↑↓ move↵ openesc close

Overage / Compare / LLM APIs

Cerebras Inference vs Perplexity API pricing

Verified 2026-10-23 (2 days ago)Source: Cerebras Inference: www.cerebras.ai/pricing, Perplexity API: docs.perplexity.ai/guides/pricingVerified shows the older of the two.

Monthly cost at three volumes

Monthly cost of Cerebras Inference and Perplexity API at three volumes and at your own
VolumeCerebras InferencePerplexity API
small1M input, 200K output$0.50 / moGPT OSS 120B$0.01 / mopplx-decider-flash-v1.2
growing50M input, 10M output$25 / moGPT OSS 120B$0.50 / mopplx-decider-flash-v1.2
scale1B input, 200M output$500 / moGPT OSS 120B$10 / mopplx-decider-flash-v1.2
your volumeset above$25 / moGPT OSS 120B$0.50 / mopplx-decider-flash-v1.2

Each cell is the cheapest feasible plan, or the chosen model, at that volume, from the shared Overage cost function. "Cheapest model" only considers models with both an input and an output price listed. Volumes are example scenarios you can edit.

Cheapest model per service, USD per 1M tokens

Cheapest priced model of each service
ServiceCheapest modelInputOutputModels listed
Cerebras InferenceGPT OSS 120B$0.35$0.752
Perplexity APIpplx-decider-flash-v1.2$0.01$06

Every model

Every model of both services, USD per 1M tokens
ModelServiceInputOutput
GPT OSS 120BCerebras Inference$0.35$0.75
Qwen 3.8 27BCerebras Inference$0.99$1.49
pplx-embed-v1-0.6bPerplexity API$0.004unlisted
pplx-embed-context-v1-0.6bPerplexity API$0.008unlisted
pplx-decider-flash-v1.2Perplexity API$0.01$0
pplx-decider-v1.2Perplexity API$0.02$0
pplx-embed-v1-4bPerplexity API$0.03unlisted
pplx-embed-context-v1-4bPerplexity API$0.05unlisted

Models are compared by name and price, never by position. Pick one model per service, or "Cheapest model", in the cost table above.

Tiers, aligned by position

Tiers of Cerebras Inference and Perplexity API aligned by position: free, entry, mid, top
PositionCerebras InferencePerplexity API
Freeno tierno tier
EntryunlistedDeveloper*unlistedSearch API
Midno tierno tier
TopContact salesEnterpriseunlistedSearch API with Fast Search

Tightest rate limit

Tightest documented rate limit of each service
MeasureCerebras InferencePerplexity API
Tightest limitunlistedunlisted

Changes in the last 90 days

No changes recorded.

No change detected for either service in the last 90 days.