// One key. Every model. Half the bill.

Three plans. One same rate card.

Drop-in OpenAI-compatible gateway to frontier models from OpenAI, Anthropic, and Google. Same code. Same SDKs. Half the per-token list price.

One endpoint. One rate card. Half the bill.

50% UNDER DIRECT LIST · EVERY MODEL · PERIOD
— Two tracks · one key · 01

Drop in. Don't refactor.

One base_url swap. Keep your SDK, keep your code. cURL-friendly. OpenAI-compatible. Zero new abstractions.

→ api.slashed.pro/openapi.json — Two tracks · one key · 02

Watch the bill fall.

Real-time spend, per-key caps, per-seat ceilings, single invoice. See the line item drop the moment you switch.

→ dashboard.slashed.pro
— Free 1M tokens to migrate · No card · No commitment
— Pricing · plans · all sit on the same per-token rate card

Three plans. One rate card.

Every plan accesses the same published per-token rate card at exactly 50% under direct list. What varies is commercial terms (annual vs monthly), procurement options (DPA / BAA / self-host), and engagement model (founder-direct vs founder-introduced).

FREE

Migrate without commitment

$0 · 1M tokens to migrate

  • 1,000,000 tokens free, any model in the catalogue.
  • No card on file, no SSO, no integration support.
  • Receipts dashboard read-only.
  • Self-serve docs only.
Start free →
PRO

Per-token at 50% list, monthly card

50% off published direct rate · monthly card billing

  • Full per-token rate card; the receipts dashboard, full read/write.
  • Per-key cost ceilings, per-seat ceilings.
  • Founder-direct email support.
  • Standard DPA available on request.
Get an sl- key →
ENTERPRISE

Annual, NET-30, self-host option

Annual · quarterly invoicing · NET-30

  • Annual prepay margin on top of the 50% list discount.
  • Self-hosted edition · BYO-cloud Terraform + Helm.
  • HIPAA BAA available on healthcare engagements · DPA on request.
  • Founder + ops engineer joint support, named.
Talk to a founder →

All three plans hit the same per-token rate card · only commercial terms differ. The discount isn't tiered; the engagement model is. See the rate card →

Direct API list — that's 50% off. Every model. No fake tiers.

Opus is in. Codex Max is in. Codex 5.5 is in. Same response shape. Half the per-token list rate, every call. See the rate card →

— The Catalogue · per 1M output tokens · list vs SLASHED

One endpoint. Every model.

A unified gateway across Anthropic, Google, and OpenAI — not the headline, the plumbing. One OpenAI-compatible endpoint. One canonical ID per model. Half the list rate. OpenAPI spec →

Anthropic
Claude Opus 4.7
$75.00$37.50
Anthropic
Claude Sonnet 4.6
$15.00$7.50
Anthropic
Claude Haiku 4.5
$4.00$2.00
Google
Gemini 3.1 Pro
$12.00$6.00
Google
Gemini 3 Flash
$3.00$1.50
OpenAI
GPT-5.4
$15.00$7.50
OpenAI
GPT-5.4 Mini
$1.25$0.63
OpenAI
GPT-5.3 Codex
$15.00$7.50
OpenAI
GPT-5.2
$15.00$7.50
OpenAI
GPT-5.2 Codex
$15.00$7.50
OpenAI
GPT-5.5 / Codex 5.5
$30.00$15.00
OpenAI
GPT-5.1 Codex Max
$30.00$15.00

// Prices per 1M OUTPUT tokens, USD. Last updated 2026-05-23. Each SLASHED price = provider direct list × 0.5. Verify at anthropic.com/pricing, openai.com/api/pricing, ai.google.dev/gemini-api/docs/pricing. Checked dates and per-model source URLs available on request via hi@slashed.pro.

— Migration Notes · before / after

Three changed characters. Bill drops 50%.

If your code talks to OpenAI, it already talks to SLASHED. Change the URL. Change the key prefix. Keep everything else.

DIRECT 
# Paying direct list rate
from openai import OpenAI

client = OpenAI(
  base_url="https://api.openai.com/v1",
  api_key="sk-...",
)
client.chat.completions.create(
  model="gpt-5.4",
  messages=[...]
)
SLASHED 
# Half the bill, same call
from openai import OpenAI

client = OpenAI(
  base_url="https://api.slashed.pro/v1",
  api_key="sl-...",
)
client.chat.completions.create(
  model="gpt-5.4",
  messages=[...]
)

Full reference at api.slashed.pro/openapi.json — endpoints, error codes, rate limits, every supported model ID.

— Also migrating from Quatarly?

BEFORE · qua- 
# Running on Quatarly
client = OpenAI(
  base_url="https://api.quatarly.cloud/v1",
  api_key="qua-...",
)
AFTER · sl- 
# Same SDK. Half the list bill. Real receipts.
client = OpenAI(
  base_url="https://api.slashed.pro/v1",
  api_key="sl-...",
)

Three changed lines either way. OpenAI direct or Quatarly — both migrate to SLASHED with the same gesture.

— vs Quatarly · behaviours we have reproduced against their published endpoint

Every router does this. We do the opposite.

Same OpenAI-compatible spec. We just didn't break it. Six gateway behaviours observed against their published endpoint — request/response captures and reproduction steps are available on request via hi@slashed.pro.

// QUATARLY DOES THIS
// SLASHED DOES THIS
01 · Tax
Hidden ~700-token system prompt
A router-authored preamble is silently prepended on every call. Billed to you. Cached on their side, paid by you forever.
01 · Zero
No hidden context
SLASHED bills only the tokens you submit and the tokens we return. No router-authored preamble, no silent system prompt, no platform context on the invoice. Ever.
02 · Ghost
gpt-5.1 returns content:null
Their gateway returns content:null for gpt-5.1 — no error, just an empty completion. The failure is invisible upstream; the debug bill is yours.
02 · Live
Content is populated
Supported models return usable content or a structured error. Silent content:null completions are treated as gateway failures, not customer-facing success. We page on it.
03 · Tiers
gemini-3.1-pro-low / -high
Same model. Two IDs. Two prices. "Tier optimisation." Translation: pay more for the same compute behind a different label.
03 · One
Canonical model IDs
Each model has one public ID and one public price. Capability controls are parameters, not duplicate SKUs with separate billing treatment.
04 · Shape
Answer in reasoning, not content
Output is inconsistently placed in reasoning. Your client crashes. You add a try/catch. You move on.
04 · Spec
Stable response schema
Assistant output stays in the OpenAI-compatible content field. reasoning never becomes an undocumented substitute for the customer-visible answer. Boring is a feature.
05 · Fog
No public rate card
Their homepage advertises a percentage discount with no public price table. "Talk to sales for Pro." Reconciliation requires a phone call.
05 · Card
Published rate card
Every model carries a public per-token rate. Savings claims reconcile to direct list without sales calls, blended tiers, or undisclosed exceptions. The CFO can paste it into Excel.
06 · 502
HTTP 502 for invalid models
Ask for a model that doesn't exist? You get 502 Bad Gateway. Your retry loop hammers them. You can't tell their bug from yours.
06 · Code
Correct HTTP semantics
Invalid model names resolve as 400 client errors. Upstream 5xx codes are reserved for actual upstream failures. Your retry, alerting, and incident logic just works.

Half the list bill. All the receipts.

Import your qua- key → — Mirror your 30-day usage against the SLASHED rate card. No card. No phone call.
— On Latency · the gateway-overhead question

The primary technical liability of any gateway is overhead. We mitigate it structurally: single-hop routing directly to provider endpoints, zero proxy chaining, no tier-based queueing. You incur raw upstream API latency plus network transit — nothing else.

// Third-party benchmarks not yet published. Self-host if you need to measure overhead inside your own VPC.

— Tenets · four pillars, one promise

No discovery decks. No tier-1 maze.

— 01

Drop-in compatible

Works with Claude Code, Codex, Cursor, Factory Droid, OpenCode, raw OpenAI SDKs. Zero vendor abstractions to learn.

— 02

Encrypted, never stored

TLS 1.3 in transit. Prompts and completions live only as long as the request. No retention, no training, no leaks.

— 03

Real-time spend

Live token counter, per-key caps, per-seat ceilings, daily digests. The dashboard mirrors the API, line for line.

— 04

Operators, not tickets

Email hits engineers who read traces and ship fixes — no ticket maze, no tier-1 hand-off. Not vibes. Not vanished threads.

— Self-hosted edition · BYO-cloud · fixed-price annual

Keep the data. Take the routing.

For buyers whose data residency, sovereignty, or compliance posture cannot accommodate a third-party gateway in the request path. Same routing intelligence, deployed inside your cloud (or on-prem). Same dashboard. Your audit trail, end to end.

— 01

BYO-cloud deploy

AWS, GCP, Azure, or on-prem. Terraform + Helm chart provided. Single-region default; multi-region available on request.

— 02

Same routing engine

The same lane-selection logic and provider-failover policies that run on slashed.pro/v1, deployed under your DNS, behind your VPC, with your existing IAM controls.

— 03

Your audit trail

Every request logged locally to your S3 / GCS / Blob. No cross-tenant log mixing. Full export to JSON or CSV; retention configurable per-engagement.

— 04

Fixed-price annual

No per-token rate. Predictable annual contract priced against your forecast volume. Quarterly invoicing. NET-30. Standard commercial terms.

The 50% direct-list savings still applies via your own pass-through provider credentials. Provider keys (Anthropic, OpenAI, Google) stay yours. We never see traffic in this deployment.

Talk to a founder about self-hosting →
— Security & Sovereignty · procurement-grade

No retention. No training. No theatre.

Mature buyers deserve a cold, declarative manifest — not a privacy-policy PDF buried three clicks deep. Here it is, in one block, in monospace.

// ENCRYPTION:     TLS 1.3 in transit; AES-256 at rest.
// RETENTION:      Zero. Payloads exist strictly for request duration.
// TRAINING:       Zero. We never inspect or train on customer prompts or completions.
// COMPLIANCE:     SOC 2 Type II [audit in progress · target Q4 2026].
// RESIDENCY:      US-East default. Multi-region routing on request.
// ISOLATION:      Per-key rate limits, per-key audit logs, cryptographic key separation.

If a procurement form needs a paragraph instead of a block, write to hi@slashed.pro — a founder replies, not a queue.

Status page
status.slashed.pro →

— RFP-grade summary · six requirements, evidence-pointed

  1. REQ-001OpenAI-compatible API surface. No client refactor.
  2. REQ-002Published per-token rate card across the catalogue.
  3. REQ-003Zero hidden context tax. Only submitted tokens billed.
  4. REQ-004Stable response schema. content field is canonical.
  5. REQ-005Correct HTTP semantics. 400/404 for client faults; 5xx upstream-only.
  6. REQ-006SOC 2 Type II in progress · GDPR · DPA on request · self-hosted edition.
SOC 2 TYPE IIaudit in progress · target Q4 2026
GDPREU sub-processor list on request
DPAstandard DPA available on request
SELF-HOSTEDBYO-cloud · fixed-price annual
— For the CFO · the line item, halved

Annual contracts. Quarterly invoicing. NET-30.

For finance leads who cannot expense card payments and need the savings on a procurement schedule — the same 50% list discount, packaged as a quarterly bill.

  • Token reconciliation matches the rate card → Receipt 01 · No hidden context
    Your monthly token total ties to the published per-token rates. No silent ~700-token preamble inflating every invoice line.
  • Output is what you submitted plus what we returned → Receipt 02 · Content populated
    Empty completions are gateway failures, not billable successes. The invoice represents work, not silence.
  • One canonical model ID per row → Receipt 03 · Canonical IDs
    No -low/-high tier splits inflating SKU count. Models on the invoice equal products consumed.
  • Schema-stable response field → Receipt 04 · Stable schema
    Engineering doesn't burn migration cycles. Finance doesn't fund unplanned client-library rewrites.
  • Public rate card · Excel-pasteable → Receipt 05 · Published rate card
    Annualised modelling without a sales call. The CFO can paste it into Excel and project a year forward in five minutes.
  • Predictable retry economics → Receipt 06 · Correct HTTP semantics
    Invalid model names resolve as 400, not 502. Retry-loop spend stays bounded, not amplified.
Talk to a founder →
— By the Numbers · live invoice

Live invoice. No surprises.

Connect any sl-, qua-, sk-, or or- key. The dashboard imports your last 30 days of usage and projects what the same workload would have cost at direct list. CFO-shareable. Audit-trail clean.

Open dashboard → Read the API spec →

Compare plans. Negotiate Skip the sales call.

— Begin · free 1M tokens to migrate · no card

Get your sl- key →
Already on Quatarly, OpenRouter, or paying OpenAI direct? Import your existing key and we'll mirror your usage against our rate card.