# Direct Model Invocation

In addition to utilizing `auto` to route between models, you can directly invoke Arcee Small Language Models and 3rd party LLMs (Claude, GPT, etc) using the Conductor API.  This makes it easy to use a large variety of models with only changing a parameter in the API request.

{% hint style="info" %}
If you're on the free plan and don't have a valid payment method on file, you will only be able to directly invoke Arcee SLMs.  To upgrade your plan reach out to <conductor@arcee.ai>.&#x20;
{% endhint %}

The models which can be directly invoked are:

<table><thead><tr><th width="119.7890625">Model</th><th width="159.9765625">API Name</th><th width="470.8046875">Description</th><th data-hidden></th></tr></thead><tbody><tr><td>Virtuoso Small</td><td>virtuoso-small</td><td>A 14B parameter SLM from Arcee AI, distilled from Deepseek V-3. Virtuoso Small is extremely performant and excels at simple tasks such as text generation and summarization.</td><td></td></tr><tr><td>Blitz</td><td>blitz</td><td>A 24B parameter SLM from Arcee AI, distilled from Deepseek V-3 Blitz offers blazing fast response times and exceptionally low costs with strong general knowledge. Ideal for simple and creative tasks.</td><td></td></tr><tr><td>Virtuoso Medium</td><td>virtuoso-medium</td><td>A 32B parameter SLM from Arcee AI, which was distilled from Deepseek V-3 giving it an impressive knowledge distribution.</td><td></td></tr><tr><td>Virtuoso Large</td><td>virtuoso-large</td><td>Arcee AI's premier 72B parameter SLM which competes with the leading LLMs on complex and analytical tasks.</td><td></td></tr><tr><td>Coder Large</td><td>coder</td><td>A 32B parameter SLM from Arcee AI fine-tuned to excel at Coding tasks.</td><td></td></tr><tr><td>Caller Large</td><td>caller-large</td><td>A 32B parameter SLM from Arcee AI fine-tuned to excel at function calling.</td><td></td></tr><tr><td>GPT-4.1</td><td>gpt-4.1</td><td>A closed-source LLM from Open AI with impressive analytical and complex problem solving capabilities.</td><td></td></tr><tr><td>Claude Sonnet 3.7</td><td>claude-3-7-sonnet-20250219</td><td>A closed-source LLM from Anthropic with strong performance on coding and complex tasks.</td><td></td></tr></tbody></table>

#### API Usage Example:

{% tabs %}
{% tab title="CURL" %}

```curl
curl -X POST https://conductor.arcee.ai/v1/chat/completions \
  -H "Authorization: Bearer $ARCEE_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
        "stream": true,
        "model": "blitz",
        "messages": [
          {
            "role": "user",
            "content": "Your prompt here"
          }
        ]
      }'
```

{% endtab %}

{% tab title="Python" %}

```python
# First, install the openai packages
# pip install openai

# Be sure to set the following environment variables
# OPENAI_BASE_URL="https://conductor.arcee.ai/v1"
# OPENAI_API_KEY="$ARCEE_TOKEN"

from openai import OpenAI

client = OpenAI()
stream = client.chat.completions.create(
  model='blitz',
  messages=[{'role': 'user', 'content': 'Your prompt here'}],
  temperature=0.4,
  stream=True
)

for chunk in stream:
    if len(chunk.choices) > 0 and chunk.choices[0].delta.content is not None:
        print(chunk.choices[0].delta.content, end="")
```

{% endtab %}
{% endtabs %}

{% hint style="info" %}
To switch the model you're invoking, simply change the "model" value from "blitz" to any of the model API names in the table above.
{% endhint %}


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.arcee.ai/arcee-conductor/features-and-functionality/direct-model-invocation.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.