Execute understand OpenRouter pricing and cost estimation. Use when budgeting or optimizing costs. Trigger with phrases like 'openrouter pricing', 'openrouter costs', 'openrouter budget', 'openrouter token pricing'.
npxskills add jeremylongshore/claude-code-plugins-plus-skills--skill openrouter-pricing-basicsLoading…
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.
sk-or-v1-...) exported as OPENROUTER_API_KEY — see the openrouter-install-auth skill for setupcurl and jq for the model-pricing and credit-balance queriesrequests package for the cost-calculation and generation-endpoint snippets:free model(prompt_tokens * prompt_rate) + (completion_tokens * completion_rate).GET /api/v1/models per Query Model Pricing, and place candidate models in the Cost Tiers table (free → premium).estimate_cost() from Calculate Request Cost with your expected prompt/completion token counts.GET /api/v1/generation?id= per Track Actual Cost Per Request.GET /api/v1/auth/key per Check Credit Balance, and enable auto-topup for production keys.:floor and :free variants per Save Money with Variants, and check Special Pricing for reasoning tokens, image inputs, per-request fees, and BYOK.(prompt_tokens * prompt_rate) + (completion_tokens * completion_rate)GET /api/v1/auth/key or the dashboard# 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 }
| Tier | Example Model | Prompt/1M | Completion/1M | Use Case |
|---|---|---|---|---|
| Free | google/gemma-2-9b-it:free | $0.00 | $0.00 | Testing, prototyping |
| Budget | meta-llama/llama-3.1-8b-instruct | $0.06 | $0.06 | Simple Q&A, classification |
| Mid | openai/gpt-4o-mini | $0.15 | $0.60 | General purpose |
| Standard | anthropic/claude-3.5-sonnet | $3.00 | $15.00 | Complex reasoning, code |
| Premium | openai/o1 | $15.00 | $60.00 | Deep reasoning |
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,
)
| Item | Pricing |
|---|---|
| Reasoning tokens | Charged as output tokens at completion rate |
| Image inputs | Per-image charge listed in pricing.image |
| Per-request fee | Some models charge a flat fee per request (pricing.request) |
| BYOK | First 1M requests/month free; then 5% of normal provider cost |
| Free model limits | 50 req/day (free users), 1000 req/day (with $10+ credits) |
prompt_per_M, completion_per_M, context (e.g. $3 / $15 per 1M tokens for anthropic/claude-3.5-sonnet)estimate_cost() and the exact post-request figures from the generation endpoint: total_cost, tokens_prompt, tokens_completion/api/v1/auth/key: credits_used, credit_limit, remaining, is_free_tierCheck remaining credits before a batch job:
curl -s https://openrouter.ai/api/v1/auth/key \
-H "Authorization: Bearer $OPENROUTER_API_KEY" | jq '{
credits_used: .data.usage,
remaining: ((.data.limit // 0) - .data.usage)
}'
# {"credits_used": 2.34, "remaining": 47.66}
Estimating first keeps surprises out: 1,000 prompt + 500 completion tokens on anthropic/claude-3.5-sonnet comes to roughly $0.0105 via estimate_cost(), and the generation endpoint then confirms the exact charge. More worked examples: references/examples.md.
| HTTP | Cause | Fix |
|---|---|---|
| 402 | Insufficient credits | Top up at openrouter.ai/credits or use :free model |
| 402 | Key credit limit reached | Increase key limit or use a different key |
/api/v1/generation?id= after each request for exact cost auditing:floor variant to automatically pick the cheapest providermax_tokens on every request to cap completion cost
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/running secrets via op.
CLI to manage emails via IMAP/SMTP. Use `himalaya` to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/running secrets via op.
CLI to manage emails via IMAP/SMTP. Use `himalaya` to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).