💳 Pay‑as‑You‑Go Pricing

Only pay for what you use — scale cost with usage, not commitment.

📊 Pricing Components at a Glance

Component	What You Pay For	Rate / Unit	Billing Frequency
Infrastructure	Compute time while your job is running on our clusters	per second	On completion of each job
LLM Tokens	Combined input + output tokens processed by the model	provider list price × tokens	On completion of each job
Storage	Persisted docs & vector embeddings leveraged for retrieval	Size (GB‑month)	Monthly
ShadAI API	Calls that trigger agent actions	$5 USD / 1 000 requests	On demand

🔍 Detailed Breakdown

1. Infrastructure

Every time an agent runs, it spins up secure, auto‑scaling compute. We meter wall‑clock execution time to the second and multiply by the tier’s per‑second rate.

Example: a 45‑second job on the “Standard” tier (0.0006**.

2. LLM Tokens

Agents call best‑in‑class LLMs. You’re charged for both directions:

Input tokens (your prompt + system context)

Output tokens (model’s response)

We simply pass through each provider’s published token price so you can choose the model that fits your budget/performance profile.

3. Storage

Documents and vectors ingested during sessions fuel semantic search. Storage is pooled, deduplicated, and billed monthly by average GB stored. Cold data archiving is free.

4. ShadAI API Usage

Using the ShadAI Client directly or via agents. Each call (sync or async) counts toward your quota.

$5 USD → 1 000 requests  
$0.005 → single request

We do not charge anything extra for infrastructure or tokens. We charge exactly what the provider charges us. In the case of storage, we charge the exact price from the provider, plus a 5% monthly fee, which covers the Monthly Storage Management Fee for accounts.

Recharge in USD credits

In billing page you can recharge credits to use ShadAI. Only you need to press ADD CREDITS button and follow next steps. The minimum amount allowed is 5 USD.

You can see that your available credits increase with new recharge of credits and decrease with each JOB agents cost automatically.

Pay your monthly Storage Fee

We will charge on the first day of the next month for the Monthly Storage Fee and the 5% Monthly Storage Management Fee, deducted from your available credits. Make sure to recharge your credits in time to avoid having your API key deactivated.

Illustration showing metered compute, token usage, storage, and API requests

💡 Tips to Optimize Cost

Choose the right model — use smaller/faster models for high‑volume tasks.

Keep sessions alive when possible.

Don't ingest multiple times same data to reduce storage.

Need more clarity? Contact support and we’ll walk you through a sample bill.

💰 LLM Token Pricing Cheat‑Sheet (May 2025)

All prices are USD per token. Multiply by 1 000 to estimate cost per K. Always verify with vendor docs before production use.

🔵 Google · Gemini

Model	In ($)	Out ($)
GEMINI_2_0_FLASH	0.00000070	0.00000040
GEMINI_2_0_FLASH_LITE	0.00000008	0.00000008
GEMINI_1_5_FLASH	0.00000015	0.00000060
GEMINI_1_5_PRO	0.00000250	0.00000100
GEMINI_1_5_FLASH_8B	0.00000008	0.00000030

🧠 Anthropic · Claude 3

Model	In ($)	Out ($)
CLAUDE_3_7_SONNET	0.00000300	0.00001500
CLAUDE_3_5_SONNET_2024_10_22	0.00000300	0.00001500
CLAUDE_3_5_SONNET	0.00000300	0.00001500
CLAUDE_3_5_HAIKU	0.00000100	0.00000400
CLAUDE_3_OPUS	0.00001500	0.00007500
CLAUDE_3_SONNET	0.00000300	0.00001500
CLAUDE_3_HAIKU	0.00000030	0.00000400

🧮 DeepSeek · R series

Model	In ($)	Out ($)
DEEPSEEK_R1_V1	0.00000135	0.00000540

🦙 Meta · Llama

Model	In ($)	Out ($)
LLAMA_4_MAVERICK_17B_INSTRUCT	0.00000024	0.00000097
LLAMA_4_SCOUT_17B_INSTRUCT	0.00000017	0.00000066
LLAMA_3_3_70B_INSTRUCT	0.00000070	0.00000072
LLAMA_3_2_1B_INSTRUCT	0.00000010	0.00000010
LLAMA_3_1_70B_INSTRUCT	0.00000070	0.00000072
LLAMA_3_1_8B_INSTRUCT	0.00000020	0.00000022

🌀 Cohere · Command

Model	In ($)	Out ($)
COHERE_COMMAND_PLUS	0.00000300	0.00001500
COHERE_COMMAND_R	0.00000050	0.00000150
COHERE_COMMAND_LIGHT	0.00000030	0.00000060

☁️ Amazon · Nova

Model	In ($)	Out ($)
AMAZON_NOVA_PRO	0.00000080	0.00000320
AMAZON_NOVA_LITE	0.00000006	0.00000024
AMAZON_NOVA_MICRO	0.00000004	0.00000014

💡 Tips

Use Flash Lite / Haiku for prototypes, then scale up as accuracy demands.

Double-check whether prices include input and output tokens separately (some dashboards only report combined cost).

Remember storage & inference infra are billed separately.

Pricing Plan

💳 Pay‑as‑You‑Go Pricing

📊 Pricing Components at a Glance

🔍 Detailed Breakdown

1. Infrastructure

2. LLM Tokens

3. Storage

4. ShadAI API Usage

Recharge in USD credits

Pay your monthly Storage Fee

💡 Tips to Optimize Cost

💰 LLM Token Pricing Cheat‑Sheet (May 2025)

💡 Tips

How to configure models

Pricing Plan

💳 Pay‑as‑You‑Go Pricing#

📊 Pricing Components at a Glance#

🔍 Detailed Breakdown#

1. Infrastructure#

2. LLM Tokens#

3. Storage#

4. ShadAI API Usage#

Recharge in USD credits#

Pay your monthly Storage Fee#

💡 Tips to Optimize Cost#

💰 LLM Token Pricing Cheat‑Sheet (May 2025)#

💡 Tips#

How to configure models#

💳 Pay‑as‑You‑Go Pricing

📊 Pricing Components at a Glance

🔍 Detailed Breakdown

1. Infrastructure

2. LLM Tokens

3. Storage

4. ShadAI API Usage

Recharge in USD credits

Pay your monthly Storage Fee

💡 Tips to Optimize Cost

💰 LLM Token Pricing Cheat‑Sheet (May 2025)

💡 Tips

How to configure models