AI Gateway Unified Billing: anthropic/* returns 401 in Cloudflare's own Playground, and openai/* returns 402 "Payment error" on the API-token path while the identical request succeeds via dashboard session

[ao1ao2]

Summary

On an account with US$50 of Unified Billing credits and zero consumption, two distinct failures are reproducible. Both are demonstrated below with a control case that rules out client-side misconfiguration.

Environment

• Unified Billing credits: US$50.00 available, US$0.00 ever consumed
• Usage over the last 30 days: 48 requests, 0 tokens, $0.00 cost, 100% error rate across both gateways
• Two gateways, both with Authentication enabled
• No BYOK provider keys configured for any provider — Unified Billing is the only credential source on the account
• Account ID available on request

---

Issue 1 — anthropic/* returns 401 inside the Cloudflare Dashboard Playground

In the Dashboard AI Gateway Playground, model anthropic/claude-opus-5:

Error: inferenceChatCompletions returned 401

Reproduced three times. On the same gateway, same endpoint, same session, openai/gpt-4.1-mini returns a normal completion.

Network capture — both requests hit the same URL:

POST https://dash.cloudflare.com/api/v4/accounts/<REDACTED>/ai-gateway/inference/<gateway>/compat/chat/completions

  openai/gpt-4.1-mini      → 200, normal completion
  anthropic/claude-opus-5  → 401

The Playground supplies its own authentication. No user-supplied header, API token, or provider key is involved, and BYOK is unconfigured. This isolates the fault to the Cloudflare-managed Anthropic provider credential for this account.

---

Issue 2 — Unified Billing ledger unreachable from API-token authentication

Same gateway, same /compat/chat/completions path, three requests:

#	Model	Auth	Result
A	openai/definitely-not-a-real-model	API token via cf-aig-authorization	HTTP 500 — {"error":"Model not found: ...","state":"Failed"}
B	openai/gpt-4.1-mini	API token via cf-aig-authorization	HTTP 402 — {"error":"Model execution failed (Payment error)","state":"Failed"} (610 ms)
C	openai/gpt-4.1-mini	Dashboard session (Playground)	200 — normal completion

A shows gateway authentication and routing are healthy: an invalid model is rejected at model resolution, not at auth.

C shows the credit ledger is funded and spendable: the same model on the same path completes.

B therefore cannot mean "insufficient credits." A byte-identical request to a model that demonstrably works returns a payment error solely because it was authenticated with an API token rather than a dashboard session. The token-authenticated path does not appear to resolve the account's Unified Billing ledger.

Additional account-level REST control

The documented account-level endpoint was also tested with the Cloudflare API token in Authorization and no gateway ID:

POST https://api.cloudflare.com/client/v4/accounts/<REDACTED>/ai/v1/chat/completions

openai/gpt-4.1-mini                 → HTTP 402, code 2021, "Model execution failed (Payment error)"
openai/definitely-not-a-real-model → HTTP 404, code 7003, "Model not found"

This independently confirms that account authentication and model resolution work while execution of a documented valid model fails specifically at the payment stage.

Questions

1. Is a specific API token permission required to spend Unified Billing credits? If so, it is not documented at https://developers.cloudflare.com/ai-gateway/features/unified-billing/.
2. What causes error 2021 / HTTP 402 on an account with a positive credit balance?
3. Is the Cloudflare-managed Anthropic credential provisioned correctly for accounts of this type?

Two support cases have been open since 2026-07-26 with no engineering response; the Dashboard Support Portal returns ErrorCode 41 — Cannot locate dashboard account for this account, so email is the only working channel. Happy to supply account ID, gateway IDs, request IDs, and screenshots privately.

[chenshu007]

I can independently reproduce this on a separate Cloudflare account as of 2026-08-18.

Environment / path:

• Client network: Macau (cf trace loc=MO, colo=MFM), no proxy detected
• Endpoint: POST /client/v4/accounts/{account_id}/ai/v1/chat/completions
• Model: openai/gpt-4.1-mini
• Auth: Cloudflare API Token only, no OpenAI API key / BYOK
• Gateway: default
• Unified Billing credit balance: positive (balance: 2000 from the billing credit-balance endpoint)
• Default payment method: present and valid

What I observed:

1. Initial token permissions were insufficient and returned 401 / code 10000 Authentication error.
2. After adding the required permissions, the request reached the Unified Billing path.
3. Gateway authentication was initially disabled, producing 402 / code 2021 with "Gateway authentication is required to use unified billing...".
4. After enabling gateway authentication (authentication=true), the request advanced further but consistently failed with:

{"errors":[{"message":"Model execution failed (Payment error)","code":2021}]}

I repeated the actual inference request twice, several seconds apart. Both returned HTTP 402 / code 2021. No completion or usage was returned, and the credit balance did not appear to be consumed.

Network/DNS/TLS connectivity to api.cloudflare.com was healthy, and the account/billing APIs were accessible with the same token, so this does not look like a client connectivity issue or a zero-balance case.

This looks very similar to the API-token + Unified Billing failure described in this issue. I can provide non-public request IDs / account or gateway identifiers through a private support channel if that would help engineering trace the billing path.

[ao1ao2]

Thank you very much for independently reproducing this and documenting the steps so clearly. Your findings are extremely helpful because they confirm that this is not limited to one account or caused by a zero balance or client connectivity issue. I also appreciate your offer to provide request IDs privately to Cloudflare engineering. If you discover any workaround or receive a response from Cloudflare, please let us know here. chenshu007 ***@***.***> 於 2026年8月18日週二 下午4:07寫道：

…

*chenshu007* left a comment (cloudflare/ai#632) <#632 (comment)> I can independently reproduce this on a separate Cloudflare account as of 2026-08-18. Environment / path: - Client network: Macau (cf trace loc=MO, colo=MFM), no proxy detected - Endpoint: POST /client/v4/accounts/{account_id}/ai/v1/chat/completions - Model: openai/gpt-4.1-mini - Auth: Cloudflare API Token only, no OpenAI API key / BYOK - Gateway: default - Unified Billing credit balance: positive (balance: 2000 from the billing credit-balance endpoint) - Default payment method: present and valid What I observed: 1. Initial token permissions were insufficient and returned 401 / code 10000 Authentication error. 2. After adding the required permissions, the request reached the Unified Billing path. 3. Gateway authentication was initially disabled, producing 402 / code 2021 with "Gateway authentication is required to use unified billing...". 4. After enabling gateway authentication (authentication=true), the request advanced further but consistently failed with: {"errors":[{"message":"Model execution failed (Payment error)","code":2021}]} I repeated the actual inference request twice, several seconds apart. Both returned HTTP 402 / code 2021. No completion or usage was returned, and the credit balance did not appear to be consumed. Network/DNS/TLS connectivity to api.cloudflare.com was healthy, and the account/billing APIs were accessible with the same token, so this does not look like a client connectivity issue or a zero-balance case. This looks very similar to the API-token + Unified Billing failure described in this issue. I can provide non-public request IDs / account or gateway identifiers through a private support channel if that would help engineering trace the billing path. — Reply to this email directly, view it on GitHub <#632?email_source=notifications&email_token=AF7DNGJJESF5OCINLK3PR6L5KQFFLA5CNFSNUABFM5UWIORPF5TWS5BNNB2WEL2JONZXKZKDN5WW2ZLOOQXTKMZSGUZTQOJZGIZKM4TFMFZW63VGMF2XI2DPOKSWK5TFNZ2KYZTPN52GK4S7MNWGSY3L#issuecomment-5325389922>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AF7DNGJDOWALGDCUDFGY5WT5KQFFLAVCNFSNUABFKJSXA33TNF2G64TZHM4TIOBVGAYTINJTHNEXG43VMU5TKMBWGIZTIOBRGQZKC5QC> . You are receiving this because you authored the thread.Message ID: ***@***.***>