Aftercore — capacity exchange

SHARED CAPACITY. MEASURED USAGE.

A market for your
next inference.

Use a public API key to access listed supply. Every request has a supplying source, a locked price and an actual usage receipt.

Claude APIChatGPTGrok BuildMeasured token usage

1eligible public seat1 supplier · 5 public requests / 24h

Search modelsProviderProtocolSupplySort by

3 of 3 priced models match. Latency is measured from this market's public traffic, including acceptance tests; unknown measurements sort last.

AIAVAILABLE

CLAUDE / OPERATOR API

claude-haiku-4-5-20251001

Input$1.00

Cached input$0.10

Output$5.00

Cache writes / million: 5m $1.25 · 1h $2.00. Native Messages. API-funded supply; no subscription discount or seller commission.

Eligible public seats: 1
Spending hold / request: $1.00
Seller share: 0%
Completed / finished · 24h: 3 / 3
Median first text · 24h: 0.63 s
Median duration · 24h: 0.69 s

3 admitted · 0 in flight · 0 awaiting usage · 0 released

Open buyer workspace ↗Price version bdaabb79Model details & setup ↗Estimate usage cost ↓

AINO ELIGIBLE SUPPLY

OPENAI / SUBSCRIPTION

gpt-5.6-sol

Streaming text Responses.

Input$0.50

Cached input$0.05

Output$3.00

Eligible public seats: 0
Spending hold / request: $1.00
Seller share: 60%
Completed / finished · 24h: 2 / 2
Median first text · 24h: 3.15 s
Median duration · 24h: 3.42 s

2 admitted · 0 in flight · 0 awaiting usage · 0 released

Open buyer workspace ↗Price version 1f23ae48Model details & setup ↗Estimate usage cost ↓

AINO ELIGIBLE SUPPLY

GROK BUILD / SUBSCRIPTION

grok-4.6

Provider model: grok-4.6-build. Streaming text Responses. Output includes reasoning; token limits are hints. Subscription cost diagnostics are not vendor invoices.

Input$1.00

Cached input$0.25

Output$3.00

Eligible public seats: 0
Spending hold / request: $1.00
Seller share: 60%
Completed / finished · 24h: No measurements
Median first text · 24h: Not measured
Median duration · 24h: Not measured

Health appears after public requests. No uptime claim is inferred from an empty sample.

Open buyer workspace ↗Price version 54ac8163Model details & setup ↗Estimate usage cost ↓

PLAN YOUR USAGE

Estimate a request

Change the example token counts to match your expected workload. The calculation uses the same price version and exact arithmetic as billing.

Model

Total input tokensIncludes uncached input, cache reads and cache writes.Cached input readsPart of total input, priced at the cached rate.Output tokensInclude reasoning tokens when the provider includes them in output.Five-minute cache writesPart of total input.One-hour cache writesPart of total input.

ESTIMATED BUYER CHARGE

$0.00225

Input / million: $1.00
Cached / million: $0.10
Output / million: $5.00
Spending hold / request: $1.00

1 eligible public sources in this snapshot.

This is a planning estimate, not a quote, reservation or inference request. Actual provider usage determines the charge; unused holds are released. Subscription output limits are hints.

Price version bdaabb79-1def-47b5-be99-60d94413bc40

Supply is checked at admission

Only listed, active sources with fresh model data and no known exhausted quota are eligible. Availability can change between discovery and dispatch.

Actual usage. Clear release policy.

Failures before output release the hold without a charge or seller earnings. Partial output is billed only with valid usage. Missing usage is waived after five minutes.

Snapshot 2026-09-14 01:50:58 UTC · Health uses public requests admitted in the last 24 hours. Deposits: unavailable. Payouts: unavailable.

A market for yournext inference.

Models & prices