Quickstart

pip install opentracy

export OPENAI_API_KEY=sk-...

import opentracy as ot

resp = ot.completion(
    model="openai/gpt-4o-mini",
    messages=[{"role": "user", "content": "Say hello in three words."}],
)

print(resp.choices[0].message.content)
print(f"cost: ${resp._cost:.6f}  latency: {resp._latency_ms:.0f}ms")

Hi there, friend!
cost: $0.000008  latency: 612ms

# Anthropic
resp = ot.completion(
    model="anthropic/claude-haiku-4-5-20251001",
    messages=[{"role": "user", "content": "Say hello in three words."}],
)

# Groq (Llama, sub-second)
resp = ot.completion(
    model="groq/llama-3.3-70b-versatile",
    messages=[{"role": "user", "content": "Say hello in three words."}],
)

# DeepSeek (cheap reasoning)
resp = ot.completion(
    model="deepseek/deepseek-chat",
    messages=[{"role": "user", "content": "Say hello in three words."}],
)

resp = ot.completion(
    model="openai/gpt-4o",
    messages=[{"role": "user", "content": "Draft a pithy tagline."}],
    fallbacks=[
        "anthropic/claude-sonnet-4-6",
        "deepseek/deepseek-chat",
    ],
    num_retries=1,
)

print(resp._provider)   # which one actually answered

import opentracy as ot

router = ot.load_router(cost_weight=0.5)

for prompt in [
    "What is the capital of France?",
    "Prove the square root of 2 is irrational.",
    "Write a haiku about autumn.",
]:
    d = router.route(prompt)
    print(f"[{d.selected_model:<24}] cluster={d.cluster_id:>3}  {prompt}")

[ministral-3b-latest     ] cluster= 84  What is the capital of France?
[gpt-4o                  ] cluster= 47  Prove the square root of 2 is irrational.
[ministral-3b-latest     ] cluster= 29  Write a haiku about autumn.