Providers

Every hosting partner routed through the Opper gateway. Privacy posture and the models on each route.

Looking for who built the models instead? See the maker directory →

26 providers33 routes599 models

All hosting providers

AnthropicAnthropic's first-party API — direct route to Claude, US-hosted.
1 route10 modelsUS
OpenAIOpenAI's first-party API — direct route to GPT and o-series, US-hosted.
1 route54 modelsUS
AzureMicrosoft Foundry — frontier OpenAI and Anthropic models on a single Azure contract.
2 routes24 modelsEU
AWS BedrockAmazon's managed inference platform — the broadest hyperscaler catalogue, EU + US.
3 routes25 modelsEU + US
Google CloudVertex AI — Gemini, Claude on Vertex, and Llama under one Google contract.
3 routes46 modelsEU + US
GeminiGoogle's direct AI Studio API — fastest access to new Gemini features.
1 route45 modelsUS
xAIxAI's first-party API — direct route to the Grok family across EU and US.
2 routes18 modelsEU + US
MistralMistral's first-party API — Paris-based, EU-hosted, GDPR-native.
1 route27 modelsEU
CerebrasWafer-scale chip inference — among the fastest tokens-per-second in the industry.
1 route4 modelsUS
GroqLPU-based inference — sub-100ms first-token latencies on open-weight models.
1 route9 modelsUS
PerplexitySonar — language models with live web search built in.
1 route4 modelsUS
ElevenLabsProduction-grade voice, speech, and conversational-AI models.
0 routes0 models—
FireworksFast, cost-efficient hosting for open-weight models.
1 route9 modelsUS
NebiusGPU cloud and managed inference — strong on EU residency for open-weight models.
2 routes31 modelsEU + US
NovitaBroad open-weight catalogue at competitive prices.
1 route119 modelsUS
BergetSwedish AI cloud — EU-only, full GDPR posture by default.
1 route16 modelsEU
EvrocEuropean AI cloud — EU residency, open-weight focus.
1 route13 modelsEU
InceptronEU-based inference for open-weight models.
1 route4 modelsEU
ArceeArcee's first-party API — direct route to the Trinity model family.
1 route3 modelsUS
PrunaEuropean image and video model lab — compression-optimised inference.
1 route4 modelsUS
DoclingIBM's document-understanding API.
1 route2 modelsEU
OpperModels that Opper hosts directly — small specialised models we ship as part of the gateway.
1 route1 modelEU
InfercomEU-based open-weight inference.
3 routes7 modelsEU + US
DeepInfraLarge open-weight catalogue at scale — US-hosted.
1 route123 modelsUS
NVIDIANemotron and realtime audio models on NVIDIA infrastructure.
0 routes0 models—
Alibaba CloudModel Studio — Qwen lineage hosted in Frankfurt (eu-central-1).
1 route1 modelEU

Start building with 300+ models

One API key. Every major provider. Up and running in minutes.

Get startedView Documentation