Provider Dossier · Aggregator
Novita AI
Low prices and a broad multimodal catalog.
The Datum Index verdict
Sound, with caveats
Ranked No. 19 of 20 in our composite reputation index, and currently improving.
≈ 3.9 / 5 aggregate · 210 reviewer notes
Composite index · reviewed 10 July 2026
Findings
- Novita AI holds a Datum Index composite reputation of 77 / 100 (≈ 3.9 / 5), ranked No. 19 of 20.
- It is a aggregator based in Singapore, founded 2023, offering open-weight model access.
- Its flagship offering is Pay-per-token open models, exposed through an OpenAI-compatible API.
- Indicative pricing is $0.30 / 1M tokens in / $0.40 / 1M tokens out (medium confidence).
- Reference throughput is ~41 tok/s with ~2400 ms time-to-first-token; stated uptime is 99.4%.
Novita AI enters our index at No. 19, a placement that reads as sound, with caveats. The composite rests on 210 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 pointed upward: reviewer sentiment has strengthened over recent quarters.
In its favour
Low prices and a broad multimodal catalog.
On the numbers that flatter it: open-weight access, 1 named compliance attestation, and a reference throughput of ~41 tokens per second.
Points of concern
Less enterprise track record than US incumbents.
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
Novita 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 Novita AI serves medium
GLM 5.2 (FP8)
| Window | TTFT ms — mean · p50 · p90 | Throughput tok/s — mean · p50 · p90 | ||||
|---|---|---|---|---|---|---|
| May 2026 | ~2530 | ~2360 | ~4860 | ~39 | ~42 | ~49 |
| June 2026 | ~2700 | ~2320 | ~5030 | ~41 | ~42 | ~49 |
| July 2026 | ~2630 | ~2360 | ~4270 | ~40 | ~42 | ~50 |
Llama 3.1 8B
| Window | TTFT ms — mean · p50 · p90 | Throughput tok/s — mean · p50 · p90 | ||||
|---|---|---|---|---|---|---|
| May 2026 | ~860 | ~800 | ~1340 | ~122 | ~127 | ~139 |
| June 2026 | ~930 | ~790 | ~1590 | ~126 | ~129 | ~147 |
| July 2026 | ~960 | ~860 | ~1710 | ~112 | ~119 | ~133 |
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 Novita AI yet — the ledger above opens as soon as the first practitioner submission clears verification.
Key Facts
The record, in brief
| Category | Aggregator |
|---|---|
| Headquarters | Singapore |
| Founded | 2023 |
| Model access | Open-weight |
| Flagship / reference | Pay-per-token open models · Llama 3.3 70B |
| OpenAI-compatible API | Yes |
| Indicative price (in / out) | $0.30 / 1M tokens / $0.40 / 1M tokens medium |
| Reference throughput | ~41 tok/s |
| Reference TTFT | ~2400 ms |
| Stated uptime | 99.4% |
| Compliance | GDPR |
| Composite reputation | 77 / 100 · ≈ 3.9 / 5 · 210 notes |
Reviewer Notes
What the field says
The 210 notes behind Novita 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: Low prices and a broad multimodal catalog. Detractors return to another: Less enterprise track record than US incumbents.
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 Novita AI's standing.