Claude Opus 4 Thinking applies extended reasoning to the original Claude Opus 4 model. Anthropic positions this generation for difficult programming work, research, writing and tasks that require maintaining direction across many steps. The Thinking designation concerns how the model approaches a response; it does not turn the original Opus 4 into a later Opus edition.
Claude Opus 4 combines a standard response mode with an extended-thinking mode. In extended thinking, it can spend more time examining a problem before answering. The manufacturer describes sustained work on complex tasks as a central strength, especially when a task requires connecting a sequence of findings rather than solving isolated prompts.
For a research question, provide the materials to compare, the decision they should support and the conditions that matter. Ask for an evidence-based synthesis that separates findings, assumptions and open questions. For a writing task, include the audience, source material, required structure and the claims the result must explain. These are practical applications of the model’s documented research and writing capabilities, rather than promises of a particular outcome.
Anthropic emphasises complex code understanding, editing, debugging and changes spanning multiple files. Give the model the relevant modules, interface contracts, expected behaviour and existing tests or error output. Define the scope of the requested change and ask it to explain the dependencies that make the proposed edits necessary.
A useful engineering result connects three things: the cause of the problem, a consistent implementation and a way to check the resulting behaviour. For a refactor, state which public interfaces and observable behaviours must remain stable. For a feature, describe the user flow and its failure cases. This makes the model’s sustained reasoning useful to the project rather than merely producing a longer answer.
The original Claude 4 generation adds reasoning between tool calls in Anthropic’s documented extended-thinking workflow. It can examine a tool result, reconsider its approach and choose a subsequent action. The manufacturer also describes parallel tool use and improved continuity when an application supplies local files that the model can read and update.
An agent using these capabilities needs its application to provide the tools, execute requested actions and return their results. Memory files likewise belong to the application environment; they are not an unlimited store carried automatically between unrelated conversations. When designing a workflow, return relevant observations to the model and keep the task’s goal and acceptance criteria available.
Claude Opus 4 also supports visual analysis. Screenshots, charts and diagrams can supply evidence alongside text, while the model’s answer remains textual. Use clearly readable images and identify the relationships you want explained. Include source values when the task depends on exact counts or measurements, since visual interpretation can be approximate.
For an Ailoot API task, specify the final artifact you need: a multi-file change proposal, a technical investigation, a research synthesis or a carefully structured document. Add the evidence and constraints that let the model choose an approach. The manufacturer’s extended-thinking summaries provide an explanation alongside the result, but a summary is not a verbatim record of all reasoning. Inspect the delivered code or analysis against the task’s requirements, including any assumptions that still need evidence.
", "aboutText": "Claude Opus 4 Thinking applies extended reasoning to the original Claude Opus 4 model. Anthropic positions this generation for difficult programming work, research, writing and tasks that require maintaining direction across many steps. The Thinking designation concerns how the model approaches a response; it does not turn the original Opus 4 into a later Opus edition.\n\n### Reasoning across a demanding task\n\nClaude Opus 4 combines a standard response mode with an extended-thinking mode. In extended thinking, it can spend more time examining a problem before answering. The manufacturer describes sustained work on complex tasks as a central strength, especially when a task requires connecting a sequence of findings rather than solving isolated prompts.\n\nFor a research question, provide the materials to compare, the decision they should support and the conditions that matter. Ask for an evidence-based synthesis that separates findings, assumptions and open questions. For a writing task, include the audience, source material, required structure and the claims the result must explain. These are practical applications of the model’s documented research and writing capabilities, rather than promises of a particular outcome.\n\n### Changes across a codebase\n\nAnthropic emphasises complex code understanding, editing, debugging and changes spanning multiple files. Give the model the relevant modules, interface contracts, expected behaviour and existing tests or error output. Define the scope of the requested change and ask it to explain the dependencies that make the proposed edits necessary.\n\nA useful engineering result connects three things: the cause of the problem, a consistent implementation and a way to check the resulting behaviour. For a refactor, state which public interfaces and observable behaviours must remain stable. For a feature, describe the user flow and its failure cases. This makes the model’s sustained reasoning useful to the project rather than merely producing a longer answer.\n\n### Tools, parallel work and continuity\n\nThe original Claude 4 generation adds reasoning between tool calls in Anthropic’s documented extended-thinking workflow. It can examine a tool result, reconsider its approach and choose a subsequent action. The manufacturer also describes parallel tool use and improved continuity when an application supplies local files that the model can read and update.\n\nAn agent using these capabilities needs its application to provide the tools, execute requested actions and return their results. Memory files likewise belong to the application environment; they are not an unlimited store carried automatically between unrelated conversations. When designing a workflow, return relevant observations to the model and keep the task’s goal and acceptance criteria available.\n\n### Visual analysis and text output\n\nClaude Opus 4 also supports visual analysis. Screenshots, charts and diagrams can supply evidence alongside text, while the model’s answer remains textual. Use clearly readable images and identify the relationships you want explained. Include source values when the task depends on exact counts or measurements, since visual interpretation can be approximate.\n\nFor an Ailoot API task, specify the final artifact you need: a multi-file change proposal, a technical investigation, a research synthesis or a carefully structured document. Add the evidence and constraints that let the model choose an approach. The manufacturer’s extended-thinking summaries provide an explanation alongside the result, but a summary is not a verbatim record of all reasoning. Inspect the delivered code or analysis against the task’s requirements, including any assumptions that still need evidence.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Plan a coordinated order refactor\n\nReview this proposed refactor. Module A emits {order_id, total_cents}; module B stores those fields; module C displays total_cents / 100. A developer proposes renaming only A to amount_cents. Identify affected contracts and propose a coordinated migration that preserves existing consumers, with checks for old and new records.A dependency map in text, a staged migration proposal and compatibility checks for each consumer.Confirm the proposal covers B and C and does not silently reinterpret cents as whole currency units.claude-opus-4-20250514-thinkingClaude Opus 4 Thinking uses the original Opus 4’s extended-thinking mode for complex software changes, sustained agent workflows and research. It can reason between supported tool steps and connect evidence across a demanding task before producing a text result.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Claude Opus 4 Thinking applies extended reasoning to the original Claude Opus 4 model. Anthropic positions this generation for difficult programming work, research, writing and tasks that require maintaining direction across many steps. The Thinking designation concerns how the model approaches a response; it does not turn the original Opus 4 into a later Opus edition.
Claude Opus 4 combines a standard response mode with an extended-thinking mode. In extended thinking, it can spend more time examining a problem before answering. The manufacturer describes sustained work on complex tasks as a central strength, especially when a task requires connecting a sequence of findings rather than solving isolated prompts.
For a research question, provide the materials to compare, the decision they should support and the conditions that matter. Ask for an evidence-based synthesis that separates findings, assumptions and open questions. For a writing task, include the audience, source material, required structure and the claims the result must explain. These are practical applications of the model’s documented research and writing capabilities, rather than promises of a particular outcome.
Anthropic emphasises complex code understanding, editing, debugging and changes spanning multiple files. Give the model the relevant modules, interface contracts, expected behaviour and existing tests or error output. Define the scope of the requested change and ask it to explain the dependencies that make the proposed edits necessary.
A useful engineering result connects three things: the cause of the problem, a consistent implementation and a way to check the resulting behaviour. For a refactor, state which public interfaces and observable behaviours must remain stable. For a feature, describe the user flow and its failure cases. This makes the model’s sustained reasoning useful to the project rather than merely producing a longer answer.
The original Claude 4 generation adds reasoning between tool calls in Anthropic’s documented extended-thinking workflow. It can examine a tool result, reconsider its approach and choose a subsequent action. The manufacturer also describes parallel tool use and improved continuity when an application supplies local files that the model can read and update.
An agent using these capabilities needs its application to provide the tools, execute requested actions and return their results. Memory files likewise belong to the application environment; they are not an unlimited store carried automatically between unrelated conversations. When designing a workflow, return relevant observations to the model and keep the task’s goal and acceptance criteria available.
Claude Opus 4 also supports visual analysis. Screenshots, charts and diagrams can supply evidence alongside text, while the model’s answer remains textual. Use clearly readable images and identify the relationships you want explained. Include source values when the task depends on exact counts or measurements, since visual interpretation can be approximate.
For an Ailoot API task, specify the final artifact you need: a multi-file change proposal, a technical investigation, a research synthesis or a carefully structured document. Add the evidence and constraints that let the model choose an approach. The manufacturer’s extended-thinking summaries provide an explanation alongside the result, but a summary is not a verbatim record of all reasoning. Inspect the delivered code or analysis against the task’s requirements, including any assumptions that still need evidence.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits claude-opus-4-20250514-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 $0.03 / 1K tokens Output · Output tokens $0.15 / 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-opus-4-20250514-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-opus-4-20250514-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-opus-4-20250514-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-opus-4-20250514-thinking
Use the method paths shown above.
Technical example in English
Plan a coordinated order refactor\n\nReview this proposed refactor. Module A emits {order_id, total_cents}; module B stores those fields; module C displays total_cents / 100. A developer proposes renaming only A to amount_cents. Identify affected contracts and propose a coordinated migration that preserves existing consumers, with checks for old and new records.A dependency map in text, a staged migration proposal and compatibility checks for each consumer.Confirm the proposal covers B and C and does not silently reinterpret cents as whole currency units.