reference
Models
The live catalogue is also available as JSON from GET /v1/models, which needs no authentication.
| model | context | input | output | status |
|---|---|---|---|---|
text-restyler-1 | 4,096 | $0.03 / 1M | $0.15 / 1M | Available |
prompt-optimizer-1 | 4,096 | $0.02 / 1M | $0.10 / 1M | Coming soon |
query-refiner-1 | 4,096 | $0.02 / 1M | $0.08 / 1M | Coming soon |
Restyler 1
Takes the response from any model, including Claude, Gemini, GPT and your own fine-tunes, and rewrites it so it reads the way a person writes. It is trained to hold on to facts, meaning, names, numbers, links and formatting — see the measured retention rates below. Built to sit at the end of a generation pipeline: cleaning up drafts, tightening documentation, and making machine-assembled copy readable.
Benchmarks and limits · Try it · task endpoint /v1/restyle
Prompt Optimizer 1
Takes an underspecified or rambling instruction and returns a prompt that states the task, the constraints and the expected output format, without inventing requirements the author did not have.
Coming soon. The id is already fixed, so you can write against it now, requests return 404 model_not_available until it goes live.
Query Refiner 1
Converts ambiguous or chatty questions into the search query that will actually retrieve the right documents, resolving pronouns, dropping conversational filler and surfacing the terms a retriever needs.
Coming soon. The id is already fixed, so you can write against it now, requests return 404 model_not_available until it goes live.
OpenRouter
Each model has a namespaced id reserved for a future OpenRouter listing, for example meragpt/text-restyler-1. The direct API accepts both forms, so code written against the namespaced id keeps working if you point it here.