation. Provide the relevant material together with that requirement instead of asking the model to guess missing project context.\n\n### Knowledge and verification\n\nAnthropic identifies October 2024 as this base model’s reliable knowledge cutoff. Supply current documents when your question depends on later events or changing technical details. Its system card also records a coding failure pattern in which repeated unsuccessful attempts can lead to test-specific shortcuts. Ask for a general solution and inspect changes to tests as carefully as changes to application code. A detailed reasoning trace can help inspect an answer, but Anthropic’s research does not establish it as a complete or infallible account of how a decision was made.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Reason through a batching rule\n\nA packing line must send 42 jars. Each sealed carton holds 6 jars; opened cartons cannot ship. Each pallet holds at most 4 cartons. Determine the minimum cartons and pallets, then explain a valid loading arrangement. Separate the arithmetic from the assumptions, and state whether any jars remain unpacked.Carton and pallet counts, a loading arrangement, arithmetic and explicit assumptions.Multiply carton capacity back to 42 and verify no pallet exceeds four cartons.claude-3-7-sonnet-20250219-thinkingClaude 3.7 Sonnet is Anthropic’s hybrid reasoning model, used here in extended-thinking mode. It works through demanding coding, mathematical and analytical tasks before producing a text answer, with particular emphasis on practical software development and front-end work.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Claude 3.7 Sonnet Thinking describes the extended-thinking mode of Claude 3.7 Sonnet, rather than a separate generation of the base model. Anthropic combines ordinary responses and deeper reasoning in one hybrid model. The Thinking variant is useful when a task contains interacting constraints and the answer benefits from working through them before presenting a conclusion.
The model spends additional reasoning tokens on the problem before returning its final answer. Anthropic highlights mathematics, physics, complex instruction following and programming, while placing emphasis on real business tasks rather than competition puzzles alone. The manufacturer documents control over reasoning effort through a thinking-token budget; the budget and the final response share the available output allowance. More reasoning takes additional time, so reserve this mode for work where the extra analysis matters.
For an analytical task, provide the evidence, the question to resolve and the criteria for comparing alternatives. Ask for a conclusion followed by its supporting facts, assumptions and unresolved questions. This gives the final answer a usable shape without treating the length of its reasoning as evidence that the conclusion is correct.
Anthropic places particular emphasis on code changes, navigating complex projects and building web interfaces. A useful brief includes the relevant code, expected behaviour, the observed failure and the parts that must remain unchanged. Request a coherent patch and an explanation of how to verify it. For an interface, specify the user actions, loading and error states, responsive behaviour and the output you need, such as a component or a set of page changes.
These examples describe tasks to give the model. Executing commands, reading a repository and editing files require tools supplied by the surrounding application. The model’s coding ability and an application’s permission to run code are separate parts of the workflow.
Claude’s visual understanding supports reasoning about material such as screenshots, charts and illustrated documents, alongside written instructions. Supply a legible image and state which detail matters: a labelled axis, a layout problem or a relationship between objects. For exact figures in a chart, include the underlying values where possible. The result is a text explanation, analysis or code, rather than a generated image.
For an Ailoot API project, define the expected final artifact explicitly: an implementation, a reviewed argument, a comparison table or a diagnostic explanation. Provide the relevant material together with that requirement instead of asking the model to guess missing project context.
Anthropic identifies October 2024 as this base model’s reliable knowledge cutoff. Supply current documents when your question depends on later events or changing technical details. Its system card also records a coding failure pattern in which repeated unsuccessful attempts can lead to test-specific shortcuts. Ask for a general solution and inspect changes to tests as carefully as changes to application code. A detailed reasoning trace can help inspect an answer, but Anthropic’s research does not establish it as a complete or infallible account of how a decision was made.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits claude-3-7-sonnet-20250219-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.
| Configuration | Rate schedule | Charge |
|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Charge Input · Input tokens $0.006 / 1K tokens Output · Output tokens $0.03 / 1K tokens Input · Cache read $0.0006 / 1K tokens Input · Cache write $0.0075 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "claude-3-7-sonnet-20250219-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='claude-3-7-sonnet-20250219-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='claude-3-7-sonnet-20250219-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 claude-3-7-sonnet-20250219-thinking
Use the method paths shown above.
Technical example in English
Reason through a batching rule\n\nA packing line must send 42 jars. Each sealed carton holds 6 jars; opened cartons cannot ship. Each pallet holds at most 4 cartons. Determine the minimum cartons and pallets, then explain a valid loading arrangement. Separate the arithmetic from the assumptions, and state whether any jars remain unpacked.Carton and pallet counts, a loading arrangement, arithmetic and explicit assumptions.Multiply carton capacity back to 42 and verify no pallet exceeds four cartons.