Provider Dossier · Specialist Application
Perplexity API
Built-in web-search grounding with citations.
The Datum Index verdict
Recommended with confidence
Ranked No. 13 of 20 in our composite reputation index, and currently holding steady.
≈ 4.1 / 5 aggregate · 410 reviewer notes
Composite index · reviewed 10 July 2026
Findings
- Perplexity API holds a Datum Index composite reputation of 82 / 100 (≈ 4.1 / 5), ranked No. 13 of 20.
- It is a specialist application based in San Francisco, USA, founded 2022, offering open & proprietary model access.
- Its flagship offering is Sonar (search-grounded), exposed through an OpenAI-compatible API.
- Indicative pricing is $1.00 / 1M tokens in / $1.00 / 1M tokens out (medium confidence).
- Reference throughput is ~70 tok/s with ~1000 ms time-to-first-token; stated uptime is 99.5%.
Perplexity API enters our index at No. 13, a placement that reads as recommended with confidence. The composite rests on 410 reviewer notes gathered across the public record, and it is best understood not as a score out of ten but as a standing among peers. The trend line is flat: reviewer sentiment has held steady over recent quarters.
In its favour
Built-in web-search grounding with citations.
On the numbers that flatter it: open & proprietary access, 2 named compliance attestations, and a reference throughput of ~70 tokens per second.
Points of concern
Optimized for search Q&A rather than general serving.
The caveat a buyer should price in before committing production traffic. As with every entry, we weigh it against the field rather than against perfection.
Incident & Uptime Note
The record of being there
Perplexity API states an availability of 99.5%. Held over a full year, that headline implies on the order of 43.8 hours of cumulative unavailability — a useful sense of scale, though real incidents cluster rather than spread evenly, and a single bad afternoon can outweigh a quiet quarter.
Observatory Panel
Latency & throughput, in distribution
Monthly panels across the models Perplexity API serves medium
Sonar Pro
| Window | TTFT ms — mean · p50 · p90 | Throughput tok/s — mean · p50 · p90 | ||||
|---|---|---|---|---|---|---|
| May 2026 | ~1100 | ~1040 | ~2020 | ~65 | ~68 | ~73 |
| June 2026 | ~1200 | ~1070 | ~2080 | ~63 | ~65 | ~78 |
| July 2026 | ~1070 | ~980 | ~2110 | ~68 | ~71 | ~82 |
Sonar
| Window | TTFT ms — mean · p50 · p90 | Throughput tok/s — mean · p50 · p90 | ||||
|---|---|---|---|---|---|---|
| May 2026 | ~890 | ~780 | ~1660 | ~115 | ~124 | ~145 |
| June 2026 | ~970 | ~830 | ~1610 | ~109 | ~116 | ~137 |
| July 2026 | ~920 | ~780 | ~1450 | ~118 | ~122 | ~130 |
All figures are single-stream, per-request rates as one user would see them — never aggregate accelerator throughput. Serving modes are not comparable with one another: shared serverless APIs batch many tenants per accelerator, dedicated and self-served deployments hand one tenant the whole card, and specialist silicon is a regime of its own. Read each figure within its mode.
No field returns on record for Perplexity API yet — the ledger above opens as soon as the first practitioner submission clears verification.
Key Facts
The record, in brief
| Category | Specialist Application |
|---|---|
| Headquarters | San Francisco, USA |
| Founded | 2022 |
| Model access | Open & proprietary |
| Flagship / reference | Sonar (search-grounded) · Search-augmented open models |
| OpenAI-compatible API | Yes |
| Indicative price (in / out) | $1.00 / 1M tokens / $1.00 / 1M tokens medium |
| Reference throughput | ~70 tok/s |
| Reference TTFT | ~1000 ms |
| Stated uptime | 99.5% |
| Compliance | SOC 2 Type II · GDPR |
| Composite reputation | 82 / 100 · ≈ 4.1 / 5 · 410 notes |
Reviewer Notes
What the field says
The 410 notes behind Perplexity API's standing are drawn from the accumulated public verdict of practitioners — the recurring praises and the recurring gripes — rather than from any single survey. Two themes dominate. Admirers return to one point above all: Built-in web-search grounding with citations. Detractors return to another: Optimized for search Q&A rather than general serving.
We publish neither individual reviews nor reviewer identities; the composite is an editorial synthesis, and the reviewer-note count is an order-of-magnitude indication of how much public signal informs it.
Related dossiers · see also
Peer entries in the same or adjacent category, for comparison against Perplexity API's standing.
- No. 12 Cerebras Inference Specialist Hardware Recommended with confidence 82/100
- No. 10 Mistral La Plateforme Frontier Lab Recommended with confidence 83/100
- No. 11 Cheapestinference Subscription (flat-rate) Recommended with confidence 83/100
- No. 14 DeepInfra Aggregator Recommended with confidence 81/100