cd /news/ai-tools/codex-on-aws-bedrock-bug-causing-10x… · home topics ai-tools article
[ARTICLE · art-105410] src=github.com ↗ pub= topic=ai-tools verified=true sentiment=↓ negative

Codex on AWS bedrock bug causing 10x charges

OpenAI's Codex CLI version 0.147.0 lacks explicit cache controls for GPT-5.6 Sol on Amazon Bedrock, causing cache-write tokens to account for about 85% of estimated spend, with 171.94 million cache-write tokens costing an estimated $1,182.09 out of a total $1,386.46 over four days. The GitHub issue #37674 requests adding support for prompt_cache_options and prompt_cache_breakpoint to reduce costs for agentic coding workloads.

read2 min views1 publishedAug 21, 2026
Codex on AWS bedrock bug causing 10x charges
Image: Michielbdejong (auto-discovered)
[Notifications](/login?return_to=%2Fopenai%2Fcodex)You must be signed in to change notification settings -
[Fork 16.6k](/login?return_to=%2Fopenai%2Fcodex)

CLIIssues related to the Codex CLIIssues related to the Codex CLI

aws-bedrockIssues related to AWS Bedrock providerIssues related to AWS Bedrock provider

enhancementNew feature or requestNew feature or request

rate-limitsIssues related to rate limits, quotas, and token usage reportingIssues related to rate limits, quotas, and token usage reporting

Description #

Summary #

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 native amazon-bedrock

provider.

Environment #

  • Codex CLI: 0.147.0

  • Provider: native amazon-bedrock

  • Endpoint: Bedrock Mantle Responses API,

`us-east-1`

- Model:
`openai.gpt-5.6-sol`

Observed production usage #

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:

Requests Cache-write tokens Estimated cache-write cost Estimated total cost
3,656 171.94M $1,182.09 $1,386.46

Cache writes were about 85% of the model's estimated spend.

A local Codex session also reported 76 Sol requests with 6.709M cache_write_input_tokens

, zero cached_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.

Investigation #

Codex already emits a session-scoped prompt_cache_key

, but the request types for both HTTP and WebSocket Responses requests do not include either:

prompt_cache_options

prompt_cache_breakpoint

The built-in Amazon Bedrock provider config exposes transport/auth settings, not structured request-body transformation, so this cannot be configured through config.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.

Requested behavior #

  • Add support for serializing prompt_cache_options

for GPT-5.6-capable Responses providers. - Add a typed prompt_cache_breakpoint

field to supported input content blocks. - Provide a provider/model capability gate and a safe placement strategy at the end of Codex's measured stable instruction/tool prefix.

  • Surface cache reads and cache writes in per-turn usage telemetry so users can diagnose costly full-prefix rewrites.

Scope #

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.

Metadata #

Metadata #

Assignees

Labels

CLIIssues related to the Codex CLIIssues related to the Codex CLI

aws-bedrockIssues related to AWS Bedrock providerIssues related to AWS Bedrock provider

enhancementNew feature or requestNew feature or request

rate-limitsIssues related to rate limits, quotas, and token usage reportingIssues related to rate limits, quotas, and token usage reporting

── more in #ai-tools 4 stories · sorted by recency
── more on @openai 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/codex-on-aws-bedrock…] indexed:0 read:2min 2026-08-21 ·