OpenRouter Pricing Calculator & Complete Cost Guide
Calculate OpenRouter API costs for 315+ models. Compare per-token pricing across Claude, GPT, Gemini, DeepSeek, and more.
Pricing TLDR
- • Pay-per-token with no monthly fees — add credits and use any model
- • 315+ models from Anthropic, OpenAI, Google, DeepSeek, Meta, and more
- • Free models available with rate limits • OpenAI-compatible API
OpenRouter Cost Calculator - Monthly Pricing
Calculate by
Input Tokens
Output Tokens
API Calls / Month
Quick Examples:
Sort:
(openai/gpt-5.5)
Context
Quality
Per 1M Tokens
In: $5.00
Out: $30.00
Monthly Cost
(google/gemini-3.1-pro-preview)
Context
Quality
Per 1M Tokens
In: $2.00
Out: $12.00
Monthly Cost
(anthropic/claude-opus-4.7)
Context
Quality
Per 1M Tokens
In: $5.00
Out: $25.00
Monthly Cost
(openai/gpt-5.4)
Context
Quality
Per 1M Tokens
In: $2.50
Out: $15.00
Monthly Cost
(google/gemini-3.5-flash)
Context
Quality
Per 1M Tokens
In: $1.50
Out: $9.00
Monthly Cost
(moonshotai/kimi-k2.6)
Context
Quality
Per 1M Tokens
In: $0.73
Out: $3.49
Monthly Cost
(x-ai/grok-4.3)
Context
Quality
Per 1M Tokens
In: $1.25
Out: $2.50
Monthly Cost
(deepseek/deepseek-v4-pro)
Context
Quality
Per 1M Tokens
In: $0.44
Out: $0.87
Monthly Cost
(anthropic/claude-sonnet-4.6)
Context
Quality
Per 1M Tokens
In: $3.00
Out: $15.00
Monthly Cost
(openai/gpt-5.4-mini)
Context
Quality
Per 1M Tokens
In: $0.75
Out: $4.50
Monthly Cost
(deepseek/deepseek-v4-flash)
Context
Quality
Per 1M Tokens
In: $0.10
Out: $0.20
Monthly Cost
(google/gemini-3-flash-preview)
Context
Quality
Per 1M Tokens
In: $0.50
Out: $3.00
Monthly Cost
(openai/gpt-5.4-nano)
Context
Quality
Per 1M Tokens
In: $0.20
Out: $1.25
Monthly Cost
(mistralai/mistral-medium-3-5)
Context
Quality
Per 1M Tokens
In: $1.50
Out: $7.50
Monthly Cost
(anthropic/claude-haiku-4.5)
Context
Quality
Per 1M Tokens
In: $1.00
Out: $5.00
Monthly Cost
(meta-llama/llama-3.3-70b-instruct)
Context
Quality
Per 1M Tokens
In: $0.10
Out: $0.32
Monthly Cost
Spending across 315+ OpenRouter models?
Monitor your OpenRouter credits and usage in real-time.
Privacy-first desktop app. No sign-up required.
About OpenRouter
What is OpenRouter?
OpenRouter is a unified API gateway that provides access to 315+ AI models from every major provider — Anthropic, OpenAI, Google, DeepSeek, Meta, Mistral, xAI, and more — through a single, OpenAI-compatible API. Instead of managing separate API keys and billing for each provider, you use one API key and one credit balance.
- 315+ Models, One API Key: Access Claude, GPT, Gemini, DeepSeek, Llama, Grok, and hundreds more through a single endpoint. Switch models by changing one parameter — no code changes needed.
- OpenAI-Compatible API: Drop-in replacement for the OpenAI API. Change the base URL and API key in your existing code — everything else works unchanged. Compatible with all OpenAI SDKs.
- Pay-Per-Token, No Commitments: Add credits to your account and pay only for what you use. No monthly fees, no minimum spend. Free models available with rate limits for testing and light usage.
When to Use OpenRouter
OpenRouter is ideal when you need access to multiple AI providers without managing separate accounts, or when you want to easily compare and switch between models.
Ideal for
- Teams using multiple AI models across different providers
- Rapid prototyping and model comparison across providers
- Applications needing fallback routing between models
- Developers who want one API key for all AI models
- Projects that need access to niche or specialized models
Not ideal for
- Enterprise workloads needing direct provider SLAs
- Applications requiring provider-specific features (batch API, caching)
- Cost-sensitive production with high volume (direct API may be cheaper)
- Workloads requiring guaranteed model version pinning
OpenRouter vs Direct API Pricing
How do OpenRouter prices compare to using each provider's API directly? For most popular models, OpenRouter passes through pricing at or near cost.
Anthropic: Claude Opus 4.7 (Anthropic)
OpenRouter (per 1M)
$5.00 / $25.00
Direct API (per 1M)
$5.00 / $25.00
Difference
Same
Anthropic: Claude Sonnet 4.6 (Anthropic)
OpenRouter (per 1M)
$3.00 / $15.00
Direct API (per 1M)
$3.00 / $15.00
Difference
Same
Anthropic: Claude Haiku 4.5 (Anthropic)
OpenRouter (per 1M)
$1.00 / $5.00
Direct API (per 1M)
$1.00 / $5.00
Difference
Same
Direct API prices from official provider documentation. OpenRouter prices from their API, updated daily via ISR.
OpenRouter Pricing Breakdown
How OpenRouter Billing Works
Credit-Based System
Add credits to your account via credit card or crypto. Credits are deducted per-token as you make API calls. No minimum purchase, no expiration, no monthly fees.
Per-Token Pricing
Each model has separate input (prompt) and output (completion) token prices. Prices are set by model providers and passed through by OpenRouter, typically at or near direct API cost.
Free Models Available
OpenRouter offers dozens of free models with zero per-token cost. Free models have rate limits (20 req/min, 200 req/day) but require no credits to use.
Usage Tracking
Track spending per model and per API key in your OpenRouter dashboard. Set up usage alerts to monitor costs and prevent unexpected charges.
OpenRouter Monthly Cost Estimates
Hobby / Testing
$0-10/mo
• Free models only
• <200 req/day
• No credits needed
Light Use
$10-50/mo
• Haiku / Flash models
• 1-5K requests/day
• Single project
Medium Use
$50-300/mo
• Sonnet / GPT-4.1
• 5-20K requests/day
• Multiple projects
Heavy Use
$300+/mo
• Opus / GPT-5
• 20K+ requests/day
• Production workloads
5 OpenRouter Cost Optimization Tips
Start with Free Models
Use free models for prototyping and testing. Models like DeepSeek R1, Llama 3.3 70B, and Gemma 3 are available at zero cost. Only switch to paid models when you need higher quality or throughput.
Match Model to Task Complexity
Don't use Opus ($5/$25 per 1M tokens) for tasks that Haiku ($1/$5) handles well. Use cheaper models for classification, routing, and simple queries. Reserve expensive models for complex reasoning.
Use Smaller Context When Possible
Input tokens cost money. Trim unnecessary context, use concise system prompts, and avoid sending full documents when a summary suffices. Every token saved is money saved.
Implement Model Fallback Chains
Start with the cheapest model that might work, then escalate to more expensive ones only when needed. Example: Llama 3.3 → Gemini Flash → Claude Sonnet → Claude Opus.
Monitor Spending with CostGoat
Track your OpenRouter credit usage in real-time with CostGoat. Get alerts when spending spikes, see per-model cost breakdowns, and identify which models are consuming the most credits.
Start Tracking Your OpenRouter Spending
Monitor your OpenRouter credit balance and overall spend from your menubar — across 315+ models. Alerts before you hit zero.
Privacy-first desktop app. 7-day free trial, no sign-up required.
OpenRouter Pricing FAQ
Common questions about OpenRouter API costs and billing
