Provider Dossier · GPU Cloud
Lepton AI
Developer-friendly platform with tuned serving.
The Datum Index verdict
Sound, with caveats
Ranked No. 18 of 20 in our composite reputation index, and currently holding steady.
≈ 3.9 / 5 aggregate · 145 reviewer notes
Composite index · reviewed 10 July 2026
Findings
- Lepton AI holds a Datum Index composite reputation of 78 / 100 (≈ 3.9 / 5), ranked No. 18 of 20.
- It is a gpu cloud based in Cupertino, USA, founded 2023, offering open-weight model access.
- Its flagship offering is Fast open-model endpoints, exposed through an OpenAI-compatible API.
- Indicative pricing is $0.50 / 1M tokens in / $0.50 / 1M tokens out (medium confidence).
- Reference throughput is ~70 tok/s with ~1400 ms time-to-first-token; stated uptime is 99.4%.
Lepton AI enters our index at No. 18, a placement that reads as sound, with caveats. The composite rests on 145 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
Developer-friendly platform with tuned serving.
On the numbers that flatter it: open-weight access, 2 named compliance attestations, and a reference throughput of ~70 tokens per second.
Points of concern
Smaller brand footprint post-acquisition.
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
Lepton AI states an availability of 99.4%. Held over a full year, that headline implies on the order of 52.6 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 Lepton AI serves medium
Llama 3.3 70B
| Window | TTFT ms — mean · p50 · p90 | Throughput tok/s — mean · p50 · p90 | ||||
|---|---|---|---|---|---|---|
| May 2026 | ~1570 | ~1410 | ~2600 | ~67 | ~69 | ~77 |
| June 2026 | ~1750 | ~1480 | ~2850 | ~63 | ~66 | ~77 |
| July 2026 | ~1710 | ~1460 | ~2400 | ~65 | ~67 | ~73 |
Mixtral 8x7B
| Window | TTFT ms — mean · p50 · p90 | Throughput tok/s — mean · p50 · p90 | ||||
|---|---|---|---|---|---|---|
| May 2026 | ~1380 | ~1170 | ~2110 | ~91 | ~97 | ~111 |
| June 2026 | ~1300 | ~1150 | ~2410 | ~94 | ~99 | ~106 |
| July 2026 | ~1380 | ~1230 | ~2580 | ~90 | ~93 | ~98 |
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 Lepton AI yet — the ledger above opens as soon as the first practitioner submission clears verification.
Key Facts
The record, in brief
| Category | GPU Cloud |
|---|---|
| Headquarters | Cupertino, USA |
| Founded | 2023 |
| Model access | Open-weight |
| Flagship / reference | Fast open-model endpoints · Llama 3.3 70B |
| OpenAI-compatible API | Yes |
| Indicative price (in / out) | $0.50 / 1M tokens / $0.50 / 1M tokens medium |
| Reference throughput | ~70 tok/s |
| Reference TTFT | ~1400 ms |
| Stated uptime | 99.4% |
| Compliance | SOC 2 Type II · GDPR |
| Composite reputation | 78 / 100 · ≈ 3.9 / 5 · 145 notes |
Reviewer Notes
What the field says
The 145 notes behind Lepton AI'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: Developer-friendly platform with tuned serving. Detractors return to another: Smaller brand footprint post-acquisition.
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 Lepton AI's standing.