work with us

LLM Integrations

03 / 10AI Engineering

Diagram: your product sends requests to an AI gateway that handles auth, routing, caching, guardrails and metrics, and routes each request to OpenAI, Anthropic or a self-hosted open-source model.

The model is only one part of the system.

We integrate OpenAI, Anthropic and open-source models into real products, with the routing, evaluation, fallbacks, observability and cost controls that keep them fast, reliable and affordable once real users arrive.

  • Model
  • Prompts & tools
  • Routing
  • Evaluation
  • Fallbacks
  • Observability
  • Cost controls

One slice is the model. Everything around it decides whether it works in production.

Capabilities

Ten things a real integration needs.

Pick a capability to see what it looks like in the code we ship. Illustrative snippets from our gateway layer.

gateway.ts

const ai = createGateway({
  providers: ["openai", "anthropic", "oss"],
})

const reply = await ai.generate({
  task: "summarise_ticket",
  input: ticket.body,
})

prompts/summarise_ticket.yaml

prompt:  summarise_ticket
version: 14
system: |
  You are a support analyst. Be concise.
  Never include customer PII.
tests:   38 passing  # runs in CI

schemas/triage.ts

const Triage = z.object({
  intent:   z.enum(["refund", "bug", "billing"]),
  priority: z.number().min(1).max(4),
  summary:  z.string().max(280),
})
// validated before it reaches your code

tools/orders.ts

tools: {
  lookupOrder: {
    input: z.object({ id: z.string() }),
    run: ({ id }) => orders.get(id),
    // scoped: read-only, own tenant
  },
}

stream · /v1/generate

event: token  data: "Your refund"
event: token  data: " has been issued"
event: tool   data: lookupOrder(4821)
event: token  data: " and should arrive"
event: done   data: { tokens: 212 }

routing.yaml

routes:
  - when: task == "classify"
    use:  small-fast
  - when: input.tokens > 50000
    use:  long-context
  - default: frontier

fallbacks.yaml

fallbacks:
  frontier:  [secondary, oss-hosted]
  trigger:   [timeout > 8s, 429, 5xx]
  retries:   2  # exponential backoff
  parity:    eval suite must pass

eval · support-replies

cases         212
accuracy      0.94  ▲ +0.03
policy_safe   1.00
tone_match    0.91
p95_latency   1.8s   ✓ budget 2.5s

trace · 7f3a

summarise_ticket
├ route      frontier            4ms
├ model      1,284212 tokens  1.42s
├ guardrail  pii_filter          okcost       $0.0061

budgets.yaml

budgets:
  per_request:  $0.02
  per_user_day: $1.50
cache:          semantic · 24h
downgrade_when: budget > 80%

Model routing

Every request, the right model.

Hover an example request and watch the router pick a track. Same product, three very different jobs.

Small, fast model. A short classification doesn’t need frontier reasoning. Routing it to a lightweight model keeps it well under a second, at a fraction of the cost.

Frontier model. A customer-facing reply needs judgement and tone, so the router pays for the strongest model and evaluates the draft before it’s sent.

Long-context model. A 180k-token contract won’t fit most context windows. The router picks a long-context model and scores the summary for coverage.

Reliability

Models fail. Products shouldn’t.

Every model and provider will have a bad day. Production systems plan for it, so a timeout becomes a reroute your users never see.

  • OutagesEvery provider has incidents. Your product shouldn’t share them.
  • Rate limitsTraffic spikes hit quotas at exactly the wrong moment.
  • Latency spikesA very slow answer can do as much damage as none.
  • DeprecationsModels retire on the provider’s timeline, not yours.

We set up health checks, circuit breakers, retries with backoff and parity evaluations, so a fallback answer still meets your quality bar.

Requestgenerate(reply)
01 · PrimaryFrontier model
02 · FallbackSecondary provider
03 · Last resortOpen-source, self-hosted
Failover chain: requests go to a primary frontier model; if it times out, they are rerouted to a secondary provider, with a self-hosted open-source model as the last resort.

Cost control

Quality. Latency. Cost. Balanced per request.

No single model wins on all three. Choosing per task, and caching what repeats, moves the whole product to a better place. Figures are illustrative.

Quality
Speed
Cost efficiency

p95 3.1sper 1k requests $18.40

Excellent answers everywhere, including the thousands of simple requests that never needed them. Slow and expensive at scale.

p95 1.6sper 1k requests $6.20

Frontier quality where it matters, lighter models for routine work. Usually the best place for a customer-facing product.

p95 0.6sper 1k requests $1.10

Very fast and cheap for high-volume, repetitive tasks such as classification and extraction, backed by a semantic cache.

p95 1.2sper 1k requests $2.40

Predictable unit costs and full data control, in exchange for owning the infrastructure and a lower quality ceiling.

Process

From first API call to a system you trust.

We measure before we optimise, and we keep measuring once real traffic arrives.

  1. 01

    Assess

    Use cases, data sensitivity, latency and budget targets, and your current stack.

    Integration plan
  2. 02

    Architect

    Gateway, routing rules, schemas, fallbacks and the evaluation strategy.

    Architecture spec
  3. 03

    Integrate

    Providers, prompts, tools and streaming wired into your product and APIs.

    Working integration
  4. 04

    Evaluate

    Benchmarks on your own data: quality, safety, latency and cost per task.

    Eval baseline
  5. 05

    Optimize

    Route, cache and right-size models until the numbers hold under load.

    Tuned config
  6. 06

    Monitor

    Traces, alerts, drift checks and spend dashboards on live traffic.

    Live dashboards

Next step

Your product. The right model. At the right time.

Tell us which models you use today, or want to. We’ll show you how to make them faster, more reliable and cheaper to run.

Integrate AI into your product

What's our client are say !

Excellent Service

Synapse rebuilt our pet-care store from the ground up. Launch was on time, conversions are up and the team still answers within the hour.

Founder, CYBE Pet Care

A True Partner

They challenged our brief in the best way. The new identity and site feel like us — only sharper. Our campaign traffic doubled in a month.

Marketing Lead, Darkside Apparel

Fast & Thoughtful

From wireframes to App Store in twelve weeks. Every screen was tested with real travellers, and it shows in our reviews.

Product Owner, Book Now Travel