LiteLLM / LiteLLM

LiteLLM Responses API Drops cache_control on Input Text Blocks, Breaks Prompt Caching

fix LiteLLM cache_control dropped / Responses API input_text cache_control not working Includes evidence for LiteLLM troubleshooting demand.

Source-backed Last updated May 15, 2026 1 source Needs local verification

Category: LiteLLM
Error signature: Responses API drops cache_control on input_text content blocks (inconsistent with tool cache_control)
Quick fix: Compare the failing environment with a known working setup, then change one configuration value at a time.
Updated: May 15, 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, 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

Responses API drops cache_control on input_text content blocks (inconsistent with tool cache_control) is a LiteLLM failure pattern reported for developers trying to fix litellm cache_control dropped / responses api input_text cache_control not working. Based on the imported evidence, treat this as a tool-specific troubleshooting page rather than a generic API error.

Why this happens

Reported 2026-05-14: cache_control on input_text silently dropped in Responses API conversion. Inconsistent behavior between content block types.

Common causes

When using OpenAI Responses API endpoint with cache_control on input_text content blocks, the cache_control field is silently dropped during conversion. This breaks prompt caching for developers using the Responses API through LiteLLM.
Reported 2026-05-14: cache_control on input_text silently dropped in Responses API conversion. Inconsistent behavior between content block types.

Quick fixes

Confirm the exact error signature matches Responses API drops cache_control on input_text content blocks (inconsistent with tool cache_control).
Check the LiteLLM 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 Responses API drops cache_control on input_text content blocks (inconsistent with tool cache_control) exactly before applying the quick fix.
Compare the failing environment with LiteLLM 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 Responses API drops cache_control on input_text content blocks (inconsistent with tool cache_control) mean in LiteLLM?

Responses API drops cache_control on input_text content blocks (inconsistent with tool cache_control) indicates the workflow described by "LiteLLM Responses API Drops cache_control on Input Text Blocks, Breaks Prompt Caching" failed in a LiteLLM context. Start by confirming the exact signature and the component that emitted it.

What should I check first for Responses API drops cache_control on input_text content blocks (inconsistent with tool cache_control)?

Check whether this cause matches your environment: When using OpenAI Responses API endpoint with cache_control on input_text content blocks, the cache_control field is silently dropped during conversion. This breaks prompt caching for developers using the Responses API through LiteLLM.

Is the Responses API drops cache_control on input_text content blocks (inconsistent with tool cache_control) guidance source-backed?

The "LiteLLM Responses API Drops cache_control on Input Text Blocks, Breaks Prompt Caching" 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 Responses API drops cache_control on input_text content blocks (inconsistent with tool cache_control)?

For "LiteLLM Responses API Drops cache_control on Input Text Blocks, Breaks Prompt Caching", 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 Responses API drops cache_control on input_text content blocks (inconsistent with tool cache_control)?

For "LiteLLM Responses API Drops cache_control on Input Text Blocks, Breaks Prompt Caching", collect the failing LiteLLM command or request, non-secret configuration, versions, timestamps, request IDs when available, and the smallest reproduction that still triggers the signature.