Research investigation R1118 / comparison

All three sampled AI gateways document same-model failover, but fallback controls differ

Same-model failover is documented across all three gateways. The useful comparison is which providers remain eligible, when another model becomes permissible and what happens when eligible providers fail—not a reliability ranking.

Archived snapshotv1Nov 18, 2026
Verified observations
2

2 measured fields

Supported claims
10

10 material findings

Cited sources
6

6 primary or authoritative

Research score
80

Automated topic and evidence score

Interactive figureAll three sampled AI gateways document...
CSV JSON
Data statusAwaiting verified observations

Evidence cutoff: November 18, 2026. The collection records documentation snapshots retrieved at 2026-11-18T16:32:59.622Z, after the packet timestamp of 2026-11-18T16:30:57.426Z. The supplied timing note is truncated, so exact historical page versions at the packet timestamp are not established.

Verified observationNo chart values are being inferredLast updated Nov 18, 2026

Version ledger

Frozen public editions

Each edition preserves the records, method, sources, and downloads available at publication time.

  1. v1 / latestNov 18, 20262 records / 6 sources

    Initial public snapshot with 2 records and 6 cited sources.

Coverage note

Evidence cutoff: November 18, 2026. The collection records documentation snapshots retrieved at 2026-11-18T16:32:59.622Z, after the packet timestamp of 2026-11-18T16:30:57.426Z. The supplied timing note is truncated, so exact historical page versions at the packet timestamp are not established.

Dataset ID
spd:perplexity-openrouter-or-vercel-which-failover-settings-preserve-the-requested-model-a93e8355
Stable URL
/research/perplexity-openrouter-or-vercel-which-failover-settings-preserve-the-requested-model-a93e8355
Version
v1
Coverage
Live collection
Records
2
Fields
7
Updated

Read the data

The records behind the figure

CSV JSON
All three sampled AI gateways document same-model failover, but fallback controls differ data records
EntityMetricValueUnitObservedSourceTransform
—bounded_sample_and_cutoffSeven official records covering three gateways. Editorial cutoff: November 18, 2026. Supplied documentation snapshots were retrieved at 2026-11-18T16:32:59.622Z, after the packet's 16:30:57.426Z timestamp; they were reused and supplemented by direct page checks. Exact historical page versions at 16:—2026-11-18https://docs.perplexity.ai/docs/orchestrator/routing-and-reliability—
—comparison_boundariesBaseline: an explicitly named fixed catalog model, no model aliases, virtual models, automatic model routers, application retries or SDK retry policies. Scenarios: upstream rate limit, provider timeout and exhaustion of eligible providers; optional alternate-model configurations evaluated separately—2026-11-18https://vercel.com/docs/ai-gateway/models-and-providers/model-fallbacks—

Measurement technique

How to read this report

  1. 01Reused the supplied evidence, including saved documentation snapshots and the collection's reported direct page checks. Recovering this material is not a new collection or experiment.
  2. 02Bounded the sample to seven official records covering three gateways. Compared a fixed, explicitly named catalog model without aliases, virtual models, automatic model routers, application retries or SDK retry policies. Evaluated optional alternate-model configurations separately.
  3. 03Planned an evidence_matrix with gateway/configuration rows and columns for upstream rate limits, provider timeouts, eligible-provider exhaustion, provider restrictions, model substitution, terminal behavior and source. Classify outcomes as model-preserving, model-changing, terminal error or unspecified; distinguish defaults from explicit settings.
  4. 04Perplexity matrix entry: retry another deployment of the same model on provider errors, upstream rate limits or timeouts when another deployment exists; return HTTP 429 with Retry-After after deployment exhaustion. No per-provider configuration is documented. Invalid requests and context overflow return HTTP 400 without another deployment attempt; streams failing after output begins end with an in-band error. Source: https://docs.perplexity.ai/docs/orchestrator/routing-and-reliability
  5. 05Perplexity model-selection entry: perplexity/auto is optional preview model selection and can change models between turns. The sampled records do not establish a failure-triggered alternate-model chain. The separate technical account reports internal measurements for October 4–November 2, 2026, not a matched cross-gateway experiment. Source: https://www.perplexity.ai/cs/hub/blog/orchestrator-one-api-for-reliable-inference
  6. 06OpenRouter matrix entry: provider.allow_fallbacks defaults true; order prioritizes providers and only restricts eligibility. With allow_fallbacks=false and no order, only the top-ranked endpoint remains. With nonempty order, unlisted public providers are excluded but eligible private endpoints remain. An explicit models list permits substitution on errors; unsuccessful fallback returns an error. Default model partitioning prioritizes primary-model endpoints, but provider.sort.partition='none' on
Next report / 01AI Model Economics Index All research reports
YOUR READING SPACE

Notifications