LLM gateway: one key and one base URL for every model

An LLM gateway on one prepaid key. 343 chat models from 46 developers answer on one base URL, in the OpenAI and Anthropic formats. Routing, fallbacks, a response cache, guardrails and session logs run on the same request. There is no proxy to host.

Get a key https://api.uplinkswitch.com/v1

One request through the LLM gateway · one base URL, one key, either SDK

curl · OpenAI chat format
curl https://api.uplinkswitch.com/v1/chat/completions \
  -H "Authorization: Bearer $UPLINK_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-5-5",
    "messages": [{"role": "user", "content": "Summarize this thread."}]
  }'
Python · OpenAI SDK
from openai import OpenAI

client = OpenAI(base_url="https://api.uplinkswitch.com/v1", api_key="sk-uplink-live-...")

res = client.chat.completions.create(
    model="claude-sonnet-5-5",
    messages=[{"role": "user", "content": "Summarize this thread."}],
)
print(res.choices[0].message.content)
Python · Anthropic SDK, same key
import anthropic

client = anthropic.Anthropic(base_url="https://api.uplinkswitch.com/v1", api_key="sk-uplink-live-...")

msg = client.messages.create(
    model="gpt-6.1-sol",  # any chat model id, not only Claude
    max_tokens=400,
    messages=[{"role": "user", "content": "Summarize this thread."}],
)
print(msg.content[0].text)
curl · fallbacks, cache and a session on the same request
curl https://api.uplinkswitch.com/v1/chat/completions \
  -H "Authorization: Bearer $UPLINK_API_KEY" \
  -H "x-uplink-cache: on" \
  -H "x-session-id: ticket-8812" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-5-5",
    "models": ["gpt-6.1-sol","gemini-4-argon"],
    "messages": [{"role": "user", "content": "Summarize this thread."}]
  }'

The answer's model field and the x-uplink-model header name the model that answered. x-uplink-cache reads HIT or MISS. Every response, errors included, carries x-uplink-request-id. The SDK guide shows the base URL and key in Python, TypeScript, Go and Rust.

What the gateway does · 8 feature groups on every key

FeatureWhat it doesIn the request
Agent toolsWeb search, web fetch, remote MCP and a code sandbox inside one chat request, on any chat model, priced per call from the catalog."tools": [{"type": "uplink:web_search"}]
Files and redactionPDF, Office and HTML files for every chat model, converted to text where the model takes none; secrets and PII replaced per key and restored in the answer."type": "input_file" · x-uplink-redact: secrets_pii
Routingmodel "auto" across fast, balanced and frontier tiers, a models list of up to 5 fallbacks, saved presets as @preset/name, and route order by price, latency or throughput."model": "auto" · "models": [...]
Caching and contextAn opt-in response cache, a hit billed at 10% of the original charge, and middle-out compression when a chat outgrows the context window.x-uplink-cache: on · "transforms": ["middle-out"]
Guardrails and app sign-inBlocked patterns, a prompt-injection check and tool allow and deny lists on every key, a blocked request free; OAuth PKCE sign-in that gives your app’s users their own key."prompt_injection": "block" · GET /auth
MCP gatewayUp to 20 MCP servers behind one /mcp/org endpoint, headers sealed, tool allowlists, the key’s tool policy and a call log.POST /mcp/org
EndpointsEmbeddings, moderation, rerank, Whisper and Parakeet transcription, image edits and an OpenAI-compatible Batch API on the same key, at catalog prices.POST /v1/embeddings · /v1/rerank · /v1/batches
ObservabilitySession timelines, a 92-day usage CSV, log export to a webhook, Langfuse or OTLP (Datadog, Honeycomb, Grafana), per-session request and spend caps and a loop guard.x-session-id: ticket-8812

Each group has its own page with the request and its price. A web search run by the gateway bills $0.01 per search today. The features page lists every tool, document and endpoint price from the live catalog.

Formats the gateway speaks · from the live catalog, read 2026-11-16

FormatPathCalled byChat models
OpenAI Chat Completions/v1/chat/completionsThe OpenAI SDK and any app with an OpenAI-compatible base URL343 of 343
OpenAI Responses/v1/responsesThe OpenAI SDK’s Responses client343 of 343
Anthropic Messages/v1/messagesThe Anthropic SDK and Claude Code343 of 343
Gemini generateContent/v1beta/models/{model}:generateContentThe Gemini SDK343 of 343

A model costs the same in every format. GET /v1/models lists the ids a key can call. Embeddings, rerank, transcription, image edits and batches have their own paths on the endpoints page, and image, video and speech models are on the media list.

What the gateway charges · the model's price per million tokens, USD, read 2026-11-16

ModelInputOutputDeveloper list, output
Claude Fable 5.2$4.00$20.00$40.00
Claude Fable 5.1$6.00$30.00$50.00
Claude Opus 5.5$2.716$9.70$20.00
Claude Sonnet 5.5$1.20$3.00$10.00
GPT-6.1 Sol$0.582$2.91$10.00
GPT-6 Sol$0.60$3.00$10.00
GPT-5.5$1.80$9.00$30.00
Gemini 4 Argon$0.60$3.00$10.00

65 of the 87 chat models with a published list price sell under it on input and output. No subscription is needed, top-ups carry no fee, and each top-up locks your prices for 30 days. Every price is on the model list and in the price index. The daily real-model check shows which models answered as themselves today.

What a key carries · set in the console or on /v1/keys

EnvironmentLive or test, in the prefix: sk-uplink-live- or sk-uplink-test-.
Rate limitsRequests per minute and concurrency on every key, tokens per minute when you set it. A 429 carries retry-after.
Spend limitA cap per day, week or month.
Model allowlist and expiryA key narrowed to a list of models, or given an end date. A request for another model returns 403 scope_denied.
RoutingRoute order by price, latency or throughput, or an auto router setting that routes every chat request on the key.
Cache, redaction and guardrailsA response cache time to live, secret and PII redaction, blocked patterns, a prompt-injection check and a tool policy, applied to every request the key sends.
Session capsA request cap and a spend cap per session, and a loop guard.

What an LLM gateway replaces · and how to compare one with another

Without a gateway, every model developer is a separate account, key, SDK shape, rate limit and invoice, and your code owns the retries. An LLM gateway puts one endpoint in front of all of them. The app sends every request to one base URL with one key, and the model is a string in the request.

This one is hosted. A model costs the same in every format and on every route, so a failover never moves the price. The model that answers is yours to set: a fixed id, a fallback list, model: "auto" on the auto router, or a custom model id that holds a base model, a system prompt and its own fallbacks.

Three questions separate one gateway from another: who holds the provider keys, what is added to the model price, and who runs the server. The OpenRouter alternatives page compares hosted gateways by the fee on top, with the date each price page was read. The hosted LiteLLM alternative page covers the move from a proxy you run to an endpoint you call, and OpenRouter vs LiteLLM sets the two side by side.

The bill is checkable. Every non-streamed answer carries a signed receipt naming the model and the charge, and a monthly statement can be checked in the browser on the verifier.

LLM gateway questions

One endpoint between your code and the language models. Your app holds one key and one base URL. The gateway holds the model routes, authentication, retries, limits, billing and logs. Here that endpoint is https://api.uplinkswitch.com/v1, and 343 chat models answer on it in the OpenAI and Anthropic formats.

The two names describe the same job. "AI gateway" is the wider one: it takes in image, video and speech models as well as chat. This key serves both, chat models per token and media models per image, per second or per generation.

The price of the model that answered, per token, from its catalog row. Credit is prepaid. No subscription is needed and top-ups carry no fee. A response cache hit bills a tenth of the original charge, and the tools the gateway runs bill at the catalog’s prices.

Yes. Set the base URL to https://api.uplinkswitch.com/v1 and use your key. The OpenAI SDK calls /v1/chat/completions or /v1/responses. The Anthropic SDK and Claude Code call /v1/messages. Every chat model answers in both formats, so a GPT or DeepSeek id works from the Anthropic SDK and a Claude id from the OpenAI SDK.

There are two layers. When a route answers with a 5xx or a 429, the gateway tries the model’s next route at the same price. When every route of a model fails before a byte, a models list in the request names up to 5 fallback models, tried in order and each billed at its own price. The x-uplink-model header names the model that answered.

No. The gateway is hosted: there is no proxy, database or container to run or patch. If you already run LiteLLM, the LiteLLM guide puts this key in its config.yaml model list.

Yes. The shape is the same: one key and an OpenAI-compatible base URL. Any tool that takes a base URL switches by changing the URL and the key, and the response cache accepts the x-openrouter-cache headers. The OpenRouter alternatives page compares the fees, with the date each price page was read.

Three records say so. The response names the model in its model field and in the x-uplink-model header. Every non-streamed answer carries a signed receipt in x-uplink-receipt, with hashes of the request and the response. Once a UTC day every model gets the same test prompt on every route, and the result is public at /proof.

Yes. A key can carry a spend limit per day, week or month, a requests-per-minute limit, a concurrency limit, a model allowlist and an expiry. A session can be capped by request count and by spend.

Get your key.

Prepaid from $10 or a monthly plan, 30-day price lock.

  • One key, every model
  • The SDK you already use
  • Prepaid, or a monthly plan
  • 30-day price lock on every top-up
  • Signed receipts for every call
Join on Telegram