Anthropic develops Claude Opus 4.7 for complex, extended development tasks. Its presentation emphasizes carrying out work in sequence, close attention to instructions and finding ways to check its own result before the final message. The model is suited to investigating a difficult code problem and preparing professional material that requires both a technical solution and clear presentation.
Opus 4.7 follows wording literally. Prompts are best expressed through explicit boundaries: which parts should be changed, what should be checked and what the result should be. If a condition applies to every part of the work, it should be stated that way. The manufacturer also highlights the use of file-based memory notes for long tasks, but reading and storing such notes requires application tools.
The model accepts text and images and produces text. Visual input supports resolution up to 2576 pixels on the longer dimension, approximately 3.75 megapixels. This is useful for dense screenshots, extracting information from complex diagrams and tasks with detailed visual references.
The manufacturer's standard visual input formats are JPEG/PNG/GIF/WebP, using the first frame of an animation. For native analysis, the longer dimension is 2576 pixels, with 4784 visual tokens; larger images are downscaled before analysis. File and parameter support depends on the application's method.
High resolution helps preserve detail but does not make visual understanding infallible. Output can be an explanation, a data structure or code; creating or editing the image itself is not an output capability of the model. Interface control requires tools that show the screen to the model and perform actions in the application.
Context is 1 million tokens, and the maximum response in ordinary mode is 128 thousand tokens. Adaptive reasoning is supported; manual extended thinking with budget_tokens is absent in this version. The default effort level is high, with low, medium, xhigh and max also available. xhigh provides a separate setting between high and max for extended engineering and agentic work.
At low effort levels, the model limits its work particularly strictly to what was requested. For complex research, the manufacturer recommends leaving enough room for reasoning and the response. This version has an updated tokenizer, so the same amount of text does not always have the token length familiar from earlier versions.
The reliable built-in knowledge cutoff is January 2026. Current research, document work and code execution use material and tools provided by the application. Opus 4.7 has safety mechanisms that can block prohibited or high-risk cybersecurity requests. Its attention to checking results is useful, but final changes and conclusions still need to be verified in the specific environment.
", "aboutText": "### Careful engineering work\n\nAnthropic develops Claude Opus 4.7 for complex, extended development tasks. Its presentation emphasizes carrying out work in sequence, close attention to instructions and finding ways to check its own result before the final message. The model is suited to investigating a difficult code problem and preparing professional material that requires both a technical solution and clear presentation.\n\nOpus 4.7 follows wording literally. Prompts are best expressed through explicit boundaries: which parts should be changed, what should be checked and what the result should be. If a condition applies to every part of the work, it should be stated that way. The manufacturer also highlights the use of file-based memory notes for long tasks, but reading and storing such notes requires application tools.\n\n### Reading dense diagrams and interface screenshots\n\nThe model accepts **text and images** and produces **text**. Visual input supports resolution up to **2576 pixels on the longer dimension**, approximately **3.75 megapixels**. This is useful for dense screenshots, extracting information from complex diagrams and tasks with detailed visual references.\n\nThe manufacturer's standard visual input formats are JPEG/PNG/GIF/WebP, using the first frame of an animation. For native analysis, the longer dimension is 2576 pixels, with 4784 visual tokens; larger images are downscaled before analysis. File and parameter support depends on the application's method.\n\nHigh resolution helps preserve detail but does not make visual understanding infallible. Output can be an explanation, a data structure or code; creating or editing the image itself is not an output capability of the model. Interface control requires tools that show the screen to the model and perform actions in the application.\n\n### Task depth and capacity\n\nContext is **1 million tokens**, and the maximum response in ordinary mode is **128 thousand tokens**. Adaptive reasoning is supported; manual extended thinking with `budget_tokens` is absent in this version. The default `effort` level is `high`, with `low`, `medium`, `xhigh` and `max` also available. `xhigh` provides a separate setting between `high` and `max` for extended engineering and agentic work.\n\nAt low effort levels, the model limits its work particularly strictly to what was requested. For complex research, the manufacturer recommends leaving enough room for reasoning and the response. This version has an updated tokenizer, so the same amount of text does not always have the token length familiar from earlier versions.\n\n### Working conditions\n\nThe reliable built-in knowledge cutoff is **January 2026**. Current research, document work and code execution use material and tools provided by the application. Opus 4.7 has safety mechanisms that can block prohibited or high-risk cybersecurity requests. Its attention to checking results is useful, but final changes and conclusions still need to be verified in the specific environment.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "54fc1a39e58ff5786d7e2ecbbd46ef85d8d51757301ef93939aaf54180c415a8", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "en", "methods": [ { "html": "claude-opus-4-7-thinkingClaude Opus 4.7 is designed for complex engineering work and analysis of documents and finely detailed images. Places particular emphasis on following instructions precisely and checking results.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Anthropic develops Claude Opus 4.7 for complex, extended development tasks. Its presentation emphasizes carrying out work in sequence, close attention to instructions and finding ways to check its own result before the final message. The model is suited to investigating a difficult code problem and preparing professional material that requires both a technical solution and clear presentation.
Opus 4.7 follows wording literally. Prompts are best expressed through explicit boundaries: which parts should be changed, what should be checked and what the result should be. If a condition applies to every part of the work, it should be stated that way. The manufacturer also highlights the use of file-based memory notes for long tasks, but reading and storing such notes requires application tools.
The model accepts text and images and produces text. Visual input supports resolution up to 2576 pixels on the longer dimension, approximately 3.75 megapixels. This is useful for dense screenshots, extracting information from complex diagrams and tasks with detailed visual references.
The manufacturer's standard visual input formats are JPEG/PNG/GIF/WebP, using the first frame of an animation. For native analysis, the longer dimension is 2576 pixels, with 4784 visual tokens; larger images are downscaled before analysis. File and parameter support depends on the application's method.
High resolution helps preserve detail but does not make visual understanding infallible. Output can be an explanation, a data structure or code; creating or editing the image itself is not an output capability of the model. Interface control requires tools that show the screen to the model and perform actions in the application.
Context is 1 million tokens, and the maximum response in ordinary mode is 128 thousand tokens. Adaptive reasoning is supported; manual extended thinking with budget_tokens is absent in this version. The default effort level is high, with low, medium, xhigh and max also available. xhigh provides a separate setting between high and max for extended engineering and agentic work.
At low effort levels, the model limits its work particularly strictly to what was requested. For complex research, the manufacturer recommends leaving enough room for reasoning and the response. This version has an updated tokenizer, so the same amount of text does not always have the token length familiar from earlier versions.
The reliable built-in knowledge cutoff is January 2026. Current research, document work and code execution use material and tools provided by the application. Opus 4.7 has safety mechanisms that can block prohibited or high-risk cybersecurity requests. Its attention to checking results is useful, but final changes and conclusions still need to be verified in the specific environment.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits claude-opus-4-7-thinking | Default— |
Fieldmessages | Typemessage[] | RequirementRequired | Values & limits Minimum items: 1 | Default— |
Fieldmessages[].role | Typestring | RequirementRequired | Values & limits Model-specific | Default— |
Fieldmessages[].content | Typestring | RequirementOptional | Values & limits Applies when: Text conversation | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
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 |
Parametercontrol_scope | ContractText conversation; stream is a boolean and defaults to false. |
Parameteroutput_modalities | Contracttext |
Parameterhosted_operations | Contractfalse |
Parametermultimodal_input_binding | Contractnull |
Method aliases: /chat/completions
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 $0.01 / 1K tokens Output · Output tokens $0.05 / 1K tokens Input · Cache read $0.001 / 1K tokens Input · Cache write $0.0125 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model":"claude-opus-4-7-thinking","messages":[{"role":"user","content":"hello"}],"stream":false}')\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-4-7-thinking", messages=[{"role":"user","content":"hello"}], stream=False)\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"))\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-4-7-thinking
/chat/completions