Native Codex CLI requests to Amazon Bedrock Mantle cannot opt into GPT-5.6 Sol explicit prompt caching. On an agentic coding workload, this has produced a large volume of cache-write tokens and materially higher cost.
This is related to#35300, but adds independent production usage evidence from the nativeamazon-bedrockprovider.
For the completed days 2026-08-05 through 2026-08-08, Cost Explorer usage quantities and the Bedrock rate card produced the following cache-aware estimate for Sol:
Cache writes were about 85% of the model’s estimated spend.
A local Codex session also reported 76 Sol requests with 6.709Mcache_write_input_tokens, zerocached_input_tokens, and an average of about 88K cache-write tokens per request. There were no client errors in the corresponding CloudWatch metrics.
These are usage-derived estimates, not finalized AWS invoice amounts.
Codex already emits a session-scopedprompt_cache_key, but the request types for both HTTP and WebSocket Responses requests do not include either:
The built-in Amazon Bedrock provider config exposes transport/auth settings, not structured request-body transformation, so this cannot be configured throughconfig.toml.
AWS documents explicit cache mode for GPT-5.6 on Bedrock specifically for agentic workflows with long stable instructions/tool definitions followed by changing tool and user content. That matches the workload above.
This report does not claim that every cache write is a defect. Cold starts, genuinely distinct prompts, forks, and compaction can all require writes. The issue is that native Bedrock Codex currently has no way to use the documented explicit-cache mechanism for the stable-prefix case.