Batchrouter
Pricing

One transparent fee. Quote before you commit.

Provider base rate plus a small service fee. Locked at quote time. No subscriptions.

1step 1

Provider base rate

Live rates from the model catalog.

2step 2

Service fee

Routing, retries, delivery, and settlement.

3step 3

Accepted quote

Locks the customer price before any work starts.

Standard routing
Pay as you go

Model batches

Route by model with SLA, privacy, and price-aware lane selection.

5.90%

service fee on provider subtotal

  • Locked quotes
  • Automatic retries
  • Webhook + Slack + email delivery
Workflow products
Most popular

Outcome batches

Start from a finished job shape — instructions, validation, and delivery built in.

11.80%

service fee on provider subtotal

  • Curated instructions
  • Output schema validation
  • Same locked-quote contract
Public-provider discount

10% off OpenAI & Anthropic

Customer quotes for native OpenAI and Anthropic batch lanes include an automatic 10% discount on the provider rate before the service fee. The savings show up on every quote and receipt.

Credit wallet

Top up as you go

Buy credits in $10, $25, or $100 packs, or a custom amount from $5 to $500. Credits reserve at micro-dollar precision, so sub-cent jobs cost only what they used.

What the service fee covers

Routing

Provider fit, capacity, privacy, SLA, health, and price.

Execution

Dispatch, polling, retries, fallback, artifacts, and webhooks.

Models

Model catalog, provider onboarding, earnings, and payouts.

On every receipt

receipt · rc_8K2xR9pL
2026-05-24 14:42 UTC
Provider subtotal
anthropic.claude-3-haiku.batch · 4,218 items
$11.04
Public-provider discount
−10% on native OpenAI / Anthropic lanes
−$1.10
Service fee
Routing, retries, delivery, settlement
$0.59
Total charge
Locked at quote time · receipt #rc_8K2xR9pL
$10.53
Credit settlement
Reserved $12.47 → charged $10.53 → released $1.94
settled
signed · sha256:9f3c…b71aauditable · exportable · immutable

Pricing questions

See what your batch will cost

Plug in your model, item count, and average tokens — get a locked quote in seconds.