Prompt caches are per-model. When Claude Fable 5 declines a request and you retry on another model, the conversation prefix that was already cached for Claude Fable 5 must be written into the new model's cache from scratch. Cache writes cost more than cache reads. Fallback credit removes that extra cost. The refusal carries a credit token, you echo the token on the retry, and the retry is billed as though the conversation had been on the new model all along.

You need this page only when you build the retry yourself: on the Ruby or PHP SDK, over raw HTTP, or with custom retry logic. Server-side fallback and the SDK middleware apply fallback credit automatically. If you use either, skip this page.

Refusals and fallback covers detecting refusals and choosing a fallback approach. Prompt caching explains cache reads and cache writes if those terms are new.

The basic flow

The fallback_has_prefill_claim field tells you whether the retry can continue the refused model's partial output instead of starting over:

Example

The following example makes a request that may be refused and redeems the credit token on a retry against Claude Opus 4.8. When a retry attempt is rejected, the example degrades through the rejection ladder: the sequence of progressively simpler retry shapes covered in When a retry is rejected.

client = Anthropic()

request = {
 "max_tokens": 1024,
 "messages": [{"role": "user", "content": "Hello, Claude"}],
}


def send(model, body):
 return client.beta.messages.create(
 model=model, betas=["fallback-credit-2026-06-01"], **body
 )


response = send("claude-fable-5", request)

if (
 response.stop_reason == "refusal"
 and (details := response.stop_details)
 and (token := details.fallback_credit_token)
):
 exact_body = request | {"fallback_credit_token": token}
 # Prefer the continuation shape unless the claim is False
 if details.fallback_has_prefill_claim is not False:
 # Echo the refusal's content, stripping trailing whitespace from a
 # final text block (the prefill validator rejects it; the server-side
 # match tolerates the edit). Tool-using requests also omit unpaired
 # tool_use blocks, then re-strip whitespace after any omissions.
 echoed = [block.model_dump() for block in response.content]
 match echoed:
 case [*_, {"type": "text"} as final_block]:
 final_block["text"] = final_block["text"].rstrip()
 attempt = exact_body | {
 "messages": [
 *request["messages"],
 {"role": "assistant", "content": echoed},
 ]
 }
 else:
 attempt = exact_body

 try:
 response = send("claude-opus-4-8", attempt)
 except BadRequestError as error:
 if "redemption temporarily unavailable" in str(error):
 raise # Transient: retry with the token within its five-minute window
 try:
 # Fall back to the unchanged body, still with the token
 response = send("claude-opus-4-8", exact_body)
 except BadRequestError as error:
 if "redemption temporarily unavailable" in str(error):
 raise # Transient: retry with the token within its five-minute window
 # The token itself was rejected: forfeit it and retry without.
 response = send("claude-opus-4-8", request)

print(json.dumps({"stop_reason": response.stop_reason, "model": response.model}))

Where it works

Fallback credit is in beta on the Claude API, Claude Platform on AWS, Amazon Bedrock, Vertex AI, and Microsoft Foundry. Credit tokens returned in Message Batches results cannot be redeemed. Redemption applies only to direct Messages API requests.

The retry model must be one of the refused model's permitted fallback targets. At launch, Claude Fable 5's permitted target is Claude Opus 4.8 (claude-opus-4-8).

Checking that the credit applied

The refund is visible in the retry's usage. Compared with what the same request would report without the token, cache_creation_input_tokens is lower, and cache_read_input_tokens is higher by the same amount. A shift of zero means the token was honored but there was nothing to reprice, for example because the retry model's cache was already warm.

When a retry is rejected

Most retries redeem on the first attempt. When one does not, the API returns a 400 error that tells you what to try next.

Reference

The sections below cover edge cases and the complete redemption rules. Most integrations do not need them.

Next steps