Perplexity / Llama 3.1 Sonar
Historical Perplexity-hosted model identity preserved from its original provider announcement and lifecycle notices.
Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.
Not verified for this exact historical release. Model names alone are not a numeric context/parameter specification; current Sonar facts are not inherited.
Not verified for this exact historical release. Model names alone are not a numeric context/parameter specification; current Sonar facts are not inherited.
Not verified for this exact historical release. Model names alone are not a numeric context/parameter specification; current Sonar facts are not inherited.
Not verified for this exact historical release. Model names alone are not a numeric context/parameter specification; current Sonar facts are not inherited.
Not verified for this exact historical release. Model names alone are not a numeric context/parameter specification; current Sonar facts are not inherited.
Not verified for this exact historical release. Model names alone are not a numeric context/parameter specification; current Sonar facts are not inherited.
Not verified for this exact historical release. Model names alone are not a numeric context/parameter specification; current Sonar facts are not inherited.
The changelog gives the announcement month, not an exact launch day.
Not verified for this exact historical release. Model names alone are not a numeric context/parameter specification; current Sonar facts are not inherited.
Not verified for this exact historical release. Model names alone are not a numeric context/parameter specification; current Sonar facts are not inherited.
Not verified for this exact historical release. Model names alone are not a numeric context/parameter specification; current Sonar facts are not inherited.
Not verified for this exact historical release. Model names alone are not a numeric context/parameter specification; current Sonar facts are not inherited.
Not verified for this exact historical release. Model names alone are not a numeric context/parameter specification; current Sonar facts are not inherited.
Not verified for this exact historical release. Model names alone are not a numeric context/parameter specification; current Sonar facts are not inherited.
Not verified for this exact historical release. Model names alone are not a numeric context/parameter specification; current Sonar facts are not inherited.
Provider lists an online/chat language model. No media support inferred.
The marketed 32k/128k string is retained in the identity; exact usable input/output limits are unverified.
Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.
llama-3.1-sonar-large-128k-chatExact provider-listed historical selector.
Endpoint pricing has not been collected. Check the provider for applicable rates.
Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.
Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.
The system processes eligible input and retains reusable state.
Reuse depends on matching input, session state and the cache policy.
Reusing state can reduce repeated work. Any charges follow the billing rules below.
llama-3.1-sonar-large-128k-chatHistorical exact-model cache contract not verified. Current Agent API cache rates are not inherited.
Historical exact-model cache contract not verified. Current Agent API cache rates are not inherited.
Historical exact-model cache contract not verified. Current Agent API cache rates are not inherited.
Historical exact-model cache contract not verified. Current Agent API cache rates are not inherited.
Historical exact-model cache contract not verified. Current Agent API cache rates are not inherited.
Historical exact-model cache contract not verified. Current Agent API cache rates are not inherited.
Historical exact-model cache contract not verified. Current Agent API cache rates are not inherited.
Historical exact-model cache contract not verified. Current Agent API cache rates are not inherited.
No verified cache rate for this endpoint. An empty rate is not a zero charge.
Caching reviewed 14 Oct 2026No benchmark observations have been added for this model. We do not turn a vendor description into a performance score.
Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.
Closed-weight distribution inference: the provider distinguishes its own PPLX/Sonar offerings from separately served public instruct models. The exact derivative weights were not found in the reviewed official inventory. This does not claim that public Mistral/Llama base weights are proprietary.
Classification evidence (opens in a new tab)