Daily Verified · Updated 2026-10-12
AI API Pricing Calculator
Compare 300+ LLM Token Rates
Compare official direct rates against verified aggregators (OpenRouter, DeepInfra, Together AI). Simulate token budgets with Prompt Caching discounts across 300+ frontier and open-weights models.
Cheapest Frontier: Muse Spark 1.3 Contributor ($0.10/1M)
Coding Standard: Claude Sonnet 5.5 ($2.00/1M)
Frontier Reasoning: GPT-6.1 Sol ($2.00/1M)
AI Token Cost Calculator
Simulate your monthly API expenses with Prompt Caching discounts & Aggregator deals.
Input Tokens (Prompt)1,500
10032k128k
Output Tokens (Completion)800
504k16k
Prompt Cache Hit30%
0% (No Cache)50%100% (Hot)
Daily API Calls (Volume Scale):500 calls / day (15,000 / mo)
Single Call Cost
$0.01015
Per request average cost
Official Monthly Bill
$152.18 / mo
Direct Lab rate: $2/1M in · $10/1M out
Via Hosting & Relays
$152.18 / mo
Official rate matches best host
Real-Time Directory
View Lowest Cost Models →
Live AI Model Token Rates
Official list pricing vs. lowest available aggregator rate (OpenRouter & inference clouds).
Tier:
Showing top 20 flagship models on initial load for instant performance.
| Cached In | Hosting Providers & Relays | Action | ||||
|---|---|---|---|---|---|---|
| 1.0M | $0.10 | $0.0020 | $0.20 | $0.10 / $0.20via OpenRouter OpenRouter | ||
| 128k | $0.14 | $0.0280 | $0.28 | $0.14 / $0.28via Novita AI Novita AINovita AINovita AIOpenRouter | ||
| 1.0M | $0.15 | $0.0030 | $0.60 | $0.03 / $0.14via OpenRouter Save $OpenRouter | ||
| 1.0M | $0.15 | $0.0160 | $0.47 | $0.15 / $0.47via OpenRouter OpenRouter | ||
| 205k | $0.60 | $0.06 | $2.40 | Direct Only | Details → | |
| 1.0M | $0.68 | $0.07 | $2.09 | $0.68 / $2.09via OpenRouter OpenRouter | ||
| 1.0M | $0.75 | $0.07 | $3.75 | $0.75 / $3.75via OpenRouter OpenRouter | ||
| 1.0M | $1.25 | $0.15 | $4.25 | $0.10 / $0.20via OpenRouter Save $OpenRouter | ||
| 1.0M | $1.40 | $0.26 | $4.40 | $1.00 / $3.20via Together AI Save $Together AIOpenRouter | ||
GPT-6.1 SolFlagship | 1.1M | $2.00 | $0.10 | $10.00 | $2.00 / $10.00via OpenRouter OpenRouter | |
Claude Sonnet 5.5Flagship | 1.0M | $2.00 | $0.10 | $10.00 | $2.00 / $10.00via OpenRouter OpenRouter | |
Gemini 4 ArgonFlagship | 128k | $2.00 | $0.10 | $10.00 | $2.00 / $10.00via OpenRouter OpenRouter | |
| 500k | $2.00 | $0.50 | $6.00 | $2.00 / $6.00via OpenRouter OpenRouter | ||
Qwen3.8 MaxFlagship | 1.0M | $2.00 | $0.25 | $6.00 | $4.00 / $12.00via OpenRouter OpenRouter | |
| 500k | $2.00 | $0.50 | $6.00 | $2.00 / $6.00via OpenRouter OpenRouter | ||
Command A PlusFlagship | 128k | $2.50 | $1.25 | $10.00 | Direct Only | Details → |
Kimi K3Flagship | 1.0M | $3.00 | $0.30 | $15.00 | $0.80 / $10.00via OpenRouter Save $TelnyxNovita AIOpenRouter | |
Sonar ProFlagship | 200k | $3.00 | $1.50 | $15.00 | $3.00 / $15.00via OpenRouter OpenRouter | |
Claude Opus 5.5Flagship | 1.0M | $4.00 | $0.20 | $20.00 | $4.00 / $20.00via OpenRouter OpenRouter | |
GPT-6 AstraFlagship | 1.1M | $10.00 | $1.00 | $50.00 | $10.00 / $50.00via OpenRouter OpenRouter |
Price Indicator: Budget (<$0.15) Mid ($0.15 - $1.00) Higher ($1.00 - $5.00) Flagship (>$5.00)
Showing 20 of 375 AI models
Monthly Plans vs. Metered API
Compare 30+ Subscriptions → Looking for Flat-Rate Monthly Subscriptions?
Compare ChatGPT Plus ($20), Claude Pro ($20), Google AI Pro ($19.99), Cursor Pro, Kimi VIP, GLM Coding, and DeepSeek. Review message caps, context windows, and find out whether a subscription or API is cheaper for your workload.
Frequently Asked Questions
Everything you need to know about AI token costs, caching discounts, and billing.
What is the cheapest LLM API currently available in 2026?
The lowest price per token among frontier models is Muse Spark 1.3 Contributor ($0.10/1M input) followed by lightweight open-weights models ($0.02/1M input via OpenRouter).
How does official provider pricing compare with aggregators like OpenRouter?
While proprietary models generally match official rates on aggregators, open-weights models (DeepSeek, Llama, Qwen) frequently feature 15% to 40% lower token pricing on hosting aggregators (such as DeepInfra, Together AI, or Fireworks) compared to hyperscalers.
How does Prompt Caching impact my actual AI API bill?
Prompt Caching allows providers to store repeated context in memory. Cache hits reduce input costs by 50% to 90% across OpenAI, Anthropic, Google Gemini, and DeepSeek endpoints.
How does this token cost calculator compute monthly estimates?
Our calculator uses the exact formula: (Input Tokens × (1 - Cache Rate) × P_in + Input Tokens × Cache Rate × P_cache + Output Tokens × P_out) / 1,000,000 × Daily Calls × 30. We evaluate both official direct endpoints and best-available aggregator endpoints.
Are the token prices updated daily?
Yes. Our automated ingestion pipeline checks official documentation and OpenRouter API endpoints daily. Price reductions or newly released models are synchronized within hours.
Can I download the raw AI pricing dataset?
Yes, we provide an open, standardized JSON endpoint at /api/pricing.json with CC-BY 4.0 license for developer and research use.