---
title: "Response cache and context compression for agents"
canonical: https://relayswitch.io/features/caching
generated: 2026-11-02T10:04:27.301Z
source: https://api.relayswitch.io/v1/catalog
base_url: https://api.relayswitch.io/v1
---

Caching and compression

# Pay a tenth for the repeat. Never hit the context wall.

Turn on the response cache and an exact repeat comes back from the cache for a tenth of its charge. Add middle-out and an agent history that outgrows the context window is trimmed from the middle instead of failing.

[Get an agent key](https://app.relayswitch.io/console)[Code](#example)

One repeat on Claude Sonnet 5.5, live

6,000 in, 600 out

$0.009000

The same request, cache hit

$0.000900

Kept by default

300 s

Longest TTL

86,400 s

## What it does for an agent

Response cache

x-uplink-cache: on answers an exact repeat from your organization’s cache, billed a tenth of the original.

You set the TTL

60 seconds to a day per request, or a default on the key. x-uplink-cache-clear forces a fresh answer.

Headers that explain it

HIT, MISS or BYPASS, the TTL left, the age of the answer and the request that paid for it.

Middle-out compression

transforms: \["middle-out"\] drops whole messages from the middle when a prompt is longer than the window.

Tool calls stay paired

A tool call and its results are dropped together, so the agent never sees a dangling result.

Prompt caching too

Cached input bills at each model’s cached rate, and large shared system prompts can get a cache breakpoint.

## Copy, paste, run

OpenAI SDK: cache on

python

1`from openai import OpenAI`

2`import os`

3

4`client = OpenAI(`

5 `base_url="https://api.relayswitch.io/v1",`

6 `api_key=os.environ["RELAYSWITCH_API_KEY"],`

7`)`

8

9`reply = client.chat.completions.create(`

10 `model="gpt-6.1-sol",`

11 `messages=[{"role": "system", "content": SYSTEM_PROMPT},`

12 `{"role": "user", "content": "Classify: refund request #1182"}],`

13 `extra_headers={"x-uplink-cache": "on", "x-uplink-cache-ttl": "3600"},`

14`)`

15`# x-uplink-cache: HIT on an exact repeat within the hour, billed a tenth`

Anthropic SDK: middle-out

python

1`import anthropic`

2`import os`

3

4`client = anthropic.Anthropic(`

5 `base_url="https://api.relayswitch.io/v1",`

6 `api_key=os.environ["RELAYSWITCH_API_KEY"],`

7`)`

8

9`reply = client.messages.create(`

10 `model="claude-sonnet-5-5",`

11 `max_tokens=2048,`

12 `messages=long_agent_history, # longer than the context window`

13 `extra_body={"transforms": ["middle-out"]},`

14`)`

15`# x-uplink-compressed: how many middle messages were dropped`

curl: a miss, then a hit

bash

1`curl -i https://api.relayswitch.io/v1/chat/completions \`

2 `-H "Authorization: Bearer $RELAYSWITCH_API_KEY" \`

3 `-H "x-uplink-cache: on" \`

4 `-H "Content-Type: application/json" \`

5 `-d '{"model": "gpt-6.1-sol", "messages": [{"role": "user", "content": "Capital of Peru?"}]}'`

6`# First call: x-uplink-cache: MISS x-uplink-cache-ttl: 300`

7`# Repeat: x-uplink-cache: HIT x-uplink-cache-age: 12`

8`# x-uplink-cache-source-id: the request that paid for it`

Key API: both on by default

bash

1`# Cache on by default for 10 minutes and middle-out on overflow, for this key.`

2`curl -X PATCH https://api.relayswitch.io/v1/keys/KEY_ID \`

3 `-H "Authorization: Bearer $ADMIN_KEY" -H "Content-Type: application/json" \`

4 `-d '{"response_cache_ttl": 600, "context_overflow": "middle-out"}'`

## Input, cached input and output, live

USD per million tokens from GET /v1/catalog. A response-cache hit bills a tenth of the original charge instead.

| Model | Input | Cached input | Output |
| --- | --- | --- | --- |
| [Claude Opus 5.5](https://relayswitch.io/models/claude-opus-5-5) | $2.80 | $0.15 | $10.00 |
| [Claude Sonnet 5.5](https://relayswitch.io/models/claude-sonnet-5-5) | $1.20 | $0.075 | $3.00 |
| [GPT-6.1 Sol](https://relayswitch.io/models/gpt-6.1-sol) | $0.60 | $0.06 | $3.00 |
| [Gemini 3.1 Pro Preview](https://relayswitch.io/models/gemini-3.1-pro-preview) | $1.20 | $0.12 | $7.20 |
| [DeepSeek V4.1 Flash](https://relayswitch.io/models/deepseek-v4.1-flash) | $0.06 | $0.0063 | $0.18 |
| [Kimi K3](https://relayswitch.io/models/kimi-k3) | $0.90 | $0.12 | $4.50 |
| [GLM 5.3](https://relayswitch.io/models/glm-5.3) | $0.3276 | $0.068 | $1.0296 |

Agent setup guides

-   [OpenClaw](https://relayswitch.io/guides/openclaw)
-   [Hermes Agent](https://relayswitch.io/guides/hermes-agent)
-   [OpenCode](https://relayswitch.io/guides/opencode)
-   [Claude Code](https://relayswitch.io/guides/claude-code)
-   [n8n](https://relayswitch.io/guides/n8n)

More features

-   [Agent tools](https://relayswitch.io/features/agent-tools)
-   [Files and redaction](https://relayswitch.io/features/files)
-   [Routing](https://relayswitch.io/features/routing)
-   [Guardrails and sign-in](https://relayswitch.io/features/guardrails)
-   [MCP gateway](https://relayswitch.io/features/mcp-gateway)
-   [Endpoints](https://relayswitch.io/features/endpoints)
-   [Key budgets](https://relayswitch.io/features/key-budgets)
-   [Observability](https://relayswitch.io/features/observability)
-   [Hosted agents](https://relayswitch.io/agents)
-   [Workflows](https://relayswitch.io/workflows)
-   [Docs](https://relayswitch.io/docs)

FAQs

## Questions

For agent builders.

Open the console

A key in under a minute

[Get a key](https://app.relayswitch.io/console)

Or email [hello@relayswitch.io](mailto:hello@relayswitch.io)

### 

### 

### 

### 

### 

### 

## Stop paying twice for the same answer

Cache and compression are opt-in headers or key defaults, on any key.

[All features](https://relayswitch.io/features)[Get an agent key](https://app.relayswitch.io/console)