> For the complete documentation index, see [llms.txt](https://docs.bullpen.fi/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.bullpen.fi/execution/jupiter-ultra-integration.md).

# Jupiter Ultra Integration

Long-tail Solana tokens on Bullpen execute through Jupiter Ultra, Jupiter's best-in-class swap infrastructure.

## What is Jupiter Ultra?

Jupiter Ultra is a meta-aggregation layer that goes beyond simple DEX aggregation. It combines quote comparison, execution simulation, MEV protection, and optimized transaction landing into a single system.

## How It Works

### 1. Quote Aggregation

Ultra queries multiple liquidity sources simultaneously:

* **Iris**: Jupiter's primary router with advanced splitting algorithms
* **JupiterZ**: Zero-slippage execution engine (\~$100M daily volume)
* **Third-party routers**: DFlow, Hashflow, OKX

### 2. Predictive Execution

Unlike simple aggregators that just show quoted prices, Ultra simulates actual execution:

1. Get quotes from all sources
2. Simulate each route onchain
3. Predict real slippage vs quoted slippage
4. Prioritize routes with best actual execution

This matters because quoted price ≠ executed price, especially with newer AMM designs.

### 3. Transaction Landing

Ultra uses **ShadowLane**, Jupiter's proprietary transaction landing engine:

* Built on Jupiter's own validator stake
* Sub-second landing (50-400ms)
* Transactions never touch external mempools
* Eliminates front-running and sandwich attacks

### 4. Execution

Final swap executes on Solana with:

* Optimized route selection
* Dynamic slippage protection
* MEV protection throughout

## Performance

| Metric               | Ultra V3                    |
| -------------------- | --------------------------- |
| Average slippage     | +0.63 bps (positive)        |
| Transaction landing  | 0-1 blocks (50-400ms)       |
| MEV extraction ratio | 34x better than competitors |

*Source: Jupiter Ultra V3 documentation*

## Real-Time Slippage Estimator (RTSE)

Ultra automatically sets appropriate slippage based on:

* Token volatility patterns
* Current liquidity depth
* Recent execution data

Benefits:

* Tighter slippage while maintaining high success rates
* Automatic prioritization of slippage-protected routes
* Token-specific heuristics

You can override with manual slippage in Bullpen's settings.

## Gasless Swaps

For trades above \~$10 USD, Ultra can cover gas fees:

* No SOL balance required
* Fee deducted from swap amount
* Works for Token2022 and memecoin-to-memecoin swaps

## Supported Tokens

Ultra routes virtually any Solana token:

* All SPL tokens with liquidity
* Pre-graduation bonding curve tokens
* Long-tail assets with minimal liquidity
* "Revived" markets that fell out of indexing

The Just-In-Time Market Revival mechanism dynamically re-indexes tokens on demand, so even old/inactive tokens can route.

## When Ultra Is Used

Bullpen routes to Jupiter Ultra when:

1. You're trading a Solana SPL token
2. The token is NOT listed on Hyperliquid spot

If the token IS listed on Hyperliquid (BTC, ETH, SOL, HYPE, etc.), it routes through UNIT instead.

## Technical Reference

For implementation details:

* [Jupiter Ultra V3 Blog Post](https://dev.jup.ag/blog/ultra-v3)
* [Jupiter Ultra API Documentation](https://dev.jup.ag/docs/ultra)


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.bullpen.fi/execution/jupiter-ultra-integration.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.