Claude Opus 4.8 combines sustained agentic work, professional analysis, visual understanding and use of application-provided memory. Anthropic specifically highlights the model's behavior when checking conclusions: it was trained to notice insufficient evidence, communicate uncertainty and avoid claiming a completed result without adequate grounds.
In an engineering task, the model can investigate several connected components, consider a plan, identify errors and continue execution after receiving new data. For document analysis, its ability to work with dense content and its attention to problems in input material and conclusions matter. Described professional uses include research, analysis, document work and preparation of presentation content.
Instructions are interpreted literally, especially at low effort levels. The model is not required to silently extend a condition from one element to all the others: scope, format and result criteria are best stated explicitly. For code review, this means that the specified severity threshold affects which issues found appear in the response. A requirement to report every finding should be stated separately from a requirement to filter them.
Opus 4.8 supports adaptive reasoning, which needs to be enabled in the application. This version does not support manual extended thinking with a separate budget_tokens budget. The effort levels are low, medium, high, xhigh and max, with high as the default. According to Anthropic, deeper levels can increase analysis, tool calls and working time, while a lower level of work is useful for short, bounded tasks.
The model chooses detail according to how complex it considers a task: a simple question may receive a brief answer, while open analysis may be extensive. If a specific length or voice is required, it should be stated explicitly, preferably with a positive example. Intermediate progress messages are provided during extended tool use; their content and frequency can also be guided by instructions.
Input consists of text and images, and the result is text. The context window is 1 million tokens, and the maximum response in ordinary mode is 128 thousand tokens. The reliable built-in knowledge cutoff is January 2026.
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.
Web search, command execution, file-based memory, interface control and autonomous subtasks require application support. The model can use available tools, but the effort level and a clear description of their purpose affect its action choices. This is especially useful in work combining information search, analysis and technical execution.
When creating interfaces and slides, Opus 4.8 has its own consistent presentation preferences. For a result in a specific style, it is useful to specify a palette, typography, composition and motion style, or first request several directions. A finished file or functioning interface is produced through environment tools; the model's own output remains text.
", "aboutText": "Claude Opus 4.8 combines sustained agentic work, professional analysis, visual understanding and use of application-provided memory. Anthropic specifically highlights the model's behavior when checking conclusions: it was trained to notice insufficient evidence, communicate uncertainty and avoid claiming a completed result without adequate grounds.\n\n### Clarifying boundaries and carrying work through\n\nIn an engineering task, the model can investigate several connected components, consider a plan, identify errors and continue execution after receiving new data. For document analysis, its ability to work with dense content and its attention to problems in input material and conclusions matter. Described professional uses include research, analysis, document work and preparation of presentation content.\n\nInstructions are interpreted literally, especially at low effort levels. The model is not required to silently extend a condition from one element to all the others: scope, format and result criteria are best stated explicitly. For code review, this means that the specified severity threshold affects which issues found appear in the response. A requirement to report every finding should be stated separately from a requirement to filter them.\n\n### Configuring reasoning and presentation\n\nOpus 4.8 supports adaptive reasoning, which needs to be enabled in the application. This version does not support manual extended thinking with a separate `budget_tokens` budget. The `effort` levels are `low`, `medium`, `high`, `xhigh` and `max`, with `high` as the default. According to Anthropic, deeper levels can increase analysis, tool calls and working time, while a lower level of work is useful for short, bounded tasks.\n\nThe model chooses detail according to how complex it considers a task: a simple question may receive a brief answer, while open analysis may be extensive. If a specific length or voice is required, it should be stated explicitly, preferably with a positive example. Intermediate progress messages are provided during extended tool use; their content and frequency can also be guided by instructions.\n\n### Material, tools and visual presentation\n\nInput consists of **text and images**, and the result is **text**. The context window is **1 million tokens**, and the maximum response in ordinary mode is **128 thousand tokens**. The reliable built-in knowledge cutoff is **January 2026**.\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\nWeb search, command execution, file-based memory, interface control and autonomous subtasks require application support. The model can use available tools, but the effort level and a clear description of their purpose affect its action choices. This is especially useful in work combining information search, analysis and technical execution.\n\nWhen creating interfaces and slides, Opus 4.8 has its own consistent presentation preferences. For a result in a specific style, it is useful to specify a palette, typography, composition and motion style, or first request several directions. A finished file or functioning interface is produced through environment tools; the model's own output remains text.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "1bb68db7eb2cb2cc0f29819d0753b945464d01716e2622f551d8e45c3d8709ac", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "en", "methods": [ { "html": "anthropic/claude-opus-4.8:batchClaude Opus 4.8 is designed for sustained development and professional analysis. Maintains the direction of multi-step work, identifies uncertainty and accounts for explicitly stated result requirements.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Claude Opus 4.8 combines sustained agentic work, professional analysis, visual understanding and use of application-provided memory. Anthropic specifically highlights the model's behavior when checking conclusions: it was trained to notice insufficient evidence, communicate uncertainty and avoid claiming a completed result without adequate grounds.
In an engineering task, the model can investigate several connected components, consider a plan, identify errors and continue execution after receiving new data. For document analysis, its ability to work with dense content and its attention to problems in input material and conclusions matter. Described professional uses include research, analysis, document work and preparation of presentation content.
Instructions are interpreted literally, especially at low effort levels. The model is not required to silently extend a condition from one element to all the others: scope, format and result criteria are best stated explicitly. For code review, this means that the specified severity threshold affects which issues found appear in the response. A requirement to report every finding should be stated separately from a requirement to filter them.
Opus 4.8 supports adaptive reasoning, which needs to be enabled in the application. This version does not support manual extended thinking with a separate budget_tokens budget. The effort levels are low, medium, high, xhigh and max, with high as the default. According to Anthropic, deeper levels can increase analysis, tool calls and working time, while a lower level of work is useful for short, bounded tasks.
The model chooses detail according to how complex it considers a task: a simple question may receive a brief answer, while open analysis may be extensive. If a specific length or voice is required, it should be stated explicitly, preferably with a positive example. Intermediate progress messages are provided during extended tool use; their content and frequency can also be guided by instructions.
Input consists of text and images, and the result is text. The context window is 1 million tokens, and the maximum response in ordinary mode is 128 thousand tokens. The reliable built-in knowledge cutoff is January 2026.
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.
Web search, command execution, file-based memory, interface control and autonomous subtasks require application support. The model can use available tools, but the effort level and a clear description of their purpose affect its action choices. This is especially useful in work combining information search, analysis and technical execution.
When creating interfaces and slides, Opus 4.8 has its own consistent presentation preferences. For a result in a specific style, it is useful to specify a palette, typography, composition and motion style, or first request several directions. A finished file or functioning interface is produced through environment tools; the model's own output remains text.
POST /v1/batchestexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldendpoint | Typestring | RequirementRequired | Values & limits /v1/chat/completions | Default— |
Fieldmodel | Typestring | RequirementRequired | Values & limits anthropic/claude-opus-4.8:batch | Default— |
Fieldrequests | Typebatch_item[] | RequirementRequired | Values & limits Minimum items: 1 | Default— |
Fieldrequests[].custom_id | Typestring | RequirementRequired | Values & limits | Default— |
Fieldrequests[].body.messages | Typemessage[] | RequirementRequired | Values & limits | Default— |
Fieldcompletion_window | Typestring | RequirementOptional | Values & limits 24h | Default— |
Fieldprovider | Typeobject|null | RequirementOptional | Values & limits | Default— |
Fieldrequests[].body.model | Typestring | RequirementOptional | Values & limits anthropic/claude-opus-4.8:batch, anthropic/claude-opus-4.8 | Default— |
Fieldprovider.only | Typestring[] | RequirementOptional | Values & limits anthropic | Default— |
Fieldprovider.allow_fallbacks | Typeboolean|null | RequirementOptional | Values & limits false, null | Default— |
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractendpoint, model, requests |
Parametermaterial_types | Contracttext |
Parameterrepresentation | Contractinline requests[]; each item has custom_id and body |
Parameterrequest_endpoint_profile | Contract/v1/chat/completions |
Parameterfile_material | ContractCaller may read actual UTF-8 JSONL locally into requests[]. No upload purpose, input_file_id or file reference is used. Missing/empty customer material stops preparation before POST. |
Parameterserialization_order | Contractendpoint, model, provider (if supplied), completion_window (if supplied), requests last |
Parameteroptional_controls | Contractprovider.only, provider.allow_fallbacks, completion_window |
Parameterschema_scope | ContractText Chat Completions bodies in the documented inline Batch envelope. |
Lifecycle: asynchronous
GET /v1/batches/{operation_id} · actual original create response.id; same user/key/group
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 $0.005 / 1K tokens Output · Output tokens $0.025 / 1K tokens Input · Cache read $0.0005 / 1K tokens Input · Cache write $0.00625 / 1K tokens Input · Cache write, 1 hour $0.01 / 1K tokens |
| ConfigurationRequest-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.005 / 1K tokens Output · Output tokens $0.025 / 1K tokens Input · Cache read $0.0005 / 1K tokens Input · Cache write $0.00625 / 1K tokens Input · Cache write, 1 hour $0.01 / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json\nfrom pathlib import Path\nbody=json.loads('{"endpoint":"/v1/chat/completions","model":"anthropic/claude-opus-4.8:batch","requests":[{"custom_id":"req-0001","body":{"messages":[{"role":"user","content":"Hello!"}],"max_tokens":16}}]}')\nPath("batch-request.json").write_text(json.dumps(body,ensure_ascii=False),encoding="utf-8")\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/batches \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @batch-request.json -D batch-response-headers.txt -o batch-create-response.json\nimport json, os\nfrom pathlib import Path\nfrom urllib.request import Request, urlopen\n\ndef prepare_requests(customer_path):\n path = Path(customer_path)\n if not path.is_file(): raise ValueError("Customer JSONL file is missing")\n items = [json.loads(line) for line in path.read_text(encoding="utf-8").splitlines() if line.strip()]\n if not items: raise ValueError("Customer JSONL contains no requests")\n ids = set()\n for item in items:\n if set(item) != {"custom_id", "body"}: raise ValueError("Each item needs custom_id and body")\n cid = item["custom_id"]\n if not isinstance(cid, str) or not cid.strip() or cid in ids: raise ValueError("custom_id must be nonempty and unique")\n ids.add(cid)\n if not isinstance(item["body"], dict) or not item["body"].get("messages"): raise ValueError("Supply actual text messages")\n supplied_model = item["body"].get("model")\n if supplied_model is not None and supplied_model not in ['anthropic/claude-opus-4.8:batch', 'anthropic/claude-opus-4.8']: raise ValueError("body.model must be an exact documented caller or wire ID")\n return {"endpoint":"/v1/chat/completions", "model":"anthropic/claude-opus-4.8:batch", "requests":items}\n\nif __name__ == "__main__":\n material = os.environ.get("AILOOT_BATCH_REQUESTS_JSONL", "")\n if not material: raise SystemExit("Set AILOOT_BATCH_REQUESTS_JSONL to your actual customer file")\n body = prepare_requests(material)\n key = os.environ.get("AILOOT_API_KEY", "")\n if not key: raise SystemExit("Set AILOOT_API_KEY")\n request = Request("https://api.ailoot.ai/v1/batches", data=json.dumps(body, ensure_ascii=False).encode("utf-8"), headers={"Authorization":"Bearer " + key, "Content-Type":"application/json"}, method="POST")\n with urlopen(request) as response:\n raw = response.read()\n Path("batch-create-response.json").write_bytes(raw)\n print(raw.decode("utf-8"))\nimport json\nfrom pathlib import Path\nraw = Path("batch-status-response.json").read_bytes()\nresponse = json.loads(raw)\nif response.get("status") != "completed":\n raise SystemExit("Keep the original operation; read its status without resubmitting")\nresults = response.get("results")\nif not isinstance(results, list) or not results:\n raise SystemExit("Preserve the original response; completed results are missing")\nPath("batch-results.jsonl").write_text("".join(json.dumps(item, ensure_ascii=False) + "\\n" for item in results), encoding="utf-8")\n# Preserve batch-status-response.json with aggregate usage and every result/error.\ninline results[].response.body JSON
GET /v1/batches/{operation_id}set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\nBATCH_OPERATION_ID="$(python3 - <<'PY_ID'\nimport json\nfrom pathlib import Path\nfrom urllib.parse import quote\nresponse = json.loads(Path("batch-create-response.json").read_text(encoding="utf-8"))\noperation = response.get("id")\nif not isinstance(operation, str) or not operation: raise SystemExit("No actual original operation ID; preserve the response and do not resubmit")\nprint(quote(operation, safe=""))\nPY_ID\n)"\ncurl --fail-with-body --silent --show-error "https://api.ailoot.ai/v1/batches/$BATCH_OPERATION_ID" \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -o batch-status-response.json\nKeep every complete returned response, file and content part.
Preserve the full original status JSON, every result/custom_id and complete response or error body. Save completed results[] as JSONL without filtering.
Preserve the original operation ID. 503 result_pending_check has X-Should-Retry:false; never resubmit an unknown original batch.
| Field | Type |
|---|---|
Fieldresults[].custom_id | Typestring |
Fieldresults[].response.body.choices[].message.content | Typestring|null |
Fieldresults[].error | Typeobject|null |
Fieldusage | Typeobject|null |
Fieldid | Typestring |
Fieldmodel | Typestring |
Fieldendpoint | Typestring |
Fieldstatus | Typestring |
Fieldrequest_counts | Typeobject |
Fieldresults[].id | Typestring |
Fieldresults[].response.status_code | Typeinteger |
Fieldresults[].response.request_id | Typestring |
| Response | Condition | Next step |
|---|---|---|
Response400 · invalid_request_error | ConditionInvalid documented inline envelope, duplicate keys, item identity, or configured model capabilities conflict. | Next stepCorrect the indicated fields before any new submission. |
Response401 · authentication_error | ConditionInvalid API key. | Next stepUse the authorized Ailoot key. |
Response403 · permission_error | ConditionBatch group unavailable. | Next stepCheck key/group entitlement. |
Response422 · invalid_request_error | ConditionBatch uses balance billing; subscription creation is rejected. | Next stepUse the authorized balance-billed group. |
Response422 · price_unavailable | ConditionBatch input cannot be quoted. | Next stepPreserve response; use documented family input. |
Response402 · billing_error | ConditionBatch reserve unavailable. | Next stepResolve admission before a new request. |
Response503 · price_unavailable | ConditionBatch method price/native rates unavailable. | Next stepPreserve response; do not substitute prices. |
Response503 · api_error | ConditionExact supplier route unavailable. | Next stepPreserve response for route repair. |
Response503 · result_pending_check | ConditionOriginal result requires checking; X-Should-Retry:false. | Next stepKeep original operation_id/id and read its status; never repeat original POST. |
Response404 · not_found | ConditionBatch status operation absent or owned by another identity. | Next stepUse exact original id and same user/key/group. |
Ailoot Ultra anthropic/claude-opus-4.8:batch
Use the method paths shown above.