Pearl Research Labs
Explore Pearl Research Labs models on TrustedRouter with current routes, token pricing, policy sources, privacy posture, regional availability, and API support.
Pearl Research Labspearl
These privacy labels describe Pearl Research Labs, the upstream model provider. Confidential requires all three: verified provider compute, end-to-end encryption and explicit zero data retention. Account and billing metadata are outside the content-retention claim.
| Provider | Pearl Research Labs |
|---|---|
| API operator country | IL Legal home of the API operator, not an inference-location guarantee. |
| Headquarters | Tel Aviv-Yafo, Israel Provider-submitted operating and registered address; public policy for contact. Source; reviewed 2026-09-27. |
| Routing status | Active |
| Provider website | https://pearlresearch.ai/ |
| Models | 6 public models |
| Credits routes | 6 |
| Zero data retention | no |
| Verified confidential inference | Not verified |
| Policy note | Pearl Research states that it retains operational metadata for security and does not train on customer data. No public contractual zero-data-retention terms are linked, so TrustedRouter classifies these routes as Standard and excludes them from ZDR, confidential-compute, and E2EE routing. Policy source |
Inference locations
Provider API declarations are also available on each model's endpoint API. Direct chat and Responses replies separate advertised availability from serving location in usage.inference_location; the actual serving region remains unknown when not reported.
Where the upstream GPUs execute the model, not the provider's headquarters, API ingress, or data storage. ZDR and confidential inference do not by themselves restrict geography.
- Declared countries or regions
- United States (Central); Taiwan; Australia
Pearl supplied these serving regions in its marketplace application. This is provider-wide information, not a confirmed per-model or exhaustive failover list. GLM 5.3 Flash and DeepSeek V4.1 Flash do not declare regions in the reviewed native catalog. - Can locations change?
- Per-model placement and cross-region failover behavior require provider confirmation.
- Provider region pinning
- No per-request region-pinning contract verified in the reviewed API information.
- Pinning through TrustedRouter
- Not supported by the current TrustedRouter integration.
- Infrastructure declaration
- Multi-region provider: US Central, Taiwan and Australia declared; model-specific inference location and exhaustive failover scope unconfirmed.
- Evidence
- Provider-submitted marketplace information; no public per-model residency declaration. Reviewed .
Provider selection alone is not a region pin. TrustedRouter's US provider filter selects company jurisdiction, not GPU location. A regional gateway hostname does not pin a downstream GPU. For a binding residency requirement, confirm the model, region, failover scope and enforced controls before sending sensitive data.
Measured performance
160 samplesContinuously sampled across Pearl Research Labs's routed models: p50 TTFT, effective throughput, and success rate. Effective throughput uses provider-reported output tokens over complete request time. Unsupported route and probe-configuration rows are separated from provider downtime. No prompt or output content stored.
| p50 TTFT | 1964 ms |
|---|---|
| Effective throughput | 100 tok/s n=3 |
| Uptime | 99.38% |
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| z-ai/glm-5.3 | 1338 ms | 113 tok/s n=1 | 100.00% | — | 10 |
| deepseek/deepseek-v4.1-flash | 1964 ms | — | 99.29% | — | 140 |
| z-ai/glm-5.3-flash | 1263 ms | — | 100.00% | — | 4 |
| qwen/qwen3.8-flash-next | 1468 ms | — | 100.00% | — | 2 |
| qwen/qwen3.8-27b | 1570 ms | — | 100.00% | — | 3 |
| google/gemma-4-31b-it | 1726 ms | 100 tok/s n=2 | 100.00% | — | 1 |
Pearl Research Labs performance history · Full provider & model leaderboard.
Models served by Pearl Research Labs.
Each row links to pricing, provider, benchmark, and API pages for the model.
| Model | AI IQ | Context | Input | Cached input | Output |
|---|---|---|---|---|---|
deepseek/deepseek-v4.1-flashDeepSeek: DeepSeek V4.1 Flash |
IQ 126#21 | 1,048,576 | $0.1477/1M | $0.01/1M | $0.4431/1M |
google/gemma-4-31b-itGoogle: Gemma 4 31B |
IQ 101#110 | 262,144 | $0.09495/1M | $0.05275/1M | $0.3587/1M |
qwen/qwen3.8-27bQwen: Qwen3.8 27B |
IQ 116#50 | 65,536 | $0.211/1M | $0.05275/1M | $2.11/1M |
qwen/qwen3.8-flash-nextQwen: Qwen3.8-Flash-Next |
— | 262,144 | $0.1477/1M | $0.015825/1M | $0.47475/1M |
z-ai/glm-5.3Z.ai: GLM 5.3 |
IQ 125#24 | 1,048,576 | $1.1605/1M | $0.24265/1M | $3.6925/1M |
z-ai/glm-5.3-flashZ.ai: GLM 5.3 Flash |
IQ 120#42 | 1,048,576 | $0.07385/1M | $0.015825/1M | $0.2532/1M |
Questions
Does Pearl Research Labs have zero data retention?
TrustedRouter does not currently mark Pearl Research Labs as provider-level zero data retention. Use trustedrouter/zdr or provider.min_privacy=zdr to select a different eligible route, and review the linked policy source for changes.
Is Pearl Research Labs end-to-end encrypted?
TrustedRouter does not currently mark Pearl Research Labs as end-to-end encrypted at the provider boundary. The TrustedRouter gateway is still attested, but the selected provider normally receives the request in order to run the model. Use trustedrouter/e2e for the stronger route requirement.
Which Pearl Research Labs models are available through TrustedRouter?
This page currently lists 6 public Pearl Research Labs models, with live pricing, route count, context length, measured performance when available, and links to each model's provider and benchmark pages.