Reactions from ranked influencers
6 posts
Really excited to see us evolve to thinking about more than just intelligence! As we develop longer flowing agentic workflows, considerations like speed and price are going to become increasingly important.
Announcing Ship: an endpoint with the highest intelligence per dollar of any frontier model. Today, Ship makes using Opus and GPT 5.6 Sol 50% cheaper guaranteed by a quality SLA.
Huge if this works as promised! Replace "model='your-favorite-model'" with "model='ship-like/your-favorite-model'" in your code. You don't need to change anything else and still get three guarantees: 1. Pay 50% less money than connecting directly to the model 2. Enjoy 100% the same capabilities 3. Enjoy 100% the same behavior Apparently, they do this using some sort of "smart routing" behind the scenes. After getting a request, they can determine: 1. How much compute to spend 2. Which model (or combination of models) to use 3. What tools, harnesses, ensembles, etc. to use 4. Which execution method to use I'm going to guess the tradeoff here would be extra latency when calling the model, but at 50% the cost, it looks like a no-brainer for most people.
Announcing Ship: an endpoint with the highest intelligence per dollar of any frontier model. Today, Ship makes using Opus and GPT 5.6 Sol 50% cheaper guaranteed by a quality SLA.
I think what’s pretty cool about Ship is that it’s finding the least expensive way to produce behavior that is effectively equivalent to frontier models. Not every request is worth the same number of tokens: the value and difficulty of inputs vary, and many requests simply do not need frontier-level reasoning. At inference time, Ship can choose how much compute a request actually deserves and which method should handle it—a model, a tool-using harness, a cascade, an ensemble, a program, or some combination. It reminds me of how we thought about introducing reasoning models with o1. Most chat experiences did not need o1; only the questions complex enough to justify the extra reasoning. The natural business model is dynamic too: price the intelligence actually used, not every request as though it required the most expensive possible system.
Announcing Ship: an endpoint with the highest intelligence per dollar of any frontier model. Today, Ship makes using Opus and GPT 5.6 Sol 50% cheaper guaranteed by a quality SLA.
Martian (@withmartian ) just launched Ship, a drop-in endpoint that replicates your model's output at a 50% lower cost. It proposes the runtime specialization of inference-time routing. Most cost tools switch you to a distinctly weaker model to save you money. Ship doesn’t seem to want to make that tradeoff because it goes after the exact abilities and behavior of your reference model. To get the same grade for cheaper, their system can blend models, tools, harnesses, cascades or ensembles. Training freezes a model before you ask for it, just like ahead-of-time compilation. Instead, Ship adds a step at runtime, which is more like a just-in-time compiler changing its focus on the fly. It all hinges on two guarantees: behavioral equivalence and capability equivalence.
Announcing Ship: an endpoint with the highest intelligence per dollar of any frontier model. Today, Ship makes using Opus and GPT 5.6 Sol 50% cheaper guaranteed by a quality SLA.
Huge if this works as promised! Replace "model='your-favorite-model'" with "model='ship-like/your-favorite-model'" in your code. You don't need to change anything else and still get three guarantees: 1. Pay 50% less money than connecting directly to the model 2. Enjoy 100% the same capabilities 3. Enjoy 100% the same behavior Apparently, they do this using some sort of "smart routing" behind the scenes. After getting a request, they can determine: 1. How much compute to spend 2. Which model (or combination of models) to use 3. What tools, harnesses, ensembles, etc. to use 4. Which execution method to use I'm going to guess the tradeoff here would be extra latency when calling the model, but at 50% the cost, it looks like a no-brainer for most people.
Announcing Ship: an endpoint with the highest intelligence per dollar of any frontier model. Today, Ship makes using Opus and GPT 5.6 Sol 50% cheaper guaranteed by a quality SLA.
Martian (@withmartian ) just launched Ship, a drop-in endpoint that replicates your model's output at a 50% lower cost. It proposes the runtime specialization of inference-time routing. Most cost tools switch you to a distinctly weaker model to save you money. Ship doesn’t seem to want to make that tradeoff because it goes after the exact abilities and behavior of your reference model. To get the same grade for cheaper, their system can blend models, tools, harnesses, cascades or ensembles. Training freezes a model before you ask for it, just like ahead-of-time compilation. Instead, Ship adds a step at runtime, which is more like a just-in-time compiler changing its focus on the fly. It all hinges on two guarantees: behavioral equivalence and capability equivalence.
Announcing Ship: an endpoint with the highest intelligence per dollar of any frontier model. Today, Ship makes using Opus and GPT 5.6 Sol 50% cheaper guaranteed by a quality SLA.