Introducing Ship Beta

HomeUpdatesContactDocs

Updates<br>Contact<br>Docs<br>Dashboard

Introducing Ship Beta<br>Read Article

Research

News

Company

Reducing LLM Costs 50% Using Best-Execution for Intelligence<br>July 21, 2026

Several Authors

Try Ship

CONTENTS

Ship is an endpoint that provides output indistinguishable from the model you're already using, at half the price.<br>Just replace model="" with model="ship-like/", and all requests will be 50% less expensive. We take the risk that any individual request costs us more to execute. This allows you to either (A) reduce costs on existing workflows or (B) increase quality by using more intelligence with the same budget.<br>We achieve this by doing inference-time optimization with two guarantees: capability equivalence and behavioral equivalence. Capability equivalence means that any problem solved by your original model will also be solved by Ship. Behavioral equivalence means that you don't need to change the prompt when you start using Ship; you'll get the same behavior (everything outside the capabilities, e.g. the shape of the output, average number of tool calls, instruction following, etc. remains the same).<br>By defining and measuring reference-relative quality, we can turn model quality into a contractual service level. Ship is the first endpoint to offer a quality SLA alongside its price and availability commitments.<br>This blog post lays out:<br>Evidence that Ship maintains capability equivalence and behavioral equivalence<br>The tech powering Ship: scaling Inference-Time Optimization<br>What people have built with Ship<br>Our quality SLA

Base model

GPT-5.6 Sol<br>Claude Opus 4.8

Equivalent Performance, at a fraction of the cost

System Performance: Capability Equivalence & Behavioral Equivalence<br>We make two claims, and measure each directly:<br>Capability equivalence : any problem your reference model (ref) solves, Ship also solves. Formally, 1 - P(Ship solves x | ref solves x) .<br>Behavioral equivalence : conditioned on the same input, Ship's outputs are drawn from the same distribution of behaviors as the reference model's — same output shapes, tool-use patterns, formatting, refusals, and so on. It should solve the problems equally well. Formally, distance(P_D(x, behavior(Ship(x))), P_D(x, behavior(ref(x)))) for any given distance metric and behavior.<br>This doesn't mean Ship gives literally identical outputs. Even the same language model isn't identical to itself under that definition: call the reference model twice and you get different tokens, a different number of tool calls, different phrasing. Instead, capability and behavioral equivalence is a claim about distributions: conditioned on the same input, Ship's outputs are drawn from a sufficiently similar distribution of behaviors as the reference model's.

To measure these, we use two sets of evaluations:<br>Public benchmarks, which are easily reproducible<br>Private benchmarks, which other companies run for us<br>The public benchmarks let anyone verify our results. The private benchmarks show that we haven't overfit, because they come from third parties who run real applications. This means Ship generalizes to distributions it was never trained on, constructed from real-world use. In this blog post, we detail the public benchmarks. As our partners run private benchmarks, we’ll report them as well.<br>Capability Equivalence<br>Capability equivalence asks a single question: when your reference model can solve a problem, does Ship still solve it?<br>Across a large number of benchmarks, Ship maintains the same performance as the reference model.<br>Solve rate by benchmark<br>± margin of error, with average cost per task beneath each score. Ship performance falls squarely within the margin for all benchmarks.

This also holds true for private benchmarks (see What People Have Built with Ship ).

Appendix: More On Capability Equivalence

More

A key part of capability equivalence is solving the same kinds of problems. Here. we can see that not only is the overall performance of Ship comparable to the base model, but that Ship solves the specific problems that the reference model solves.<br>Other models within each GPT-5.6 Sol solve-rate bucket<br>Tasks grouped into bands by GPT-5.6 Sol's solve rate (deep band = base solved it); within each band every column is sorted by its own solve rate. Rows are not task-aligned across columns. Under each column: its overall solve rate and correlation r with the base model.

Base model

GPT-5.6 Sol<br>Claude Opus 4.8

[[toggle-end]]

Behavioral Equivalence<br>In addition to solving the same problem, you want the problem to be solved without having to modify your prompts or harness. We call this behavioral equivalence. It matters for two reasons: (A) it guards against overfitting — a system can ace traditional benchmarks while behaving worse in ways the benchmark doesn't capture — and (B) it means you don't have to invest excessive engineering effort to use the new system. Ship was optimized for behavioral equivalence to maintain...