技能 编程开发 OpenRouter费用计算与成本优化

OpenRouter费用计算与成本优化

v20260423
openrouter-pricing-basics
本技能旨在指导用户全面掌握OpenRouter的API计费体系。它详细讲解了如何根据Prompt和Completion Token计算准确成本,并提供了实用代码示例,用于估算费用、检查账户余额,以及使用`:floor`或`:free`等变体进行成本优化。适用于预算规划、成本控制和生产环境的资源管理。
获取技能
146 次下载
概览

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)

TierExample ModelPrompt/1MCompletion/1MUse Case
Freegoogle/gemma-2-9b-it:free$0.00$0.00Testing, prototyping
Budgetmeta-llama/llama-3.1-8b-instruct$0.06$0.06Simple Q&A, classification
Midopenai/gpt-4o-mini$0.15$0.60General purpose
Standardanthropic/claude-3.5-sonnet$3.00$15.00Complex reasoning, code
Premiumopenai/o1$15.00$60.00Deep reasoning

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

ItemPricing
Reasoning tokensCharged as output tokens at completion rate
Image inputsPer-image charge listed in pricing.image
Per-request feeSome models charge a flat fee per request (pricing.request)
BYOKFirst 1M requests/month free; then 5% of normal provider cost
Free model limits50 req/day (free users), 1000 req/day (with $10+ credits)

Error Handling

HTTPCauseFix
402Insufficient creditsTop up at openrouter.ai/credits or use :free model
402Key credit limit reachedIncrease key limit or use a different key

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

信息
分类 编程开发
名称 openrouter-pricing-basics
版本 v20260423
大小 7.57KB
更新时间 2026-09-06
语言