LiteLLM / Anthropic API / LiteLLM

LiteLLM Responses API Drops cache_control on input_text Content Blocks

Fix LiteLLM cache_control not forwarding to Anthropic when using Responses API Includes evidence for LiteLLM / Anthropic API troubleshooting demand.

Source-backed Last updated May 14, 2026 1 source Needs local verification

Category: LiteLLM
Error signature: LiteLLM Responses API silently drops cache_control on input_text content blocks during transformation
Quick fix: Compare the failing environment with a known working setup, then change one configuration value at a time.
Updated: May 14, 2026
Verification status: Source-backed
Evidence: 1 public source URL

Before you change production

This page includes public source URLs in the imported troubleshooting record. Compare those references with your version and environment before applying changes.

Reproduce the smallest failing action and save non-secret logs before changing configuration.
Check versions for LiteLLM / Anthropic API, related SDKs, package managers, CI runners, and hosting providers.
Change one setting or dependency at a time, then rerun the same failing command or request.
Avoid destructive commands, credential rotation, billing changes, or security relaxations without a rollback plan.

What this error means

LiteLLM Responses API silently drops cache_control on input_text content blocks during transformation is a LiteLLM / Anthropic API failure pattern reported for developers trying to fix litellm cache_control not forwarding to anthropic when using responses api. Based on the imported evidence, treat this as a tool-specific troubleshooting page rather than a generic API error.

Why this happens

Bug confirmed in litellm v1.83.14. In _transform_responses_api_content_to_chat_completion_content(), input_text handler builds output dict with only type and text, ignoring cache_control. Tools correctly preserve cache_control at lines ~1400-1401.

Common causes

Prompt caching directives sent via Responses API are silently lost, causing higher API costs and slower responses. Tools correctly preserve cache_control but text content does not.
Bug confirmed in litellm v1.83.14. In _transform_responses_api_content_to_chat_completion_content(), input_text handler builds output dict with only type and text, ignoring cache_control. Tools correctly preserve cache_control at lines ~1400-1401.

Quick fixes

Confirm the exact error signature matches LiteLLM Responses API silently drops cache_control on input_text content blocks during transformation.
Check the LiteLLM / Anthropic API account, local tool state, and provider configuration involved in the failing workflow.
Compare the failing environment with a known working setup, then change one configuration value at a time.

Platform/tool-specific checks

Verify the command, editor, extension, or API client that produced the error.
Compare local settings with CI, deployment, or editor-level settings when the error appears in only one environment.
Avoid deleting credentials, local model data, or project settings until the failing scope is clear.

Step-by-step troubleshooting

Capture the exact error message and the command, editor action, or request that triggered it.
Check whether the failure is account/auth, quota/rate, model/provider, local runtime, or deployment configuration.
Review the source evidence below and compare it with your environment.
Apply one change at a time and rerun the smallest failing action.
Keep the working fix documented for the team or deployment environment.

How to prevent it

Keep provider/tool configuration documented.
Record non-secret diagnostics such as tool version, provider name, model name, and command path.
Add a lightweight check before CI or production workflows depend on the tool.

Diagnostic flow for this page

Match LiteLLM Responses API silently drops cache_control on input_text content blocks during transformation exactly before applying the quick fix.
Compare the failing environment with LiteLLM / Anthropic API versions, account scope, provider settings, and deployment context.
Check the listed common causes in order, starting with the cause that best matches your logs.
Use the evidence status below to decide whether to confirm against public sources or official documentation.
Apply one reversible change, rerun the smallest failing action, and keep rollback notes.

FAQ

What does LiteLLM Responses API silently drops cache_control on input_text content blocks during transformation mean in LiteLLM / Anthropic API?

LiteLLM Responses API silently drops cache_control on input_text content blocks during transformation indicates the workflow described by "LiteLLM Responses API Drops cache_control on input_text Content Blocks" failed in a LiteLLM context. Start by confirming the exact signature and the component that emitted it.

What should I check first for LiteLLM Responses API silently drops cache_control on input_text content blocks during transformation?

Check whether this cause matches your environment: Prompt caching directives sent via Responses API are silently lost, causing higher API costs and slower responses. Tools correctly preserve cache_control but text content does not.

Is the LiteLLM Responses API silently drops cache_control on input_text content blocks during transformation guidance source-backed?

The "LiteLLM Responses API Drops cache_control on input_text Content Blocks" page is labeled source-backed. It has 1 public source URL from github.com, so use that evidence status when deciding how much additional verification you need.

When should I avoid the quick fix for LiteLLM Responses API silently drops cache_control on input_text content blocks during transformation?

For "LiteLLM Responses API Drops cache_control on input_text Content Blocks", avoid applying "Compare the failing environment with a known working setup, then change one configuration value at a time." when the error text differs, the affected version or provider is different, or the change would touch credentials, billing, DNS, production deploy settings, or irreversible data.

What should I collect before debugging LiteLLM Responses API silently drops cache_control on input_text content blocks during transformation?

For "LiteLLM Responses API Drops cache_control on input_text Content Blocks", collect the failing LiteLLM / Anthropic API command or request, non-secret configuration, versions, timestamps, request IDs when available, and the smallest reproduction that still triggers the signature.