Send your first request

curl https://api-router.aetron.io/v1/chat/completions \
  -H "Authorization: Bearer $AETRON_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "aetron/qwen3.5-9b-gguf-q4-k-m",
    "messages": [{ "role": "user", "content": "hi" }]
  }'

curl https://api-router.aetron.io/v1/models -H "Authorization: Bearer $AETRON_KEY"

curl https://api-router.aetron.io/v1/messages \
  -H "Authorization: Bearer $AETRON_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "aetron/qwen3.5-9b-gguf-q4-k-m",
    "max_tokens": 512,
    "system": "You are terse.",
    "messages": [{ "role": "user", "content": "hi" }]
  }'

stream = client.chat.completions.create(
    model="aetron/qwen3.5-9b-gguf-q4-k-m",
    messages=[{"role": "user", "content": "write a haiku"}],
    stream=True,
    stream_options={"include_usage": True},
)
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)
    if chunk.usage:
        print("\n", chunk.usage.total_tokens, "tokens")

tools = [{
    "type": "function",
    "function": {
        "name": "get_weather",
        "description": "Current weather for a city",
        "parameters": {
            "type": "object",
            "properties": {"city": {"type": "string"}},
            "required": ["city"],
        },
    },
}]

r = client.chat.completions.create(
    model="aetron/qwen3.5-9b-gguf-q4-k-m",
    messages=[{"role": "user", "content": "Weather in Lisbon?"}],
    tools=tools,
)
call = r.choices[0].message.tool_calls[0]
# run get_weather(**json.loads(call.function.arguments)), then continue:
# messages += [r.choices[0].message, {"role": "tool", "tool_call_id": call.id, "content": "..."}]