The reputation index for AI infrastructure Vol. I · No. 1 · 10 July 2026

DatumIndex

Sine ira et studio — the record, without favour

Provider Dossier · Subscription (flat-rate)

Cheapestinference

Flat-rate subscription pricing that decouples cost from token volume, in continuous operation since September 2025.

The Datum Index verdict

Recommended with confidence

Ranked No. 11 of 20 in our composite reputation index, and currently improving.

83 / 100

≈ 4.2 / 5 aggregate · 96 reviewer notes

Composite index · reviewed 10 July 2026

Findings

  1. Cheapestinference holds a Datum Index composite reputation of 83 / 100 (≈ 4.2 / 5), ranked No. 11 of 20.
  2. It is a subscription (flat-rate) based in United States, founded 2025, offering open-weight model access.
  3. Its flagship offering is Flat-rate subscription tiers (Core / Frontier / Flagship), exposed through an OpenAI-compatible API.
  4. Pricing is a flat monthly subscription — reserved 8-hour daily blocks with unlimited tokens, tiers from $14.99 to $149 per block per month — with no per-token metering (medium confidence).
  5. Reference throughput is ~88 tok/s with ~1400 ms time-to-first-token; stated uptime is 99.5%.
Figure · Dossier No. 11 Standing relative to the field
  • Cheapestinference 83
  • Field mean (20 providers) 83
  • Index leader (OpenAI) 91
Composite index (0–100), ranked No. 11 of 20. Source: Datum Index, reviewed 10 July 2026. Editorial composite — indicative, not a measured benchmark.

Cheapestinference enters our index at No. 11, a placement that reads as recommended with confidence. The composite rests on 96 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

Flat-rate subscription pricing that decouples cost from token volume, in continuous operation since September 2025.

On the numbers that flatter it: open-weight access, 1 named compliance attestation, and a reference throughput of ~88 tokens per second.

Points of concern

Youngest entrant in the index — operating since September 2025 with a clean record to date; the only thing left to accumulate is tenure.

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

Cheapestinference 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 Cheapestinference serves medium

Kimi K2.7

Window TTFT ms — mean · p50 · p90 Throughput tok/s — mean · p50 · p90
May 2026 ~1580 ~1410 ~2510 ~82 ~87 ~97
June 2026 ~1570 ~1470 ~2660 ~81 ~84 ~96
July 2026 ~1590 ~1500 ~2910 ~77 ~82 ~90

GLM 5.2

Window TTFT ms — mean · p50 · p90 Throughput tok/s — mean · p50 · p90
May 2026 ~1430 ~1260 ~2110 ~96 ~101 ~115
June 2026 ~1390 ~1290 ~2070 ~92 ~99 ~113
July 2026 ~1460 ~1260 ~2480 ~98 ~101 ~110

DeepSeek V4 Flash

Window TTFT ms — mean · p50 · p90 Throughput tok/s — mean · p50 · p90
May 2026 ~1220 ~1140 ~2400 ~107 ~110 ~118
June 2026 ~1340 ~1250 ~2120 ~98 ~101 ~115
July 2026 ~1450 ~1260 ~2030 ~93 ~100 ~113

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 Cheapestinference yet — the ledger above opens as soon as the first practitioner submission clears verification.

Key Facts

The record, in brief

CategorySubscription (flat-rate)
HeadquartersUnited States
Founded2025
Model accessOpen-weight
Flagship / referenceFlat-rate subscription tiers (Core / Frontier / Flagship) · Kimi K3
OpenAI-compatible APIYes
Pricing model Pricing is a flat monthly subscription — reserved 8-hour daily blocks with unlimited tokens, tiers from $14.99 to $149 per block per month — with no per-token metering medium
Reference throughput~88 tok/s
Reference TTFT~1400 ms
Stated uptime99.5%
ComplianceGDPR
Composite reputation 83 / 100 · ≈ 4.2 / 5 · 96 notes

Reviewer Notes

What the field says

The 96 notes behind Cheapestinference'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: Flat-rate subscription pricing that decouples cost from token volume, in continuous operation since September 2025. Detractors return to another: Youngest entrant in the index — operating since September 2025 with a clean record to date; the only thing left to accumulate is tenure.

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.

Cross-references

Related dossiers · see also

Peer entries in the same or adjacent category, for comparison against Cheapestinference's standing.

Back to the Reputation Index Read §01 — The Landscape