RivenGet started

Search docs

Find a page across the Riven documentation

Cloud Fallback

Live

72 cloud models across nine providers, behind the same aliases as the on-prem fleet. Reached only when on-prem cannot serve the request.

Cloud fallback exists so that saturation or a node failure degrades latency rather than availability. 72 cloud models across nine providers sit behind the same tier aliases as the on-prem fleet, so a fallback is invisible to your code — the model ID you sent does not change.

Three on-prem models plus 72 cloud models is 75 live models on the gateway. Alias IDs in the catalog outnumber that, because several aliases resolve to the same pool — Riven Ultra Router explains the mapping.

The nine providers#

ProviderTypically used for
OpenAIGeneral reasoning and broad tool-use compatibility
AnthropicLong-context work and careful instruction following
GoogleMultimodal input and very long context windows
xAIFast general chat
MistralEfficient open-weight lanes and European hosting
PerplexitySearch-grounded answers, paired with Riven Grounding
DeepSeekReasoning and code at low cost per token
CohereEmbeddings and reranking
GroqVery low-latency serving for short completions

When fallback triggers#

  1. The on-prem pool for the resolved tier has no healthy replica with a free slot.
  2. The on-prem attempt fails or exceeds its deadline.
  3. The request needs a capability no on-prem model provides — a modality or a context length beyond the fleet.
  4. An organisation policy explicitly prefers a named provider for a given workload.

If none of these hold, the request stays on-prem. Fallback is a reaction to conditions, not a load-balancing default.

Knowing what served you#

Every response carries the upstream that produced it, so attribution never requires guessing.

`x-riven-upstream`Meaning
onprem-qwen36-aServed by the on-prem primary — no third party involved
onprem-nemotron75-bServed by the on-prem heavy-reasoning pool
onprem-bonsai27-*Served by the ternary efficiency pool
A provider nameFell back to cloud — the provider is named explicitly

Cost and quota#

Cloud tokens are metered through Riven Pricing Brain using the same tier multipliers documented in Models & usage. A fallback does not change the multiplier you are quoted — the tier you requested is the tier you are billed at.

Opting out#

Organisations that cannot send data to a third party at all can pin routing to on-prem only. Requests then queue or fail rather than falling back, which is the correct trade for regulated workloads. Configure it per organisation — see Riven Business Suite for which tiers include the policy.

Provider credentials are held in Riven Keymaster and are never exposed to clients or included in model context.