Optimization
Not every request needs the expensive model.
Most requests do not need the expensive model. The hard part is not saving money, it is proving that quality held while you did, which requires measuring the work rather than just the latency.
❯ Rename the billing props
4 files changed, 61 lines
❯ Why is the payments test flaky?
bisected 9 runs, found it
❯ Design the caching layer
write-through, 90s TTL
❯ Add a /changelog page from MDX
2 routes, RSS 2.0
❯ Write the migration for orders
reversible, 1 new index
❯ Bump the Terraform providers
no plan diff
❯ Refactor the session module
11 call sites updated
❯ Add tests for the cart reducer
18 cases, 3 edge
❯ Explain why recall dropped
analyzer change, week 31
❯ Rename the billing props
4 files changed, 61 lines
❯ Why is the payments test flaky?
bisected 9 runs, found it
❯ Design the caching layer
write-through, 90s TTL
❯ Add a /changelog page from MDX
2 routes, RSS 2.0
❯ Write the migration for orders
reversible, 1 new index
❯ Bump the Terraform providers
no plan diff
❯ Refactor the session module
11 call sites updated
❯ Add tests for the cart reducer
18 cases, 3 edge
❯ Explain why recall dropped
analyzer change, week 31
Haiku
4.5
GLM-5.2
Z.ai
Gemini
3.1 Pro
Sonnet
4.6
GPT-5.5
Codex
Opus
4.8
Four questions, asked per request.
A router that only asks how hard the prompt looks will send everything expensive the moment it is unsure. Ours prices the decision: the cost of switching, the odds the cheap model finishes without a retry, and which of your subscriptions has quota left before it spends anything on the API.
- How hard is this turn, given the repository it is acting on?
- Would switching cost more in retries than it saves in tokens?
- Is the cheaper model actually finishing this class of task?
- Which subscription has quota before we pay API rates?
- Difficulty0.21
low · single-file edit
- Switch cost$0.004
below retry threshold
- Completion odds97.2%
haiku, this task class
- Quotaavailable
team subscription
Cheaper is easy. Cheaper at the same bar is what we do.
Any router can cut your bill by sending everything to a small model. The reason to trust this one is that the quality bar is measured on your work rather than on a public benchmark, using the same machinery that computes your Slop Index, so a saving that quietly raised your rework rate shows up as a loss rather than a win.
- Quality measured on your repositories, not a leaderboard
- Savings reported net of retries, rework and review drag
- Per task class, so you can route aggressively where it is safe
- Roll back a routing policy the moment the bar moves
- Spenddown
- Pass rateheld
- Retrieswatch
- Reworkwatch
The fourth bar is the one that matters. A router that cuts the bill and raises rework has not saved anything.
Your tools stay exactly as they are.
The router is a base URL. Point your existing agents and IDEs at it, keep your own provider keys, and nothing else in your workflow changes. Self-hosting is available if your requests cannot leave your network, which for several of the organizations we work with is not negotiable.
- Drop-in base URL, OpenAI-compatible
- Bring your own keys, we never hold provider credentials
- Self-hosted deployment for regulated environments
- Per-policy rollback, and a kill switch that reverts to frontier
- 1
Get a router key
From the console, scoped per team.
- 2
Change one line
Point the base URL at Behold.
- 3
Work as usual
Readings appear within a day.
base_url = "https://router.beholdlabs.dev/v1"