Plan and implement with anyr task
Run a two-phase pipeline from the terminal: one model plans, a second model executes the plan.
anyr task runs a request through two models in sequence: a planning model writes a numbered plan, then an implementation model executes it. Both phases stream to your terminal and a token summary prints at the end. A strong planner with a fast, cheap implementer keeps most of the quality at lower cost.
anyr task "refactor this CSV parser to stream instead of buffering" \
--plan-model openai/gpt-5.2 \
--do-model z-ai/glm-4.7-flashBy default both phases use your profile's default model. Any id from the catalog works (anyr models lists them).
Before running, the CLI shows both models with their per-token prices and asks for confirmation, since a task makes two model calls. Without a terminal (scripts, pipes, CI) pass --yes.
--json suppresses streaming and prints one object with task, plan_model, do_model, plan, result, and usage.plan / usage.implement (prompt and completion tokens):
anyr task "summarize RFC 8628 in five bullets" --yes --json | jq -r .result| Flag | Meaning |
|---|---|
--plan-model <id> | Model for the planning phase (default: profile default model) |
--do-model <id> | Model for the implementation phase (default: profile default model) |
--yes | Skip the confirm prompt (required in non-interactive shells) |
--json | Print {plan, result, usage} as JSON instead of streaming |
--profile <name> | Use a named profile |
--key sk-ar-v1-... | Use an explicit key (or the ANYROUTER_API_KEY environment variable) |
Signed out? Run anyr auth login first (Login).
AnyRouter routes requests to third-party models. Models and outputs are provided as is, with no warranty; you use them at your own risk. Disclaimer