Scenario Workload Preset
RAG & Large-Context Document Analysis Cost Estimator
Calculate inference spend for retrieval-augmented generation and large-context document processing workloads with high prompt caching reuse.
Input Tokens / Req
35,000
Output Tokens / Req
1,200
Monthly Volume
10,000 reqs
Prompt Cache Hit Ratio
75% cached
Estimated Monthly Spend by Model
Simulated at 10,000 requests/mo with 35,000 in / 1,200 out.
| Foundation Model | Base Rate / 1M | Estimated Spend / Mo | Prompt Cache Savings | Action |
|---|---|---|---|---|
DeepSeek V4 ProRecommended DeepSeek • 1049k context | In: $0.955/1M Out: $1.911/1M | $127.39 | -$229.79 | Customize → |
Claude Sonnet 5.5Recommended Anthropic • 1000k context | In: $2/1M Out: $10/1M | $321.25 | -$498.75 | Customize → |
Claude Fable 5.1Recommended Anthropic • 1000k context | In: $10/1M Out: $50/1M | $1,540.63 | -$2,559.38 | Customize → |
Ling 3.0 Flash InclusionAI • 262k context | In: $0.021/1M Out: $0.063/1M | $3.70 | -$4.41 | Customize → |
Ling 3.1 Flash InclusionAI • 262k context | In: $0.075/1M Out: $0.225/1M | $13.20 | -$15.75 | Customize → |
Mercury 3 Inception • 1000k context | In: $0.1/1M Out: $0.35/1M | $15.58 | -$23.63 | Customize → |
MiMo-V2.6 Flash Xiaomi • 1050k context | In: $0.14/1M Out: $0.28/1M | $16.35 | -$36.02 | Customize → |
GPT-6 Luna OpenAI • 1050k context | In: $0.1/1M Out: $0.5/1M | $17.38 | -$23.63 | Customize → |
Claude Haiku 5.5 Anthropic • 1000k context | In: $0.1/1M Out: $0.5/1M | $17.38 | -$23.63 | Customize → |
DeepSeek V4.1 Flash DeepSeek • 1049k context | In: $0.15/1M Out: $0.6/1M | $21.11 | -$38.59 | Customize → |
Qwen 3.8 Flash Qwen • 1000k context | In: $0.15/1M Out: $0.47/1M | $22.97 | -$35.18 | Customize → |
MiniMax M3.1 Flash MiniMax • 1049k context | In: $0.15/1M Out: $0.6/1M | $24.26 | -$35.44 | Customize → |
GLM 5.3 Flash Zhipu AI • 1311k context | In: $0.15/1M Out: $0.5/1M | $27.00 | -$31.50 | Customize → |
Nemotron 3.5 Super VL NVIDIA • 1049k context | In: $0.1/1M Out: $0.4/1M | $34.55 | -$5.25 | Customize → |
Llama 4 Maverick Meta • 1000k context | In: $0.1875/1M Out: $0.6525/1M | $37.36 | -$36.09 | Customize → |
Deploy Autonomous AI Workers at Scale
Vicaro AI deploys autonomous digital coworkers that handle complex workflows, integrate with your tools, and optimize inference token economics automatically.
Explore Vicaro AI Workforce →