{"title":"All three sampled AI gateways document same-model failover, but fallback controls differ","description":"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.","dataset_id":"spd:perplexity-openrouter-or-vercel-which-failover-settings-preserve-the-requested-model-a93e8355","canonical_url":"https://superpowerdaily.com/research/perplexity-openrouter-or-vercel-which-failover-settings-preserve-the-requested-model-a93e8355","version_url":"https://superpowerdaily.com/research/perplexity-openrouter-or-vercel-which-failover-settings-preserve-the-requested-model-a93e8355","version":"v1","snapshot_hash":"71c6bc210e866447fb1fc60d94e7470f80b980df0e022f25ec497a231c3ce186","date_created":"2026-11-18T16:45:02.683Z","date_modified":"2026-11-18T16:45:02.683Z","license":{"name":"Superpower Daily data reuse terms","url":"https://superpowerdaily.com/terms"},"license_url":"https://superpowerdaily.com/terms","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.","measurement_technique":["Reused 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.","Bounded 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.","Planned 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.","Perplexity 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","Perplexity 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","OpenRouter 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"],"methodology":["Reused 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.","Bounded 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.","Planned 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.","Perplexity 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","Perplexity 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","OpenRouter 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"],"metrics":[{"label":"Verified observations","value":"2","detail":"2 measured fields"},{"label":"Supported claims","value":"10","detail":"10 material findings"},{"label":"Cited sources","value":"6","detail":"6 primary or authoritative"},{"label":"Research score","value":"80","detail":"Automated topic and evidence score"}],"columns":[{"key":"entity","label":"Entity"},{"key":"metric","label":"Metric"},{"key":"value","label":"Value"},{"key":"unit","label":"Unit"},{"key":"observed","label":"Observed"},{"key":"source","label":"Source"},{"key":"transform","label":"Transform"}],"data":[{"unit":null,"value":"Seven 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:","entity":null,"metric":"bounded_sample_and_cutoff","source":"https://docs.perplexity.ai/docs/orchestrator/routing-and-reliability","observed":"2026-11-18","transform":null},{"unit":null,"value":"Baseline: 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","entity":null,"metric":"comparison_boundaries","source":"https://vercel.com/docs/ai-gateway/models-and-providers/model-fallbacks","observed":"2026-11-18","transform":null}],"sources":[{"url":"https://vercel.com/docs/ai-gateway/models-and-providers/model-fallbacks","name":"Vercel","title":"AI Gateway Model Fallbacks","records":1},{"url":"https://vercel.com/docs/ai-gateway/models-and-providers/provider-filtering-and-ordering","name":"Vercel","title":"AI Gateway Provider Filtering, Ordering, and Sorting","records":0},{"url":"https://vercel.com/docs/ai-gateway/models-and-providers/provider-timeouts","name":"Vercel","title":"AI Gateway Provider Timeouts","records":0},{"url":"https://openrouter.ai/docs/guides/routing/model-fallbacks","name":"OpenRouter","title":"Model Fallbacks - Automatic Failover Between Models","records":0},{"url":"https://openrouter.ai/docs/guides/routing/provider-selection","name":"OpenRouter","title":"Provider Routing - Smart Multi-Provider Request Management","records":0},{"url":"https://docs.perplexity.ai/docs/orchestrator/routing-and-reliability","name":"Perplexity","title":"Routing & Reliability - Perplexity","records":1}],"provenance":{"publisher":"Superpower Daily","source_count":6,"source_urls":["https://vercel.com/docs/ai-gateway/models-and-providers/model-fallbacks","https://vercel.com/docs/ai-gateway/models-and-providers/provider-filtering-and-ordering","https://vercel.com/docs/ai-gateway/models-and-providers/provider-timeouts","https://openrouter.ai/docs/guides/routing/model-fallbacks","https://openrouter.ai/docs/guides/routing/provider-selection","https://docs.perplexity.ai/docs/orchestrator/routing-and-reliability"],"methodology":["Reused 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.","Bounded 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.","Planned 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.","Perplexity 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","Perplexity 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","OpenRouter 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"],"snapshot_hash":"71c6bc210e866447fb1fc60d94e7470f80b980df0e022f25ec497a231c3ce186"},"distributions":{"csv":"https://superpowerdaily.com/api/research/perplexity-openrouter-or-vercel-which-failover-settings-preserve-the-requested-model-a93e8355?format=csv","json":"https://superpowerdaily.com/api/research/perplexity-openrouter-or-vercel-which-failover-settings-preserve-the-requested-model-a93e8355?format=json"}}