# Get pricing for all models
curl -s https://openrouter.ai/api/v1/models | jq '.data[] | select(.id == "anthropic/claude-3.5-sonnet") | {
  id: .id,
  prompt_per_M: ((.pricing.prompt | tonumber) * 1000000),
  completion_per_M: ((.pricing.completion | tonumber) * 1000000),
  context: .context_length
}'
# → { "id": "anthropic/claude-3.5-sonnet", "prompt_per_M": 3, "completion_per_M": 15, "context": 200000 }

def estimate_cost(model_id: str, prompt_tokens: int, completion_tokens: int) -> float:
    """Calculate cost for a single request."""
    import requests
    models = requests.get("https://openrouter.ai/api/v1/models").json()["data"]
    model = next((m for m in models if m["id"] == model_id), None)
    if not model:
        raise ValueError(f"Model {model_id} not found")

    prompt_rate = float(model["pricing"]["prompt"])       # Cost per token
    completion_rate = float(model["pricing"]["completion"])
    return (prompt_tokens * prompt_rate) + (completion_tokens * completion_rate)

# Example: Claude 3.5 Sonnet, 1000 prompt + 500 completion tokens
cost = estimate_cost("anthropic/claude-3.5-sonnet", 1000, 500)
print(f"Estimated cost: ${cost:.6f}")  # ~$0.0105

import requests

# Method 1: From response usage (estimate)
response = client.chat.completions.create(
    model="anthropic/claude-3.5-sonnet",
    messages=[{"role": "user", "content": "Hello"}],
    max_tokens=100,
)
# response.usage.prompt_tokens, response.usage.completion_tokens

# Method 2: Query generation endpoint (exact cost from OpenRouter)
gen = requests.get(
    f"https://openrouter.ai/api/v1/generation?id={response.id}",
    headers={"Authorization": f"Bearer {os.environ['OPENROUTER_API_KEY']}"},
).json()
print(f"Exact cost: ${gen['data']['total_cost']}")
print(f"Tokens: {gen['data']['tokens_prompt']} prompt + {gen['data']['tokens_completion']} completion")

curl -s https://openrouter.ai/api/v1/auth/key \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" | jq '{
    credits_used: .data.usage,
    credit_limit: .data.limit,
    remaining: ((.data.limit // 0) - .data.usage),
    is_free_tier: .data.is_free_tier
  }'

# :floor variant picks the cheapest provider for a model
response = client.chat.completions.create(
    model="anthropic/claude-3.5-sonnet:floor",  # Cheapest provider
    messages=[{"role": "user", "content": "Hello"}],
    max_tokens=100,
)

# :free variant uses free providers (where available)
response = client.chat.completions.create(
    model="google/gemma-2-9b-it:free",
    messages=[{"role": "user", "content": "Hello"}],
    max_tokens=100,
)