anypick

Select the best LLM across providers using filters over capabilities, pricing, and benchmarks, then pick a winner with a strategy. anypick only selects — you wire the chosen model into your chat client.

Two implementations share the same design, fixtures, and behavior:

• anypick-python/
• anypick-ts/

Example

Python

import os
from anypick import anypick, ModelFilters

sel = anypick(
    filters=ModelFilters(
        max_prompt_price=2e-6,
        min_context_length=128_000,
        requires_tools=True,
    ),
    strategy="cheapest",
    openrouter_api_key=os.environ["OPENROUTER_API_KEY"],
)
print(sel.model.id)

TypeScript

import { anypick, ModelFilters } from "anypick";

const sel = await anypick({
  filters: new ModelFilters({
    maxPromptPrice: 2e-6,
    minContextLength: 128_000,
    requiresTools: true,
  }),
  strategy: "cheapest",
  openrouterApiKey: process.env.OPENROUTER_API_KEY,
});

console.log(sel.model.id);

Providers

anypick v1 ships two model providers; wiring differs by capability:

openrouter (the default) is the only provider with both a model catalog and benchmarks, so it supports every strategy. vercel is models-only: pair it with NoopBenchmarkObtainer, and only price-only strategies (cheapest) are meaningful — cheapest_with_floor, best_score, and best_value find no scores and behave as if every model's score is unknown.

Select a provider with the obtainer argument (or pass obtainers directly):

from anypick import anypick, ModelFilters, VercelModelObtainer, NoopBenchmarkObtainer

sel = anypick(
    filters=ModelFilters(requires_tools=True),
    strategy="cheapest",
    obtainer="vercel",   # or (VercelModelObtainer(), NoopBenchmarkObtainer())
)

Prefer fine-grained control? Pass a custom model and/or benchmark obtainer individually with model_obtainer / benchmark_obtainer — they override the corresponding side of obtainer:

from anypick import anypick, MyModelObtainer, MyBenchmarkObtainer

sel = anypick(
    filters=ModelFilters(requires_tools=True),
    model_obtainer=MyModelObtainer(),      # custom model catalog
    benchmark_obtainer=MyBenchmarkObtainer(),  # custom benchmark feed
)

Filters

Filters reduce (models, scores) to a subset before a strategy picks a winner. Build them ergonomically with ModelFilters, or as composable predicates with pred.* — both compile to the same engine.

ModelFilters fields

Everything is optional; None means "no constraint on this dimension". Clauses apply in the order listed (the order reported by NoModelsFound.survivors_by_clause).

A maker is the id prefix before the first / (e.g. "openai" for "openai/gpt-4o"). Makers without a / have no maker: a maker whitelist drops them, a blacklist leaves them alone. Sigils are preserved verbatim (OpenRouter's ~deepseek/... has maker ~deepseek).

BenchmarkThreshold narrows by source ("artificial-analysis", "openrouter", "design-arena"), task_type (coding | intelligence | agentic), and benchmark_type (a specific OpenRouter benchmark field, e.g. gpqa_diamond), with min/max on the source's native scale.

Benchmark matching: a model passes a threshold iff at least one of its scores matching the threshold's source/task_type/benchmark_type (wildcards) satisfies the bound. Unknown ≠ zero — a threshold with only source/task_type and no min/max keeps scoreless models.

Predicate form — pred.*

For negation, alternation, or custom logic, compose predicates with & (and), | (or), and ~ (not); negate a capability to forbid it:

from anypick import pred

f = (pred.maker_in(["openai", "anthropic"])
     & pred.price_below(prompt=2e-6, completion=8e-6)
     & pred.price_above(prompt=1e-7)          # skip free tier
     & pred.context_at_least(128_000)
     & pred.context_at_most(1_000_000)
     & pred.modalities_exactly(["text", "image"])
     & pred.supports_tools()
     & ~pred.supports_reasoning()              # forbid reasoning
     & pred.benchmark_above(task_type="coding", min=60))

Apply filters directly with apply_filters(models, scores, filters); pick_best and anypick call it internally. See docs/filters.md for full semantics, and docs/strategies.md for the pickers that run on the filtered set.

More

• docs/ — full design and API reference
• anypick-python/README.md
• anypick-ts/README.md