96 models.
17 providers.
One endpoint.
One OpenAI-compatible endpoint reaches all 17 providers in the catalog, several with a free tier included. Integrate once, and route to whichever provider fits the call.
17 providers, one integration
Every provider below sits behind the same endpoint and the same API key. Where a provider offers a free tier, Hober routes to it at no cost to you.
GPT-class frontier models
Claude family built for long-context reasoning
Multimodal Gemini models
V3 chat + R1 reasoning
Qwen3 across sizes + coder variants
Open-weight European models
LPU inference built for very low latency
Broad open-weight hosting
Cost-efficient open-weight hosting
Wafer-scale inference throughput
Command models + retrieval
GLM-4 / GLM-5 family
Long-context Kimi models
Long-context generation
Search-grounded answer models
Step series models
Grok reasoning models
Looking for a specific model? Browse the live catalog →
Same model, many providers
Some models run on more than one provider. Hober groups those by weights, not by vendor, so a routing decision can shift to whichever host is fastest or cheapest right now without changing which model answers the call.
See how equivalence keys off routing decisions on the verifiable routing page →
Route by what the work needs
Pick a tier yourself when you already know what the job needs, or leave the pick to Hober Auto Routing and let it decide per call.
Top-tier reasoning and generation: best quality, higher cost. R1, Qwen3 235B, Kimi K2.
Strong general-purpose models that hit the quality/cost sweet spot. DeepSeek V3, Qwen3 Coder, GLM-4.
Lightweight and fast, built for the lowest cost on high-throughput workloads. Qwen3 32B, GLM-4 Flash.
Four ways to pick a model
Append a suffix to any model slug to choose what HAR (Hober Auto Routing) optimizes for on that call.
Plug your agent in
One endpoint, 96 models, 17 providers, OpenAI-compatible.
npm i @hober/sdkRoute your first request.
The catalog above is live right now. Get a key and call any model in it, or hand the pick to Auto Routing.
Pick a model or let Auto Routing choose for you.
Get an API key →