I'm guessing you mainly think of planning and maybe review when you say that Opus and GPT vary in their output. This is more of a qualitative judgment because it's difficult to write a planning benchmark. If you wanted planning to pass between both of these generalist models, role-model supports this via the pi-role-model extension for Pi that lets the coding agent send request metadata, define routing strategy to use and even model ID.
To implement it, you would make a rule for Pi to do another pass for any coder.planning task that it sends to the role-model router.
These types of personalizations are suited for implementation in the consumer application layer instead of in the router in my opinion.
Feel free to take a look at the docs for how routing decisions are made: https://role-model.dev/
When you use Pi with pi-role-model, Pi will include task and role metadata with its request; the role-model router runtime additionally holds benchmark and observability data, and a configured routing strategy. A composite of this is used to make the decision.
What you are pointing out is correct: making the actual decision and ensuring it is accurate can be difficult, which is why you need rich data as above, and also a model pool where each model is distinct, as I wrote in this post and in one of the comments below.
This is an interesting comment because it makes me want to ask the question, what is the use for fable then? For me, GPT 5.4 is enough when using recursive-mode. I do appreciate GPT 5.5 Pro for some larger research, architecture, planning tasks though. I think that's what Fable is for. A very small % of total work.
I can add to the above that an accurate model router is what enables specialist models, and specialist models is what will in turn make model routing common place.
When we have a standard model routing protocol in place used by both applications and providers, we can start to really reap immense benefits from accurate routing and fine-tuned specialist models resulting in better performance and lower cost.
I am European, working in China for 12 years making multiples of the average salary, speak Chinese above B1 level and am not eligible for permanent residency yet.
First of all, if you want to become a resident somewhere you must learn the language. Not should.
Second, no country owes any foreign citizen residency there.
If we define GPT 5.5 and Opus 4.8 as the frontier models for simplicity, there is some value in routing between them theoretically because two models will always have some differences.
However, when the models have the same generalist profile capabilities and are at the same performance and cost tier, making a decision for when to route between them and also making sure that that decision is correct, requires enormously granular information. While there are benchmarks that show differences between the models across different domains and tasks, the differences are generally not major and we also cannot assume that benchmarks that we know are optimized for, because if the new model wasn't presented together with good benchmarks the business would tank, really reflect real-world task performance at the request-level.
So routing between similar models is an information problem that is unlikely to be solved.
Routing between these two models is also likely to have a lower benefit than routing between GPT and DeepSeek on the cost vector. Routing to DS has clear, known and verifiable impact on cost. There is no need to guess.
Similarly, if we routed between GPT and a specialized math model, lets say Leanstral, that we can assume outperforms GPT by >50%, the benefits are also massively larger, and the routing decisions are also easy to make.
This is why the biggest pay offs come from routing between models that have a 2-10x difference in one of the cost-speed-quality factors, or specialized in a specific domain, or runs locally for data-security sensitive work.
Different but related: When you use a Codex subscription in an agent like Pi or OpenCode, all the requests and tool call execution go through a sandbox owned by Codex app server, and all the tool calls function somewhat differently, and you can't read files outside of the sandbox as easily. It's currently tripping me up a bit when building a model router.
We should probably only interact with the agent by writing to the log, which it executes from, and the agent should probably only interact with the external environment by writing and executing code. That fixes a lot of issues with non-determinism.
yeah but it was on the frontpage and quite popular last time! and the timestamp on the comments changed too, to be relative to the new "posted" timestamp.
For this to work there needs to be a standard protocol for model routing so that you as the user can decide where requests go. You may wish to use mainly local models but at some times for some tasks you'll need to route requests to cloud models.
I've designed the role-model protocol for this, allowing routing between any model, however to function optimally it needs consumer applications to use the protocol when sending requests: https://role-model.dev/concepts/how-role-model-works
You can do this with role-model, the model router I've built. It routes based on roles and tasks among other things. It has an extension for Pi that lets your coding agent specify request metadata for roles and capabilities etc.
https://x.com/trydotworks