Claude Fable 5.1 is intended for work that starts with an open question and continues to a verifiable result. In programming, Anthropic highlights changes across many files, major refactoring, migrations, debugging and code verification. In research, it highlights sequences of search steps, comparison of material and maintaining direction as new information arrives.
The model can help identify the root cause of a complex software bug, plan a correction and check the proposed solution. Its ability to connect details that are far apart in a large body of material is useful when working with information. A task can continue after its initial findings: the analysis becomes document content, a spreadsheet with formulas or a presentation.
Such finished materials are produced through application tools. Code execution, file reading, information searches and interface actions also require a connected environment. Anthropic describes continuing after an unsuccessful action and recovering a workflow in interfaces, but the availability of these tools and the permitted operations are determined by the application.
The model accepts text and images, and its own output is text. Visual uses include dense charts, financial material and tables in documents. When a source page contains many small details, additional zooming or cropping through tools may help isolate the relevant area.
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.
In research examples, the manufacturer demonstrates Fable 5.1 being used to train a neural network that reconstructs a height map of Venus from radar data. This is an example of data and programming work, not a separate type of media output from the model.
Adaptive reasoning in Fable 5.1 is always enabled. The effort parameter sets its depth: low, medium, high, xhigh and max are available, with high as the default. Context is 1 million tokens, and the maximum response is 128 thousand tokens. The reliable built-in knowledge cutoff is June 2026.
The manufacturer provides for changing effort during a conversation and reporting progress when the application supports these mechanisms. If the application passes retained reasoning blocks, their connection to the model and original history matters. Changes to previous messages, the system instruction or earlier tool definitions may invalidate subsequent blocks: the binding check either rejects the request or excludes the affected blocks. Fable 5.1 can read retained reasoning from earlier Claude models, but those earlier models cannot read its blocks. An incompatible block is excluded before the next turn, and work continues without it. Fable 5.1 uses the same tokenizer as Fable 5; material size needs to be assessed for the selected model.
At low effort, Fable 5.1 may prefer answering from built-in knowledge to using search. If a question requires a current check, this should be stated explicitly and the necessary tools provided. The model sometimes writes dense text, rarely reports intermediate progress or replaces an entire file when a local edit was expected; the desired style and change boundaries are useful to specify in advance.
If the method provides tool control, the manufacturer's model supports automatic selection with auto and disabling tools with none. Forced calls are not supported, either for any tool with any or for a specific named tool with tool. Safety rules allow investigation of bugs and vulnerabilities in source code, but restrict some sensitive tasks, including exploit development.
In a method that supports these settings, continuation from a predefined response prefix and non-default values of temperature, top_p and top_k are not accepted. Text generated by the model contains Anthropic's statistical watermark: it does not change meaning, quality or readability, and adds no hidden characters or tokens.
anthropic/claude-fable-5.1:batchClaude Fable 5.1 is designed for complex research, large code changes and extended professional analysis. Connects information across a large context window and works with text and detailed images.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Claude Fable 5.1 is intended for work that starts with an open question and continues to a verifiable result. In programming, Anthropic highlights changes across many files, major refactoring, migrations, debugging and code verification. In research, it highlights sequences of search steps, comparison of material and maintaining direction as new information arrives.
The model can help identify the root cause of a complex software bug, plan a correction and check the proposed solution. Its ability to connect details that are far apart in a large body of material is useful when working with information. A task can continue after its initial findings: the analysis becomes document content, a spreadsheet with formulas or a presentation.
Such finished materials are produced through application tools. Code execution, file reading, information searches and interface actions also require a connected environment. Anthropic describes continuing after an unsuccessful action and recovering a workflow in interfaces, but the availability of these tools and the permitted operations are determined by the application.
The model accepts text and images, and its own output is text. Visual uses include dense charts, financial material and tables in documents. When a source page contains many small details, additional zooming or cropping through tools may help isolate the relevant area.
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.
In research examples, the manufacturer demonstrates Fable 5.1 being used to train a neural network that reconstructs a height map of Venus from radar data. This is an example of data and programming work, not a separate type of media output from the model.
Adaptive reasoning in Fable 5.1 is always enabled. The effort parameter sets its depth: low, medium, high, xhigh and max are available, with high as the default. Context is 1 million tokens, and the maximum response is 128 thousand tokens. The reliable built-in knowledge cutoff is June 2026.
The manufacturer provides for changing effort during a conversation and reporting progress when the application supports these mechanisms. If the application passes retained reasoning blocks, their connection to the model and original history matters. Changes to previous messages, the system instruction or earlier tool definitions may invalidate subsequent blocks: the binding check either rejects the request or excludes the affected blocks. Fable 5.1 can read retained reasoning from earlier Claude models, but those earlier models cannot read its blocks. An incompatible block is excluded before the next turn, and work continues without it. Fable 5.1 uses the same tokenizer as Fable 5; material size needs to be assessed for the selected model.
At low effort, Fable 5.1 may prefer answering from built-in knowledge to using search. If a question requires a current check, this should be stated explicitly and the necessary tools provided. The model sometimes writes dense text, rarely reports intermediate progress or replaces an entire file when a local edit was expected; the desired style and change boundaries are useful to specify in advance.
If the method provides tool control, the manufacturer's model supports automatic selection with auto and disabling tools with none. Forced calls are not supported, either for any tool with any or for a specific named tool with tool. Safety rules allow investigation of bugs and vulnerabilities in source code, but restrict some sensitive tasks, including exploit development.
In a method that supports these settings, continuation from a predefined response prefix and non-default values of temperature, top_p and top_k are not accepted. Text generated by the model contains Anthropic's statistical watermark: it does not change meaning, quality or readability, and adds no hidden characters or tokens.
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-fable-5.1: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-fable-5.1:batch, anthropic/claude-fable-5.1 | 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 $0.01 / 1K tokens Output · Output tokens $0.05 / 1K tokens Input · Cache read $0.00025 / 1K tokens Input · Cache write $0.0125 / 1K tokens Input · Cache write, 1 hour $0.02 / 1K tokens |
| ConfigurationRequest-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.01 / 1K tokens Output · Output tokens $0.05 / 1K tokens Input · Cache read $0.00025 / 1K tokens Input · Cache write $0.0125 / 1K tokens Input · Cache write, 1 hour $0.02 / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${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-fable-5.1: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-fable-5.1:batch', 'anthropic/claude-fable-5.1']: raise ValueError("body.model must be an exact documented caller or wire ID")\n return {"endpoint":"/v1/chat/completions", "model":"anthropic/claude-fable-5.1: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-fable-5.1:batch
Use the method paths shown above.