Skip to content
bInference RouterLive1,634,959,210 tokens routedAI Privacy47.2K/minTop this weekClaude Sonnet 5.522%Live stats
LaunchLaunch an agent

Stake-to-Privacy AI, or not private AI backed by BSC revenue

Stake $BINF and get private AI every day, sealed in NVIDIA Hopper and Intel TDX. Or launch a token, and its trading fees pay for your agent's AI.

Example: Nova answers a question with Claude Sonnet 5 through the bInference Router, paid from its AI budget. Credit agents leave unused for 7 days moves to the pool with AI bought in bulk, and $BINF holders buy credit for less.

Example
AI models, one key
347
off AI for $BINF holders
Up to 8%
until unused credit moves to the pool
7 days
to launch an agent
0.005 BNB

See how much AI your agent gets

Enter a daily trading volume, then pick a tax and an AI model. We use today’s prices.

$
Tax on each trade
AI model
Answer size

15,000 words read, 750 written$0.040 an answer

Your agent’s AI budget

$926a week

7 days, oldest spent first$132 added a day

About 23,000 answers a week from Claude Sonnet 5, or one every 26 seconds.

Routed viabInference Router
Where the tax goes$2,100 a week from traders
AI budget 44.1%
$926
Treasury 18.9%
$397
Your token’s holders 27%
$567
Flap 10%
$210
Launch an agent

Today’s model prices, and the same volume every day.

How the flywheel turns

Follow one dollar your token earns. Your token trades against NVDAB, a tokenized NVIDIA share, so its tax comes in NVDAB. Flap keeps a small cut and pays your token’s holders a share. The rest goes to bInference: most of it becomes your agent’s AI, and the remainder buys AI in bulk for the pool.

Your token’s tax comes in NVDAB. Of every dollar of it, 10 cents go to Flap, the launch platform, and 27 cents to your token’s holders. The other 63 cents go to bInference, which gives 44.1 cents to your agent’s AI budget and 18.9 cents to the treasury. Your agent spends its budget on AI, and what it has not used after 7 days goes to the pool, together with the AI the treasury buys in bulk. $BINF holders buy credit for up to 8% less.

What your agent hasn’t used after 7 days
Flap keeps 10%. Of the rest, Flap’s contract sends 30% to your token’s holders and 70% to bInference, which splits it 70/30.View the contract

The flywheel, live

Every token used through bInference, counted as it is charged. The wheel holds the last four weeks, one cell a day, and turns a cell each day.

Tokens used, all time

1,634,959,210

Roughly 13,625 novels of text, read and written. 47.2K a minute over the last hour.

AI paid for by trading
$1,529
Agents using AI this week
8
Calls answered
14,206
Models in use this week
26

Counts only: no prompt or answer is ever stored. New numbers every 5 minutes. Last read just now.

Cheaper AI for $BINF holders

Credit that agents don’t use and AI the treasury buys in bulk keep the AI credit pool full. Hold $BINF, the bInference token, and the credit you buy costs up to 8% less.

How the pool fills

Every trade keeps it turning

  1. Trades pay tax
  2. Agents get AI
  3. The pool fills
  4. Holders save

Up to8%off for holders

$BINF’s own trading tax goes into the pool too.

Your discount

The more $BINF you hold, the more you save

5M $BINF
1% off
6M $BINF
2% off
7M $BINF
3% off
8M $BINF
4% off
9M $BINF
5% off
10M $BINF
6% off
12.5M $BINF
7% off
15M $BINF
8% off

We count your lowest balance of the last 7 days. Credit you buy lasts at least 7 days.

Example: with 10,000,000 $BINF, Carol pays $94 for $100 of credit.

You pay for credit in BNB, as everyone does. $BINF only sets your discount.

Every model, one key

347 AI models from Anthropic, OpenAI, Google, DeepSeek and more. Agents pay from their AI budget, and $BINF holders pay up to 8% less than the usual price.

The whole bar is the priceHolders, the solid part

  1. Claude Opus 5.5Anthropic

    Price $0.080

    Holders pay $0.074

  2. Claude Sonnet 5Anthropic

    Price $0.040

    Holders pay $0.037

  3. GPT-6 SolOpenAI

    Price $0.040

    Holders pay $0.037

  4. Grok 4.7SpaceXAI

    Price $0.037

    Holders pay $0.034

  5. Kimi K3MoonshotAI

    Price $0.022

    Holders pay $0.020

  6. Gemini 3.8 FlashGoogle

    Price $0.015

    Holders pay $0.014

  7. GPT-6 LunaOpenAI

    Price $0.0020

    Holders pay $0.0018

  8. DeepSeek V4.1 FlashDeepSeek

    Price $0.0020

    Holders pay $0.0018

One answer reads about 15,000 words and writes about 750. Prices are for the AI credit you buy, and holders’ are at the top discount. Every model’s price per token is at binference.io/api/v1/models.

See all 347 models, with usage and details

Connect your agent with two settings

Point your agent at our address and give it its key. Every call is paid from its AI budget. No card and no monthly bill.

Your agent calls binference.io/api/v1 with its own key. The bInference Router passes the call to the model it names, from Anthropic, OpenAI, Google and more.
Your agentClaude Code, Codex, OpenClaw, Hermes or your own codeAddressbinference.io/api/v1Keybinf_…AnthropicOpenAIGoogleand more
import OpenAI from "openai";const client = new OpenAI({});const reply = await client.chat.completions.create({  model: "anthropic/claude-sonnet-5",  messages: [{ role: "user", content: "Summarize today's trades" }],  max_tokens: 1024,});
  • OpenAI and Anthropic formats, streamed
  • Tools, images and web search as usual
  • Checks its budget and keys over MCP
  • Prompts and answers are never stored
Read the docs: every endpoint, limit and error

Plain answers

About fees, budgets and $BINF.

Launch your agent’s token

It takes one screen and 0.005 BNB. Your agent gets its key as soon as the token is live.

Launch an agent