> ## Documentation Index
> Fetch the complete documentation index at: https://docs.aevyra.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Providers & Models

> Choose which LLM powers Origin's attribution engine.

Origin uses one LLM for attribution — the model that reads the trace, the score,
and the rubric, and returns the ranked culprit list. This is different from the
model your agent pipeline runs on, which Origin does not control.

## Default: Anthropic Claude

Claude is included when you `pip install aevyra-origin`. No extra flags needed.

```bash theme={null}
pip install aevyra-origin
export ANTHROPIC_API_KEY=sk-ant-...
```

The default model is `claude-sonnet-4-5`. It's fast, capable, and well-suited
to the diagnostic reasoning Origin requires.

## Provider format

Models are specified as `provider/model` — the same convention as aevyra-reflex:

```python theme={null}
from aevyra_origin.llm import anthropic_llm, openai_llm

llm = anthropic_llm(model="claude-sonnet-4-5")          # Anthropic
llm = openai_llm(model="gpt-4o")                        # OpenAI
llm = openai_llm(model="qwen/qwen3-8b",                 # OpenRouter
                 base_url="https://openrouter.ai/api/v1",
                 api_key=os.environ["OPENROUTER_API_KEY"])
llm = openai_llm(model="qwen3:8b",                      # Ollama (local)
                 base_url="http://localhost:11434/v1",
                 api_key="ollama")  # pragma: allowlist secret
```

## Provider reference

| Provider        | Extra        | Env var              |
| --------------- | ------------ | -------------------- |
| **Anthropic**   | *(included)* | `ANTHROPIC_API_KEY`  |
| **OpenAI**      | `[openai]`   | `OPENAI_API_KEY`     |
| **OpenRouter**  | `[openai]`   | `OPENROUTER_API_KEY` |
| **Together AI** | `[openai]`   | `TOGETHER_API_KEY`   |
| **Groq**        | `[openai]`   | `GROQ_API_KEY`       |
| **Ollama**      | `[openai]`   | —                    |

```bash theme={null}
pip install aevyra-origin[openai]   # adds OpenAI-compatible providers
pip install aevyra-origin[all]      # everything
```

## CLI provider format

The CLI uses `provider/model` strings via `--model`:

```bash theme={null}
aevyra-origin diagnose trace.json --score 0.4 --rubric rubric.txt \
  --model anthropic/claude-sonnet-4-5

aevyra-origin diagnose trace.json --score 0.4 --rubric rubric.txt \
  --model openrouter/qwen/qwen3-8b

aevyra-origin diagnose trace.json --score 0.4 --rubric rubric.txt \
  --model ollama/qwen3:8b
```

Bare model names are also accepted — `claude-sonnet-4-5` infers `anthropic`,
anything else infers `openai`.

## Choosing a model

For most traces, a mid-tier model like `claude-sonnet-4-5` or `gpt-4o` is
sufficient. Use a stronger model (`claude-opus-4-6`) when the trace is long
or the rubric has many competing criteria. For quick debugging runs, a fast
local model (Ollama `qwen3:8b`) works well.

Attribution quality depends more on clear rubric writing than on model choice —
a specific, criterion-by-criterion rubric outperforms a vague one regardless
of model.