Provider Dossier · Specialist Hardware
SambaNova Cloud
High-throughput serving of large open models.
The Datum Index verdict
Sound, with caveats
Ranked No. 16 of 20 in our composite reputation index, and currently holding steady.
≈ 4.0 / 5 aggregate · 140 reviewer notes
Composite index · reviewed 10 July 2026
Findings
- SambaNova Cloud holds a Datum Index composite reputation of 79 / 100 (≈ 4.0 / 5), ranked No. 16 of 20.
- It is a specialist hardware based in Palo Alto, USA, founded 2017, offering open-weight model access.
- Its flagship offering is RDU-served open models, exposed through an OpenAI-compatible API.
- Indicative pricing is $0.60 / 1M tokens in / $1.20 / 1M tokens out (medium confidence).
- Reference throughput is ~292 tok/s with ~2030 ms time-to-first-token; stated uptime is 99.4%.
SambaNova Cloud enters our index at No. 16, a placement that reads as sound, with caveats. The composite rests on 140 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
High-throughput serving of large open models.
On the numbers that flatter it: open-weight access, 1 named compliance attestation, and a reference throughput of ~292 tokens per second.
Points of concern
Smaller ecosystem and tooling footprint.
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
SambaNova Cloud 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 SambaNova Cloud serves high
Llama 3.3 70B
| Window | TTFT ms — mean · p50 · p90 | Throughput tok/s — mean · p50 · p90 | ||||
|---|---|---|---|---|---|---|
| May 2026 | ~2300 | ~1970 | ~4030 | ~280 | ~301 | ~341 |
| June 2026 | ~2120 | ~1970 | ~4270 | ~292 | ~301 | ~333 |
| July 2026 | ~2140 | ~1990 | ~4120 | ~279 | ~297 | ~318 |
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 SambaNova Cloud yet — the ledger above opens as soon as the first practitioner submission clears verification.
Key Facts
The record, in brief
| Category | Specialist Hardware |
|---|---|
| Headquarters | Palo Alto, USA |
| Founded | 2017 |
| Model access | Open-weight |
| Flagship / reference | RDU-served open models · Llama 3.3 70B |
| OpenAI-compatible API | Yes |
| Indicative price (in / out) | $0.60 / 1M tokens / $1.20 / 1M tokens medium |
| Reference throughput | ~292 tok/s |
| Reference TTFT | ~2030 ms |
| Stated uptime | 99.4% |
| Compliance | SOC 2 Type II |
| Composite reputation | 79 / 100 · ≈ 4.0 / 5 · 140 notes |
Reviewer Notes
What the field says
The 140 notes behind SambaNova Cloud'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: High-throughput serving of large open models. Detractors return to another: Smaller ecosystem and tooling footprint.
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 SambaNova Cloud's standing.