# Prompt caching

> Source: https://trigger.dev/docs/ai-chat/prompt-caching

The AI Agents and Prompts surface ships as part of the **v4.5 release candidate**. Install with `@trigger.dev/sdk@rc` (or pin `4.5.0-rc.0` or later) to use these features — they aren’t yet on the latest stable, and APIs may still change before the 4.5.0 GA. See [supported AI SDK versions](https://trigger.dev/docs/ai-chat/reference#compatibility)
 and the [AI chat changelog](https://trigger.dev/docs/ai-chat/changelog)
 for details.

**Prompt caching lets a provider reuse the unchanged prefix of your prompt across requests, billing it at a fraction of the input price and skipping re-processing.** With Anthropic, cache reads cost ~10% of base input tokens, so a long, stable system prompt or a growing conversation history pays full price once and reads cheaply on every turn after. Caching is a **byte-exact prefix match**: any change in the prefix invalidates everything after it. A multi-turn agent is the ideal case — the system prompt, tools, and earlier turns are identical turn over turn, so the cacheable prefix only grows. `chat.agent` is built to keep that prefix stable across turns, suspends, and resumes; this page shows how to place the cache breakpoints and verify they’re hitting. Caching is provider-specific. This guide covers Anthropic (`@ai-sdk/anthropic`), where you opt in per breakpoint with `providerOptions.anthropic.cacheControl`. Other providers cache differently, and most cache automatically — see [Other providers](https://trigger.dev/docs/ai-chat/prompt-caching#other-providers)
.

[​](https://trigger.dev/docs/ai-chat/prompt-caching#what-you-cache-and-where)

What you cache, and where
----------------------------------------------------------------------------------------------------------

A request renders as `tools` → `system` → `messages`. There are three prefix regions worth caching, in order:

| Region | How to cache it | Stability |
| --- | --- | --- |
| System prompt (+ tools) | `cacheControl` / `systemProviderOptions` on `chat.toStreamTextOptions()`, or `providerOptions` on `chat.prompt.set()` | Set once, never changes — the highest-value target |
| Conversation history | `prepareMessages` adds a breakpoint to the last message | Grows append-only across turns |
| Tool definitions | Stable as long as your tool set doesn’t change between turns | Render at position 0 — changing them invalidates everything |

`chat.agent` preserves `providerOptions` through message persistence and rehydration, so a breakpoint you place survives a suspend/resume or a page refresh. The recommended way to place message breakpoints is `prepareMessages` (below) rather than baking `cacheControl` into stored messages — `prepareMessages` runs on every prompt-assembly path, including after compaction, so the breakpoint is always in the right place.

[​](https://trigger.dev/docs/ai-chat/prompt-caching#cache-the-system-prompt)

Cache the system prompt
-------------------------------------------------------------------------------------------------------

The system prompt (your `chat.prompt` text plus any skills preamble) is usually the largest stable block, so it’s the first thing to cache. `chat.toStreamTextOptions()` returns `system` as a plain string by default; opt into caching and it returns a structured system message carrying the cache breakpoint instead.

System-prompt caching needs AI SDK v6 or later, where the `system` parameter accepts a structured message. On AI SDK v5 `system` is a plain string, so these options won’t apply a breakpoint to the system block — cache the conversation via `prepareMessages` instead.

Three ways to opt in, depending on where you’d rather express it. **`cacheControl` at the `streamText` call site** — the Anthropic-flavored one-liner:

/trigger/chat.ts

    import { chat } from "@trigger.dev/sdk/ai";
    import { streamText } from "ai";
    import { anthropic } from "@ai-sdk/anthropic";
    
    export const myChat = chat.agent({
      id: "my-chat",
      onChatStart: async () => {
        chat.prompt.set(SYSTEM_PROMPT); // a large, stable instruction block
      },
      run: async ({ messages, signal }) => {
        return streamText({
          model: anthropic("claude-sonnet-4-6"),
          // Caches the system block with a 5-minute breakpoint.
          ...chat.toStreamTextOptions({ cacheControl: { type: "ephemeral" } }),
          messages,
          abortSignal: signal,
        });
      },
    });
    

**`systemProviderOptions`** is the provider-agnostic form — pass the raw `providerOptions` so it composes with any provider:

/trigger/chat.ts

    return streamText({
      model: anthropic("claude-sonnet-4-6"),
      ...chat.toStreamTextOptions({
        systemProviderOptions: { anthropic: { cacheControl: { type: "ephemeral" } } },
      }),
      messages,
      abortSignal: signal,
    });
    

**`providerOptions` on `chat.prompt.set()`** co-locates the intent with where the prompt is defined. It carries through to `toStreamTextOptions()` with no call-site change:

/trigger/chat.ts

    onChatStart: async () => {
      chat.prompt.set(SYSTEM_PROMPT, {
        providerOptions: { anthropic: { cacheControl: { type: "ephemeral" } } },
      });
    },
    run: async ({ messages, signal }) => {
      return streamText({
        model: anthropic("claude-sonnet-4-6"),
        ...chat.toStreamTextOptions(), // already cached
        messages,
        abortSignal: signal,
      });
    },
    

If more than one is set, the call-site option wins: `systemProviderOptions` overrides `cacheControl`, and both override `chat.prompt.set`’s `providerOptions`. There’s no deep merge — the most specific option replaces the rest.

Use the 1-hour cache for prefixes that sit idle longer than 5 minutes between turns: `cacheControl: { type: "ephemeral", ttl: "1h" }`. Writes cost more (2× vs 1.25×), so it pays off only when reads span the longer window.

[​](https://trigger.dev/docs/ai-chat/prompt-caching#cache-the-conversation-history)

Cache the conversation history
---------------------------------------------------------------------------------------------------------------------

Place a breakpoint on the last message and the entire conversation prefix up to that point is cached, so the next turn reads it back instead of re-processing it. Do this in [`prepareMessages`](https://trigger.dev/docs/ai-chat/reference#chatagentoptions)
 — it transforms model messages once, and `chat.agent` applies it on every path that builds a prompt (each turn, and both compaction rebuild paths), so the breakpoint always lands on the real last message.

/trigger/chat.ts

    export const myChat = chat.agent({
      id: "my-chat",
      prepareMessages: async ({ messages }) => {
        if (messages.length === 0) return messages;
        const last = messages[messages.length - 1];
        return [\
          ...messages.slice(0, -1),\
          {\
            ...last,\
            providerOptions: {\
              ...last.providerOptions,\
              anthropic: { cacheControl: { type: "ephemeral" } },\
            },\
          },\
        ];
      },
      run: async ({ messages, signal }) => {
        return streamText({
          model: anthropic("claude-sonnet-4-6"),
          ...chat.toStreamTextOptions({ cacheControl: { type: "ephemeral" } }),
          messages,
          abortSignal: signal,
        });
      },
    });
    

The system breakpoint and the conversation breakpoint compose: the system block is cached once for the life of the chat, and each turn extends the cached message prefix.

Anthropic allows **at most 4** cache breakpoints per request, and a prefix must be at least ~1024 tokens (model-dependent) to cache at all — shorter prefixes silently don’t cache. One system breakpoint plus one rolling message breakpoint is the typical setup and leaves headroom.

[​](https://trigger.dev/docs/ai-chat/prompt-caching#caching-and-compaction)

Caching and compaction
-----------------------------------------------------------------------------------------------------

Compaction rewrites the conversation prefix — it replaces earlier turns with a summary — so it necessarily invalidates the cached message prefix at that point. That’s a one-time reset, not a regression: because `prepareMessages` also runs on the compaction rebuild and result paths, the new (shorter) prefix gets a fresh breakpoint and re-warms on the next turn. Your system-prompt cache is unaffected — compaction never touches the system block. See [Compaction](https://trigger.dev/docs/ai-chat/compaction)
 for how the summary is produced.

[​](https://trigger.dev/docs/ai-chat/prompt-caching#other-providers)

Other providers
---------------------------------------------------------------------------------------

Caching is provider-specific, and most providers don’t use per-block breakpoints at all:

*   **OpenAI** and **Google Gemini** cache automatically. OpenAI caches any prompt prefix over 1024 tokens; Gemini 2.5 caches implicitly (1024 tokens on Flash, 2048 on Pro). Neither needs a breakpoint, so the system-caching options above are a no-op for them — `chat.agent` already gives automatic caching exactly what it needs: a byte-stable prefix that only grows across turns. Keep the system prompt frozen and the prefix over the model’s minimum and reads happen on their own. (OpenAI’s optional `providerOptions.openai.promptCacheKey` improves hit-routing across requests; it’s a top-level option, not a system-block breakpoint.)
*   **Anthropic** and **Amazon Bedrock** take an explicit breakpoint on the system block — Anthropic via `cacheControl`, Bedrock via `cachePoint`. Both go through the provider-agnostic `systemProviderOptions`:

/trigger/chat.ts

    // Amazon Bedrock
    return streamText({
      ...chat.toStreamTextOptions({
        systemProviderOptions: { bedrock: { cachePoint: { type: "default" } } },
      }),
      messages,
    });
    

The `cacheControl` shorthand is Anthropic-only; `systemProviderOptions` (and `chat.prompt.set`’s `providerOptions`) is the form to reach for on any other breakpoint-based provider. Usage reporting is normalized. Each provider reports cache tokens under its own provider-specific field, but the AI SDK maps them into the same `inputTokenDetails.cacheReadTokens` / `cacheWriteTokens` that `previousTurnUsage` and `totalUsage` carry and the dashboard shows — so the [verify step](https://trigger.dev/docs/ai-chat/prompt-caching#verify-caching-is-working)
 is the same regardless of provider.

[​](https://trigger.dev/docs/ai-chat/prompt-caching#verify-caching-is-working)

Verify caching is working
-----------------------------------------------------------------------------------------------------------

The turn’s usage carries cache token counts. `chat.agent` accumulates them across turns and hands them to `run` as `previousTurnUsage` (last turn) and `totalUsage` (whole chat), both `LanguageModelUsage`:

/trigger/chat.ts

    run: async ({ messages, signal, previousTurnUsage }) => {
      // After turn 1, cacheReadTokens should be > 0 on a stable prefix.
      console.log("cache read", previousTurnUsage?.inputTokenDetails?.cacheReadTokens);
      console.log("cache write", previousTurnUsage?.inputTokenDetails?.cacheWriteTokens);
    
      return streamText({
        model: anthropic("claude-sonnet-4-6"),
        ...chat.toStreamTextOptions({ cacheControl: { type: "ephemeral" } }),
        messages,
        abortSignal: signal,
      });
    },
    

The first turn writes the cache (`cacheWriteTokens > 0`, `cacheReadTokens` is 0). Every turn after, on an unchanged prefix, reads it (`cacheReadTokens > 0`). The dashboard surfaces the same numbers on the AI span as **Cache write** and **Cache read**, so you can confirm hits per run without logging. If `cacheReadTokens` stays 0 across turns with an identical prefix, a silent invalidator is shifting the bytes — see below.

Anything that changes the prefix between turns silently kills the cache. Keep the system prompt **byte-stable** — never interpolate a timestamp, request ID, or per-turn value into `chat.prompt`. Don’t change the **model** or the **tool set** mid-conversation (tools render at position 0, so adding one invalidates everything after). Inject dynamic per-turn context as a late message via [pending messages](https://trigger.dev/docs/ai-chat/pending-messages)
 or [background injection](https://trigger.dev/docs/ai-chat/background-injection)
, not into the cached prefix.

[​](https://trigger.dev/docs/ai-chat/prompt-caching#next-steps)

Next steps
-----------------------------------------------------------------------------

[Compaction\
----------\
\
Keep long conversations within token limits — and re-warm the cache after.](https://trigger.dev/docs/ai-chat/compaction)

[Fast starts\
-----------\
\
Cut cold-start latency so a cached prefix is the only thing between a message and a reply.](https://trigger.dev/docs/ai-chat/fast-starts)

[chat.agent reference\
--------------------\
\
Full option surface, including `prepareMessages` and `toStreamTextOptions`.](https://trigger.dev/docs/ai-chat/reference#chatagentoptions)

[Building agents: backend\
------------------------\
\
The three ways to build a chat backend and when to reach for each.](https://trigger.dev/docs/ai-chat/backend)

Was this page helpful?

YesNo

[Previous](https://trigger.dev/docs/ai-chat/compaction)
[Pending MessagesInject user messages mid-execution to steer agents between tool-call steps.\
\
Next](https://trigger.dev/docs/ai-chat/pending-messages)

Ctrl+I

Assistant

Responses are generated using AI and may contain mistakes.