Claude Fable 5.2
claude-fable-5.2Claude Fable 5.2 supports long-context analysis, reasoning, coding assistance, and tool-assisted workflows. Its published specifications include a 1 million-token context window, up to 128,000 output tokens, multimodal input, and content caching. Access it on OpenAny using the public model ID claude-fable-5.2 through the configured Claude Messages endpoint.
- Published price
- From $7.600 / 1M tokens
- Billing unit
- / 1M tokens
- Context / Max output
- 1000K / 128K
- Listed routes
- 1
Code review using the Messages format. The user-provided Dev response ended at max_tokens. The captured balanced request did not pin a supplier; Playground route selection may adapt the request.
Other parameters (1)
Result preview
Neolink · 4843ms
Response example. Run to see the actual response.
{
"id": "msg_011CgzhFMty6QU47yxS964pD",
"role": "assistant",
"type": "message",
"model": "claude-fable-5-2",
"usage": {
"speed": "standard",
"input_tokens": 53,
"service_tier": "standard",
"inference_geo": "global",
"output_tokens": 1024,
"cache_creation": {
"ephemeral_1h_input_tokens": 0,
"ephemeral_5m_input_tokens": 0
},
"output_tokens_details": {
"thinking_tokens": 460
},
"cache_read_input_tokens": 0,
"cache_creation_input_tokens": 0
},
"content": [
{
"type": "thinking",
"thinking": "",
"signature": "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"
},
{
"text": "## The main issue: empty input\n\nIf `values` is empty, `len(values)` is `0` and the function raises a `ZeroDivisionError`:\n\n```python\naverage([]) # ZeroDivisionError: division by zero\n```\n\nThe error message is misleading because it doesn't tell the caller what actually went wrong, which is that an empty collection was passed.\n\n## Other edge cases\n\n- **Generators and iterators:** `average(x for x in data)` fails with `TypeError` because generators have no `len()`.\n- **Floating-point precision:** `sum()` accumulates rounding error. For example, `sum([0.1] * 10)` gives `0.9999999999999999`, not `1.0`.\n- **`None` or non-numeric input:** these raise a `TypeError`. That is usually acceptable, but worth knowing.\n\n## Corrected version\n\n```python\nimport math\n\ndef average(values):\n values = list(values) # allows generators and other iterables\n if not values:\n raise ValueError(\"average() requires at least one value\")\n return math.fsum(values) / len(values)\n```\n\nThis version makes three changes:\n\n- **`list(values)`** lets the function accept any iterable, not just sequences.\n- **The explicit check** replaces the confusing `ZeroDivisionError` with a clear `ValueError`.\n- **`math.fsum`** does precision-preserving summation, so `average([0.1] * 10)` returns exactly `0.1`.\n\n## Design choice: raise or return a default?\n\nAn empty average is mathematically undefined, so I'd raise an exception by default, because it keeps bugs from passing silently. If your use case calls for a fallback value instead, make it explicit:\n\n```python\ndef average(values, default=None):\n values = list(values)\n if not values:",
"type": "text"
}
],
"container": null,
"diagnostics": null,
"stop_reason": "max_tokens",
"openany_cost": 289688,
"stop_details": null,
"stop_sequence": null,
"input_transformations": []
}Request example
POST /v1/messagescurl 'https://api.openany.si/v1/messages' \
-H "Authorization: Bearer $OPENANY_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"max_tokens": 1024,
"messages": [
{
"content": "Review this function for edge cases, explain the issue, and suggest a corrected version:\n\ndef average(values):\n return sum(values) / len(values)",
"role": "user"
}
],
"model": "claude-fable-5.2",
"route_mode": "balanced"
}'Model API questions
How do I call Claude Fable 5.2 through OpenAny?
Use model ID claude-fable-5.2 with an OpenAny key and the operation published in this model's API tab. The model API base is https://api.openany.si/v1. Confirm the protocol and request schema; model availability does not imply every OpenAI API operation is supported.
How is Claude Fable 5.2 billed?
Compare the published rate and billing unit of the selected provider route. Input, output and cache token rates may differ. Image, audio and video models can use other units. Recorded usage determines the charge under that route's billing contract.
Are Community and Verified routes the same as an official publisher API?
No. Inspect the provider name and supply classification for the specific route. A marketplace listing or a supply label is not a claim of publisher endorsement, identical service or measured uptime. Different route prices may reflect different supply and conditions.
Where do these prices come from, and when were they updated?
Rates come from the provider routes in OpenAny's public model catalog, not an independent quote from the model publisher. The catalog does not supply a price update timestamp. A page or catalog snapshot date is not a price revision date. Compare supply, billing units, tiers and conditions; a lower listed rate alone does not establish equivalent service or explain the price difference.
Use Claude Fable 5.2 with your agent
Inspect endpoint contracts and confirm availability and pricing before a paid call.