1. Live Monthly LLM Cost & Prompt Caching Calculator
Loading models...
| Model ⇅ | Capabilities | Context ⇅ | In / 1M ⇅ | Out / 1M ⇅ | Est. / Mo (Cached) ⇅ | Est. / Mo (Raw) |
|---|
2. Self-Host Cloud GPU vs. API Break-Even Calculator
Calculating...
Est. GPU Cost
—
Recommended Cloud GPUs & Unified API Routers
Best for H100 / A100 / 4090
Launch GPU on RunPod →
RunPod Cloud GPUs
Spin up on-demand H100, A100, and RTX 4090 pods or serverless vLLM endpoints in seconds.
Predictable Cloud Infra
Try DigitalOcean →
DigitalOcean GPU Droplets
Deploy AI inference APIs, vector databases, and GPU droplets with simple monthly billing.
Global Low-Latency Regions
Deploy on Vultr →
Vultr Cloud GPU
Run dedicated NVIDIA H100/A100/L40S instances across 32 global data center regions.
1 API Key · 470+ Models
Get Unified API Key →
OpenRouter Unified API
Switch between Gemini, Claude, GPT, DeepSeek, and Llama with one OpenAI-compatible key.
Newest AI Models Added
Thinking Machines: Inkling 2 MiniIn $0.075 · Out $0.300 / 1M · 1.0MRadixArk: DaisyRose 27BIn $0.150 · Out $1.88 / 1M · 262KMistral: Pixtral Large 2502In $2.00 · Out $6.00 / 1M · 128KGoogle: Gemini 4 Neon (batch)In $1.50 · Out $7.50 / 1M · 1.0MGoogle: Gemini 4 NeonIn $3.00 · Out $15.00 / 1M · 1.0MOpenAI: GPT-6.2 Astra Pro (batch)In $4.00 · Out $20.00 / 1M · 1.1MOpenAI: GPT-6.2 Astra ProIn $8.00 · Out $40.00 / 1M · 1.1MOpenAI: GPT-6.2 Astra (batch)In $4.00 · Out $20.00 / 1M · 1.1MOpenAI: GPT-6.2 AstraIn $8.00 · Out $40.00 / 1M · 1.1MOpenAI: GPT-6.2 Sol Pro (batch)In $1.00 · Out $5.00 / 1M · 1.1MOpenAI: GPT-6.2 Sol ProIn $2.00 · Out $10.00 / 1M · 1.1MOpenAI: GPT-6.2 Sol (batch)In $1.00 · Out $5.00 / 1M · 1.1M
Popular Head-to-Head Model Pricing Comparisons
Pixtral Large 2502 vs Gemini 4 Neon$3.00 vs $6.00 / blended 1MPixtral Large 2502 vs GPT-6.2 Astra Pro$3.00 vs $16.00 / blended 1MPixtral Large 2502 vs GPT-6.2 Astra$3.00 vs $16.00 / blended 1MPixtral Large 2502 vs Qwen4 Max$3.00 vs $2.14 / blended 1MPixtral Large 2502 vs Gemini 4 Hydrogen$3.00 vs $3.00 / blended 1MPixtral Large 2502 vs Claude Fable 5.2$3.00 vs $16.00 / blended 1MPixtral Large 2502 vs DeepSeek V4.1 Flash 1017$3.00 vs $0.263 / blended 1MPixtral Large 2502 vs Claude Haiku 5.5$3.00 vs $0.200 / blended 1MPixtral Large 2502 vs Qwen3.8 Max Prime$3.00 vs $6.00 / blended 1MPixtral Large 2502 vs Command A+$3.00 vs $0.600 / blended 1MPixtral Large 2502 vs Grok 4.7$3.00 vs $3.00 / blended 1MPixtral Large 2502 vs DeepSeek V4.1 Flash$3.00 vs $0.087 / blended 1MGemini 4 Neon vs GPT-6.2 Astra Pro$6.00 vs $16.00 / blended 1MGemini 4 Neon vs GPT-6.2 Astra$6.00 vs $16.00 / blended 1MGemini 4 Neon vs Qwen4 Max$6.00 vs $2.14 / blended 1MGemini 4 Neon vs Claude Fable 5.2$6.00 vs $16.00 / blended 1MGemini 4 Neon vs DeepSeek V4.1 Flash 1017$6.00 vs $0.263 / blended 1MGemini 4 Neon vs Claude Haiku 5.5$6.00 vs $0.200 / blended 1MGemini 4 Neon vs Mistral Large 4$6.00 vs $1.05 / blended 1MGemini 4 Neon vs Qwen3.8 Max Prime$6.00 vs $6.00 / blended 1MGemini 4 Neon vs Command A+$6.00 vs $0.600 / blended 1MGemini 4 Neon vs Grok 4.7$6.00 vs $3.00 / blended 1MGemini 4 Neon vs DeepSeek V4.1 Flash$6.00 vs $0.087 / blended 1MGPT-6.2 Astra Pro vs Qwen4 Max$16.00 vs $2.14 / blended 1M
Browse Pricing by AI Lab / Provider
openai106 live modelsgoogle49 live modelsqwen43 live modelsanthropic32 live modelsmistralai22 live modelsz-ai20 live modelsdeepseek17 live modelsmeta10 live modelsmoonshotai10 live modelsnvidia10 live modelsx-ai9 live modelsmeta-llama7 live modelstencent7 live modelsaion-labs6 live modelsamazon5 live modelscohere5 live modelsinclusionai5 live modelsminimax5 live modelsperplexity5 live modelsthinkingmachines5 live modelsxiaomi5 live models~openai5 live modelsmorph4 live modelssakana4 live models