Free Tier

$0
  • 12 models, 4 providers
  • 170ms to 9s latency range
  • Text, JSON, reasoning, code, search
  • Same API format as paid
  • Idempotent retries included
  • No rate limits during beta
Start free

Per-Request Pricing

USDC on Solana mainnet. Launch discounts applied automatically.

ModelPriceLatencyNote
tongkhokr/claude-haiku-4.5$0.0021-2sCheapest
quickai/gpt-5.4-mini$0.0052-4sBudget GPT
quickai/gpt-5.6-luna$0.0072-4sMid-tier GPT
clervo/code$0.0152-3s10% launch discount
tongkhokr/claude-sonnet-5$0.0152-3s10% launch discount
tongkhokr/claude-sonnet-4.6$0.0152-3s10% launch discount
quickai/gpt-5.4$0.0182-4sFull GPT-5.4
quickai/gpt-5.6-terra$0.0182-4sGPT-5.6 mid
quickai/gpt-5.5$0.0352-4sGPT-5.5 full
quickai/gpt-5.6-sol$0.0352-4sGPT-5.6 flagship
tongkhokr/claude-opus-4.7$0.0842-3sOpus tier
tongkhokr/claude-opus-5$0.0842-3sMost capable

Questions

What currency?

USDC on Solana mainnet. Your agent needs a Solana wallet with USDC.

What if my request fails?

Payment only happens after success. Failed requests are never charged. Use idempotency keys for safe retries.

Will free models stay free?

Depends on upstream providers. If a free tier is removed, those models move to paid with notice.

Rate limits?

None during beta. Paid requests have higher priority.

Input/output limits?

20,000 input characters, 4,096 output tokens for paid. 10,000 / 1,024 for free.