Nå aldri grenser
Automatisk fallback på tvers av 339 leverandører på millisekunder. Kvoten brukt opp? Neste leverandør overtar. null nedetid.
Gratis og åpen kildekode AI-gateway
Route across 352 providers through one OpenAI-compatible endpoint, with automatic fallback.
OmniRoute × Cheaper Inference
Combine OmniRoute’s automatic fallback and developer tools with Cheaper Inference’s cost-ranked marketplace. Every eligible request starts with the cheapest available provider route.
| Model | Input price | Output price | Savings |
|---|---|---|---|
| gpt-5.6-lunaOpenAI · text | 60% off | ||
| gpt-5.6-solOpenAI · text | 50% off | ||
| glm-5.3Z.ai · text | 45% off | ||
| deepseek-v4-flashDeepSeek · text | 40% off | ||
| deepseek-v4-flash-0731DeepSeek · text | 40% off | ||
| glm-5.3-flashZ.ai · text | 30% off |
Løftet
Automatisk fallback på tvers av 339 leverandører på millisekunder. Kvoten brukt opp? Neste leverandør overtar. null nedetid.
A 12-engine pipeline reduces eligible context by 15–95%. The documented tool-heavy example reduced it by ~89%.
90+ free tiers and 56 recurring or keyless free-forever providers. No credit card needed for the keyless quick start.
16+ kodings-agenter. Claude Code, Codex, Cursor, Cline, Copilot, Antigravity. gjennom én konfigurasjon.
OpenAI ↔ Claude ↔ Gemini ↔ Responses API-oversettelse. Pek et hvilket som helst verktøy mot /v1 og det bare fungerer.
Kretsbryterne, TLS-stealth, MCP (105 verktøy), A2A, minne, sikkerhetsskinner, evalueringer. støttet av 25,000+ tester.
Katalogen
A catalog spanning chat, media, search, local runtimes, cloud agents and system integrations.
352 providers+
Oppe og kjørende på 60s
Install the package, launch the gateway, then point any OpenAI-compatible client at port 20128.
Install the `omniroute` npm package globally.
$ npm install -g omnirouteadded 1 package
Launch the API and dashboard together on port 20128.
$ omniroute▸ dashboard ✓ http://localhost:20128/dashboard▸ api ...... ✓ serving on :20128
Use `http://localhost:20128/v1`; the keyless `auto` route works on a fresh install.
$ curl localhost:20128/v1/models✓ models listed
Alt inkludert
Ruting, motstandsdyktighet, gratiskvoteoppbruk, komprimering og agentprotokoller. én binær, null plugin å sette sammen.
Set a model to `auto` or build your own combo with 19 strategies and tiered fallback.
Use a ready-made mode or combine 19 strategies around the goal that matters.
Vedvarende samtalehukommelse. FTS5 nøkkelord + Qdrant vektorgjenfinning, innebygd.
Feil på riktig nivå. aldri hele tjenesten. Kretsbryter per leverandør, nedkjøling per tilkobling, utestengelse per modell. Andre nøkler og modeller fortsetter å betjene.
Pool-deduped accounting across 90+ free tiers.
~1.51B gratis tokens per måned.
12 composable engines for tool output, context and response style.
Reduce eligible tokens by 15–95%.
A built-in server exposing 110 gateway tools across 33 scopes.
110 tools · 33 scopes · stdio / HTTP
A JSON-RPC agent server with 6 skills.
6 skills · JSON-RPC 2.0 · Agent Card
Client compatibility
Point an OpenAI-compatible CLI or editor at one local base URL; OmniRoute handles the providers behind it.
http://localhost:20128/v1
curl http://localhost:20128/v1/chat/completions \
-H "Authorization: Bearer $OMNIROUTE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"auto","messages":[{"role":"user","content":"Hello"}]}'Nytt
Installer OmniCopilot-utvidelsen, så dukker hver OmniRoute-modell rett opp i model picker-en du allerede bruker. ingen ny sidepanel, ingen ny chat-UI.
Works in VS Code stable and Insiders. Install from the Marketplace or Extensions view.
For VS Code-forker som ikke bruker den offisielle butikken. Cursor, Windsurf, VSCodium, Theia, code-server, Gitpod og flere.
Fra og med VS Code 1.122 fungerer leverandørmodeller uten GitHub-innlogging eller Copilot-abonnement. agent mode, tool calling og vision, på OmniRoutes gratis modeller.
Den daglige virkeligheten
Hvert problem med AI-koding har en innebygd løsning. Ingen skript, ingen overvåking.
Ærlig sammenligning
Capabilities checked against the linked project documentation on 2026-08-30.
| Capability | OmniRoute (opens in a new tab) | 9Router (opens in a new tab) | LiteLLM (opens in a new tab) | CLIProxyAPI (opens in a new tab) |
|---|---|---|---|---|
| Providers | 352 | 40+ | 100+ | 8+ upstreams |
| Routing strategies | 19 | 3-tier | retry / priority | round-robin / fill-first |
| Tiered fallback with UI | Yes | Yes | Manual policy | Multi-account |
| Token compression | 12 engines · 15–95% | RTK / Headroom / Caveman | No built-in pipeline | HTTP compression |
| Capability | OmniRoute (opens in a new tab) | 9Router (opens in a new tab) | LiteLLM (opens in a new tab) | CLIProxyAPI (opens in a new tab) |
|---|---|---|---|---|
| Built-in MCP server | 110 gateway tools | No | MCP client / gateway | No |
| A2A protocol | Server · 6 skills | No | A2A client / gateway | No |
| Cloud agents | Codex / Cursor / Devin / Jules | No | No | Sidecar integrations |
| Capability | OmniRoute (opens in a new tab) | 9Router (opens in a new tab) | LiteLLM (opens in a new tab) | CLIProxyAPI (opens in a new tab) |
|---|---|---|---|---|
| Failure-isolation layers | 3: provider / connection / model | Cooldown | Cooldown / retry | Cooldown |
| Persistent memory | FTS5 + vector | No | Semantic cache | No |
| Guardrails | PII / injection / vision | No | Yes | Cloaking controls |
| Eval framework | Built in | No | No | No |
| TLS fingerprint controls | wreq-js | No | No | uTLS |
| Capability | OmniRoute (opens in a new tab) | 9Router (opens in a new tab) | LiteLLM (opens in a new tab) | CLIProxyAPI (opens in a new tab) |
|---|---|---|---|---|
| Dashboard stack | Next.js 16 | Next.js 16 | Next.js | Next.js / React |
| UI locales | 42 | 10 | Not documented | 3 |
| OAuth providers | 25 | 6 | SSO | CLI auth |
| Self-hostable | Yes | Yes | Yes | Yes |
| License | MIT | MIT | MIT + enterprise | MIT |
Public README and official documentation snapshot; verify linked sources before purchase or deployment decisions.
Kjører overalt
Én kodebase, ni måter å kjøre på. bærbar, server, telefon eller plugin. Velg installasjonskommandoen og du betjener på port 20128.
npm
npm install -g omnirouteOpen guide (opens in a new tab)Docker
docker run … diegosouzapw/omnirouteOpen guide (opens in a new tab)Skrivebord
npm run electron:buildOpen guide (opens in a new tab)ARM
native arm64Termux
pkg install nodejs && npx -y omnirouteOpen guide (opens in a new tab)PWA
Add to Home ScreenOpen guide (opens in a new tab)OpenCode-plugin
@omniroute/opencode-providerOpen guide (opens in a new tab)VS Code
Install OmniCopilotOpen guide (opens in a new tab)Kildekode
npm install && npm run devOpen guide (opens in a new tab)Routing
Use a ready-made mode or combine 19 strategies around the goal that matters.
autoBalanced defaultcurl http://localhost:20128/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{"model":"auto","messages":[{"role":"user","content":"Write a TypeScript retry helper."}]}'Routing alias auto selected. Objective: Balanced default. Fallback enabled.
Use quota you already have before touching paid APIs.
priority · fill-firstBalance traffic across keys and accounts to reduce rate-limit pressure.
weighted · round-robin · p2c · least-used · headroomRoute to the lowest-cost eligible target.
cost-optimizedKeep long contexts on models that fit, then relay when needed.
context-relay · context-optimized · cache-optimizedDistribute eligible traffic across targets.
random · strict-randomUse 15-factor scoring, last-known-good and reset-aware windows.
reset-window · reset-aware · lkgp · auto · fusion · pipelineGratis tokens, ærlig talt
455 catalog entries are deduplicated into 40 recurring pools; only published positive budgets feed the headline.
1.51B
Pool-deduped accounting keeps shared quotas from being counted more than once. No-cap providers stay visible without inflating the token total. Checked 2026-08-30.
View the calculation (opens in a new tab)Slutt å brenne tokens
Verktøyutdata, gjentatt kontekst og oppblåst JSON komprimeres før de treffer modellen. samme mening, en brøkdel av tokenene. 12 sammensettbare motorer stables i en pipeline du kontrollerer.
The function should iterate over the list of items, and for each item, it should check whether the value is greater than zero, and if so, add it to the running total.sum all list items where value > 0x-omniroute-compression: standardStandard compression selected. Published range ~30%.
Control precedence: request header → combo → profile → adaptive policy → default.
3 lag, ikke 3 nivåer
En dårlig nøkkel bør ikke drepe en leverandør. En død modell bør ikke drepe en nøkkel. Hvert feil er isolert til det minste mulige omfanget, slik at alt annet fortsetter å betjene.
Network controls
Proxy scopes control network routing while local-first storage keeps operational data on your machine.
Route globally, per provider or per individual connection.
Match supported provider clients down to selected transport characteristics.
Keys, usage and history stay on the host you control.
Se alt på ett blikk
Manage providers, combos, analytics, health and costs at `localhost:20128/dashboard`.
Agent-native
OmniRoute er ikke bare en proxy. den snakker agentprotokollene. Koble den til en MCP-klient, et A2A-nettverk eller en skykodingsagent, og den blir et verktøy agenten kan betjene.
110 tools across 33 scopes over stdio and HTTP transports.
110 tools · 33 scopes · stdio / HTTP
claude mcp add omniroute --type http --url http://localhost:20128/api/mcp/stream6 skills for smart routing, quota, discovery, cost analysis and health reporting over JSON-RPC 2.0.
6 skills · JSON-RPC 2.0 · Agent Card
Styr Codex, Cursor, Devin og Jules gjennom ett grensesnitt. opprett oppgaver, godkjenn planer og strøm resultater, alt rutet gjennom OmniRoute.
Codex · Cursor · Devin · Jules
Mer enn ruting
Kjør Bifrost (Go-relay), 9Router eller CLIProxy som administrerte sidecars. eller en full klyngeprofil. rett fra dashbordet.
Notion & Obsidian koblet inn som MCP-verktøy. notatene og vaultene dine blir førsteklasses kontekst for enhver modell.
Prompt-injeksjon-vern på hver rute, valgfri PII-maskering og normalisering av sikkerhetsinnholdsfiltre. forsvar uten lock-in.
Streaks, prestasjoner og live-besparelser. forbruket ditt, gjort håndgripelig.
Guides
Walkthroughs cover installation, free-provider setup and connecting an IDE.
Bygget i det åpne
OmniRoute oppdateres kontinuerlig. drevet av hundrevis av bidragsytere som holder det i forkant.
Snapshot from 2026-09-01
Chat, support and roadmap
(opens in a new tab)News and announcements
(opens in a new tab)Global community
(opens in a new tab)Comunidade Brasil
(opens in a new tab)OmniRoute by Cheaper Inference
Self-host OmniRoute, or start with Cheaper Inference for a hosted cost-ranked gateway.