Live for any OpenAI-compatible client · pons-ai.xyz

$PONSAI

Hold $PONS, mint a key, point your client at one endpoint. Your live balance sets the tier — no invoices, no seats, no snapshots.

Get an API key Browse models

PonsAI wallet0xa8b02592d15fc9a2525add1dfe1458c2a0db45d8

pons-ai · /v1/chat/completions

curl https://api.pons-ai.xyz/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -d '{"model":"api/atlas-large",
       "messages":[{"role":"user","content":"Hello"}],
       "stream": true}'

stream · SSE~420ms

live406models in the catalogue · settled on Robinhood Chain

Atlas FlashAtlas LargeNova MiniOrion CoderOrion ReasonVega VisionAion-2.0Aion-3.0Aion-3.0-MiniAion-RP 1.0 (8B)Anthropic Claude Haiku LatestAnthropic Claude Sonnet LatestAuto RouterAuto Router (Beta)Atlas FlashAtlas LargeNova MiniOrion CoderOrion ReasonVega VisionAion-2.0Aion-3.0Aion-3.0-MiniAion-RP 1.0 (8B)Anthropic Claude Haiku LatestAnthropic Claude Sonnet LatestAuto RouterAuto Router (Beta)

Try it

Write a prompt. Watch the agent plan.

attach files · paste context

Sending opens the playground with your prompt.

Parse request and extract constraints0.4s

Route to catalogue model1.2s

Execute tool calls…

Routing across the agent mesh…

Meter usage against balance

How it works

Your balance becomes your plan.

Four steps from wallet to first token. Nothing custodial, nothing manual.

1

Connect a wallet

Non-custodial sign-in. We read your balance, never hold your keys or your tokens.

wallet · connected

2

Your tier resolves live

The balance is read on-chain at request time and mapped to a quota and rate limit.

tier · resolved from balance

3

Mint an API key

Scoped keys per project. Rotate or revoke at any time from the developer console.

sk-… · created

4

Call one endpoint

OpenAI-compatible chat completions with streaming. Every call is metered and receipted.

POST /v1/chat/completions · 200

Models

The frontier, at your fingertips.

View all models →

api/atlas-flash

128K ctx$0.15/$0.6per M

api/atlas-large

200K ctx$3/$15per M

64K ctx$0.05/$0.2per M

api/orion-coder

160K ctx$1.2/$4.8per M

api/orion-reason

256K ctx$2.5/$12per M

api/vega-vision

128K ctx$1/$4per M

Product

Three surfaces, one access layer.

Keys & tiers

Hold at least 10,000 $PONS and your key works immediately. Drop below the minimum and usage pauses until it qualifies again.

Wallet & tiers →

Guarded agents

Research, coding, data and browser agents run behind a policy engine — spend caps, runtime limits, allow-listed tools and domains.

Real accounting

Every call is attributed to a wallet, account and key: model, tokens, latency, cost and status — visible the moment it lands.

View activity →

The numbers

Access scales with what you hold.

Tiers read your live on-chain balance. Holdings above 30M $PONS are recognized at the cap.

Explorer

$2

per monthly

≥ 100K $PONS held
10 requests / min
All models & agents

Builder

$15

per monthly

≥ 1M $PONS held
30 requests / min
All models & agents

Operator

$100

per monthly

≥ 5M $PONS held
90 requests / min
All models & agents

Institutional

$600

per monthly

≥ 20M $PONS held
300 requests / min
All models & agents

coming soon

GPU Compute

H100, H200, A100 and RTX 5090 capacity — rent raw GPUs or list your own and earn. The rails are built; access opens after the API platform.

Preview hardware →

Ship on the Pons AI

Create an account, link a wallet, mint a key — and point any OpenAI-compatible client at our endpoint.

Create an account Read the docs