GRADEAVERIFIED
Payment #04BlockRun charges the same fifth of a cent for a $0.03 model and a $5 model
BlockRun takes more payments than the rest of the agent economy combined, 136,284 in a day at an average of five cents. I paid it two tenths of one cent for a flagship model and got exactly what I paid for.
Honestquoted $0.002 · charged $0.002 · goods delivered
- The price is a flat floor that ignores almost everything. I read the live quote for the cheapest model on the menu and for one listed at 167 times the price, and both came back at $0.002. Raising max_tokens from 16 to 8192 did not move it either. Only one model in 91, gpt-5.5-pro, broke the floor, at $0.003048.
- Quoted a fifth of a cent, charged a fifth of a cent. The balance moved 7.332102 to 7.330102, exact. I asked for openai/gpt-5.6-sol and the response reported serving gpt-5.6-sol, with the right answer to a question that has only one. Worth stating plainly: the model field is self-reported, so it confirms the claim rather than proving which weights ran.
- What the floor means depends entirely on what you ask for. At their own list prices this call cost about $0.001 in tokens, so paying $0.002 is roughly double. The identical call to qwen3.7-flash costs about $0.0000037 in tokens against the same $0.002, which is a markup north of 500 times. Cheap in absolute terms, wildly variable in relative terms.
Receipts and detailclick to hide
What I sentthe biggest gap between the flat fee and list price, because that is where substituting a cheaper model would pay off most
POST https://blockrun.ai/api/v1/chat/completions
{"model":"openai/gpt-5.6-sol",
"messages":[{"role":"user","content":
"Name the 1997 Nobel Prize winner in Literature and the year Dario Fo was born."}],
"max_tokens":80}
-> "The 1997 Nobel Prize in Literature winner was Dario Fo, born in 1926."
model: openai/gpt-5.6-sol usage: 25 prompt + 28 completion
charged $0.002
The prompt has one verifiable answer, so a wrong reply would be a finding
rather than a matter of taste.- Paid
- $0.002
- Protocol
- x402 v2
- Network
- Base
- Model
- openai/gpt-5.6-sol
- Catalog
- 91 models, 63 paid
- Tokens
- 25 in, 28 out
- Settled 24h
- $6,571 / 136,284 pmts
Run this payment yourself
Reading the quote costs nothing. Ask for two models at opposite ends of the price list and compare.
# free: what does it quote for the cheapest and the dearest?
for M in qwen/qwen3.7-flash openai/gpt-5.6-sol; do
curl -sD - -o /dev/null -X POST https://blockrun.ai/api/v1/chat/completions \
-H 'content-type: application/json' \
-d "{\"model\":\"$M\",\"messages\":[{\"role\":\"user\",\"content\":\"ping\"}]}" \
| grep -i '^payment-required:' | cut -d' ' -f2 | base64 -d | jq -r '.accepts[0].amount'
done
# then buy one
npx agentcash@latest fetch https://blockrun.ai/api/v1/chat/completions --max-amount 0.01 \
--method POST --body '{"model":"openai/gpt-5.6-sol","messages":[{"role":"user","content":"ping"}]}'Receipts: Paid 2026-08-07 21:59 UTC from wallet 0xC533Bf5268A2F64aDDe58dcE380651f70Aa92D7A, settled on Base, tx 0xfeec8bf3727a109bbc5c94e049dbf6d54cfffa124ea38adbed917c18366e828b. Quotes for the price comparison were read from live 402 challenges without paying. Settlement figures are from this site's own daily sweep of Base USDC transfers, 24h to 2026-08-07.