OpenRouter Pricing Basics

OpenRouter Pricing Basics

Overview

OpenRouter charges per token with separate rates for prompt (input) and completion (output) tokens. Prices are listed per token in the models API (multiply by 1M for per-million rates). Credits are prepaid with a 5.5% processing fee ($0.80 minimum). Free models are available for testing and low-volume use.

How Pricing Works

1. Buy credits at openrouter.ai/​credits (5.5% fee, $0.80 minimum)
2. Each request deducts (prompt_tokens * prompt_rate) + (completion_tokens * completion_rate)
3. Check balance via GET /​api/​v1/​auth/​key or the dashboard
4. Auto-topup is available to prevent service interruption

Query Model Pricing

# 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 }

Cost Tiers (Representative)

Calculate Request Cost

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

Track Actual Cost Per Request

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")

Check Credit Balance

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
  }'

Save Money with Variants

# :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,
)

Special Pricing

Error Handling

Enterprise Considerations

• Set per-key credit limits via the dashboard or provisioning API to isolate blast radius
• Query /​api/​v1/​generation?id= after each request for exact cost auditing
• Use :floor variant to automatically pick the cheapest provider
• Route simple tasks to budget models and complex tasks to premium models (see openrouter-model-routing)
• Set max_tokens on every request to cap completion cost
• Enable auto-topup to prevent service interruptions in production

References

• Examples | Errors
• Pricing | Credits | Models API